Skip to main content
:fellow professors
:fellow professors
:all professors

Michele Magno

Fellow Professor of Embedded Systems & Edge AI 

title
PD Dr. 
email
location
ETH Zürich 
:back to overview

Publications

TitleYear
End-to-end multicamera event-image stitching and object detection on the edge
2025
Julian Moosmann, Jakub Mandula, Jiayong Li, Philipp Mayer, Luca Benini, Michele Magno
Target and Background Signatures XI: Traditional Methods and Artificial Intelligence 13…
:read more
Authors:Julian Moosmann, Jakub Mandula, Jiayong Li, Philipp Mayer, Luca Benini, Michele Magno
Publication date:10/28/2025
Journal:Target and Background Signatures XI: Traditional Methods and Artificial Intelligence
Volume:13673
Pages:225-235
Publisher:SPIE
Description:Wide Field-of-View (FoV) and high-resolution imaging are crucial capabilities for visual surveillance. However, they impose significant computational demands, posing significant challenges for embedded platforms targeting real-time performance. Event-based cameras help in curtailing computational effort by capturing only brightness changes at the pixel level, thereby reducing data volume while enhancing temporal resolution and dynamic range. Moreover, their inherent sensitivity to object edges improves the visibility of camouflage patterns. This work presents a real-time, wide-FoV event-based vision system based on a dual-camera setup with onboard object detection and tracking. The proposed system implements a low-latency end-to-end pipeline encompassing data capture, event-stream processing, image stitching, object detection, and tracking. Custom CUDA kernels are developed for efficient event …
:view less
QuantSparse: Comprehensively Compressing Video Diffusion Transformer with Model Quantization and Attention Sparsification
2025
Weilun Feng, Chuanguang Yang, Haotong Qin, Mingqiang Wu, Yuqi Li, Xiangqi Li, Zhulin An…
arXiv preprint arXiv:2509.23681
:read more
Authors:Weilun Feng, Chuanguang Yang, Haotong Qin, Mingqiang Wu, Yuqi Li, Xiangqi Li, Zhulin An, Libo Huang, Yulun Zhang, Michele Magno, Yongjun Xu
Publication date:09/28/2025
Journal:arXiv preprint arXiv:2509.23681
Description:Diffusion transformers exhibit remarkable video generation capability, yet their prohibitive computational and memory costs hinder practical deployment. Model quantization and attention sparsification are two promising directions for compression, but each alone suffers severe performance degradation under aggressive compression. Combining them promises compounded efficiency gains, but naive integration is ineffective. The sparsity-induced information loss exacerbates quantization noise, leading to amplified attention shifts. To address this, we propose textbf{QuantSparse}, a unified framework that integrates model quantization with attention sparsification. Specifically, we introduce textit{Multi-Scale Salient Attention Distillation}, which leverages both global structural guidance and local salient supervision to mitigate quantization-induced bias. In addition, we develop textit{Second-Order Sparse Attention Reparameterization}, which exploits the temporal stability of second-order residuals to efficiently recover information lost under sparsity. Experiments on HunyuanVideo-13B demonstrate that QuantSparse achieves 20.88 PSNR, substantially outperforming the state-of-the-art quantization baseline Q-VDiT (16.85 PSNR), while simultaneously delivering a textbf{3.68} reduction in storage and textbf{1.88} acceleration in end-to-end inference. Our code will be released in https://github.com/wlfeng0509/QuantSparse.
Resources:[PDF] from arxiv.org
:view less
Quantized Visual Geometry Grounded Transformer
2025
Weilun Feng, Haotong Qin, Mingqiang Wu, Chuanguang Yang, Yuqi Li, Xiangqi Li, Zhulin An…
arXiv preprint arXiv:2509.21302
:read more
Authors:Weilun Feng, Haotong Qin, Mingqiang Wu, Chuanguang Yang, Yuqi Li, Xiangqi Li, Zhulin An, Libo Huang, Yulun Zhang, Michele Magno, Yongjun Xu
Publication date:09/25/2025
Journal:arXiv preprint arXiv:2509.21302
Description:Learning-based 3D reconstruction models, represented by Visual Geometry Grounded Transformers (VGGTs), have made remarkable progress with the use of large-scale transformers. Their prohibitive computational and memory costs severely hinder real-world deployment. Post-Training Quantization (PTQ) has become a common practice for compressing and accelerating models. However, we empirically observe that PTQ faces unique obstacles when compressing billion-scale VGGTs: the data-independent special tokens induce heavy-tailed activation distributions, while the multi-view nature of 3D data makes calibration sample selection highly unstable. This paper proposes the first Quantization framework for VGGTs, namely QuantVGGT. This mainly relies on two technical contributions: First, we introduce Dual-Smoothed Fine-Grained Quantization, which integrates pre-global Hadamard rotation and post-local channel smoothing to mitigate heavy-tailed distributions and inter-channel variance robustly. Second, we design Noise-Filtered Diverse Sampling, which filters outliers via deep-layer statistics and constructs frame-aware diverse calibration clusters to ensure stable quantization ranges. Comprehensive experiments demonstrate that QuantVGGT achieves the state-of-the-art results across different benchmarks and bit-width, surpassing the previous state-of-the-art generic quantization method with a great margin. We highlight that our 4-bit QuantVGGT can deliver a 3.7 memory reduction and 2.5 acceleration in real-hardware inference, while maintaining reconstruction accuracy above 98% of its full-precision counterpart. This …
Resources:[PDF] from arxiv.org
:view less
xMasonV2: An Open-Source Model Extension for Cascaded Transducer Arrays
2025
Gabriele Spisani, Philipp Mayer, Sofia Papa, Francesco Greco, Michele Magno, Luca Benin…
2025 IEEE International Ultrasonics Symposium (IUS), 1-4
:read more
Authors:Gabriele Spisani, Philipp Mayer, Sofia Papa, Francesco Greco, Michele Magno, Luca Benini, Christoph Leitner
Publication date:09/15/2025
Journal:2025 IEEE International Ultrasonics Symposium (IUS)
Pages:1-4
Publisher:IEEE
Description:Flexible polymer piezoelectrics such as P(VDF-TrFE) are increasingly employed in wearable ultrasound transducers, yet their high dielectric and elastic losses, together with the complexity of multilayer architectures, demand accurate and accessible design tools. We present xMasonV2, an open-source Python framework that translates a previously published state-space formulation of the Mason equivalent circuit into a practical simulation tool. This extension supports cascaded transducers with arbitrary layer configurations and incorporates dielectric and mechanical losses, thereby bridging the gap between theoretical models and design needs. Validation was performed against custom-fabricated P(VDF-TrFE) and PZT double-stack transducers as well as published single-layer datasets. Across four modes of the P(VDF-TrFE) stack, predicted resonance frequencies deviated by less than ±0.5MHz, corresponding to …
:view less
ModulUS: A Sandbox for High-Resolution Wearable Ultrasound Development
2025
Christoph Leitner, Marco Giordano, Martin Tanner, Federico Villani, Michele Magno, Luca…
2025 IEEE International Ultrasonics Symposium (IUS), 1-4
:read more
Authors:Christoph Leitner, Marco Giordano, Martin Tanner, Federico Villani, Michele Magno, Luca Benini
Publication date:09/15/2025
Journal:2025 IEEE International Ultrasonics Symposium (IUS)
Pages:1-4
Publisher:IEEE
Description:We introduce ModulUS, a modular sandbox platform for wearable ultrasound (US) development. The four-board system integrates a 32-channel pulser, an analog frontend (AFE) with bandwidth reduction, and an ARM Cortex-M4 microcontroller (MCU) with a dual 5Msps, 12bit analog-digital converter (ADC), each implemented as a swappable module to support rapid prototyping and evaluation of alternative circuit architectures. To demonstrate its functionality, we validated the AFE board, which reduces the effective signal bandwidth by a factor of 4 while preserving structural features, with envelope fidelity confirmed against digital Hilbert transforms (R2 = 0.88). Compared to State-of-the-Art (SoA) platforms, ModulUS-derived designs set a new benchmark in power efficiency, achieving the lowest reported average power normalized by excitation frequency (0.6mW/MHz), down to two orders of magnitude below …
:view less
Efficient and Accurate Downfacing Visual Inertial Odometry
2025
Jonas Kühne, Christian Vogt, Michele Magno, Luca Benini
IEEE Internet of Things Journal
:read more
Authors:Jonas Kühne, Christian Vogt, Michele Magno, Luca Benini
Publication date:09/11/2025
Journal:IEEE Internet of Things Journal
Publisher:IEEE
Description:Visual Inertial Odometry (VIO) is a widely used computer vision method that determines an agent’s movement through a camera and an IMU sensor. This paper presents an efficient and accurate VIO pipeline optimized for applications on micro- and nano-UAVs. The proposed design incorporates state-of-the-art feature detection and tracking methods (SuperPoint, PX4FLOW, ORB), all optimized and quantized for emerging RISC-V-based ultra-low-power parallel systems on chips (SoCs). Furthermore, by employing a rigid body motion model, the pipeline reduces estimation errors and achieves improved accuracy in planar motion scenarios. The pipeline’s suitability for real-time VIO is assessed on an ultra-low-power SoC in terms of compute requirements and tracking accuracy after quantization. The pipeline, including the three feature tracking methods, was implemented on the SoC for real-world validation. This …
Resources:[PDF] from arxiv.org
:view less
Wireless Low-Latency Synchronization for Body-Worn Multi-Node Systems in Sports
2025
Nico Krull, Lukas Schulthess, Michele Magno, Luca Benini, Christoph Leitner
arXiv preprint arXiv:2509.06541
:read more
Authors:Nico Krull, Lukas Schulthess, Michele Magno, Luca Benini, Christoph Leitner
Publication date:09/08/2025
Journal:arXiv preprint arXiv:2509.06541
Description:Biomechanical data acquisition in sports demands sub-millisecond synchronization across distributed body-worn sensor nodes. This study evaluates and characterizes the Enhanced ShockBurst (ESB) protocol from Nordic Semiconductor under controlled laboratory conditions for wireless, low-latency command broadcasting, enabling fast event updates in multi-node systems. Through systematic profiling of protocol parameters, including cyclic-redundancy-check modes, bitrate, transmission modes, and payload handling, we achieve a mean Device-to-Device (D2D) latency of 504.99 +- 96.89 us and a network-to-network core latency of 311.78 +- 96.90 us using a one-byte payload with retransmission optimization. This performance significantly outperforms Bluetooth Low Energy (BLE), which is constrained by a 7.5 ms connection interval, by providing deterministic, sub-millisecond synchronization suitable for high-frequency (500 Hz to 1000 Hz) biosignals. These results position ESB as a viable solution for time-critical, multi-node wearable systems in sports, enabling precise event alignment and reliable high-speed data fusion for advanced athlete monitoring and feedback applications.
Resources:[PDF] from arxiv.org
:view less
Optimizing Energy Consumption and Coverage in Underwater Magnetic Induction-Assisted Acoustic WSNs Using Learning Automata-Based Cooperative MIMO Formation
2025
Qingyan Ren, Yanjing Sun, Sizhen Bian, Michele Magno
IEEE Transactions on Network Science and Engineering 12 (5), 3527-3540
:read more
Authors:Qingyan Ren, Yanjing Sun, Sizhen Bian, Michele Magno
Publication date:08/22/2025
Journal:IEEE Transactions on Network Science and Engineering
Volume:12
Issue:5
Pages:3527-3540
Publisher:IEEE
Description:Underwater Wireless Sensor Networks (UWSNs) offer promising exploration capabilities in challenging underwater environments, necessitating a focus on reducing energy consumption while guaranteeing monitoring coverage. Underwater magnetic induction (MI)-assisted acoustic cooperative multiple-input–multiple-output (MIMO) WSNs have shown advantages over traditional UWSNs in various aspects due to the seamless integration of sensor networks and communication technology. However, as an emerging topic, a critical gap exists, as they often overlook the vital considerations of monitoring coverage requirements and the dynamic nature of the unknown underwater environment. Moreover, these advantages can be further enhanced by harnessing the collaborative potential of multiple independent underwater nodes. This paper introduces a significant advancement to the field of MI-assisted Acoustic …
:view less
Bridging Generalization and Personalization in Human Activity Recognition via On-Device Few-Shot Learning
2025
Pixi Kang, Julian Moosmann, Mengxi Liu, Bo Zhou, Michele Magno, Paul Lukowicz, Sizhen Bian
arXiv preprint arXiv:2508.15413
:read more
Authors:Pixi Kang, Julian Moosmann, Mengxi Liu, Bo Zhou, Michele Magno, Paul Lukowicz, Sizhen Bian
Publication date:08/21/2025
Journal:arXiv preprint arXiv:2508.15413
Description:Human Activity Recognition (HAR) with different sensing modalities requires both strong generalization across diverse users and efficient personalization for individuals. However, conventional HAR models often fail to generalize when faced with user-specific variations, leading to degraded performance. To address this challenge, we propose a novel on-device few-shot learning framework that bridges generalization and personalization in HAR. Our method first trains a generalizable representation across users and then rapidly adapts to new users with only a few labeled samples, updating lightweight classifier layers directly on resource-constrained devices. This approach achieves robust on-device learning with minimal computation and memory cost, making it practical for real-world deployment. We implement our framework on the energy-efficient RISC-V GAP9 microcontroller and evaluate it on three benchmark datasets (RecGym, QVAR-Gesture, Ultrasound-Gesture). Across these scenarios, post-deployment adaptation improves accuracy by 3.73%, 17.38%, and 3.70%, respectively. These results demonstrate that few-shot on-device learning enables scalable, user-aware, and energy-efficient wearable human activity recognition by seamlessly uniting generalization and personalization. The related framework is open sourced for further researchfootnote{https://github.com/kangpx/onlineTiny2023}.
Resources:[PDF] from arxiv.org
:view less
Optimized Blood Pressure Prediction with a Hybrid CNN-SVR Model Using Multi-Wavelength PPG
2025
Chiara Botrugno, Kanika Dheman, Pietro Bonazzi, Francesco Dell’Olio, Michele Magno
IEEE Transactions on Instrumentation and Measurement
:read more
Authors:Chiara Botrugno, Kanika Dheman, Pietro Bonazzi, Francesco Dell’Olio, Michele Magno
Publication date:08/18/2025
Journal:IEEE Transactions on Instrumentation and Measurement
Publisher:IEEE
Description:Noninvasive vital sign monitoring, especially blood pressure (BP), is crucial for evaluating overall health and identifying early indicators of medical issues. Photoplethysmography (PPG) is a noninvasive technique increasingly adopted in vital sign monitoring, as it allows for the continuous and precise measurement of cardiac-related signals. This technology is sensitive to fluctuations in blood volume within blood vessels, enabling real-time tracking of each heartbeat and identification of any irregularities. This study investigates the effectiveness of machine learning (ML) models for predicting arterial pressure based solely on PPG signals, utilizing a novel dataset and multiwavelength sensor technology that captures data from four distinct wavelengths: infrared (IR), red, green, and blue. The participant pool consisted of 88 individuals, with each measurement lasting 30 s at a sampling rate of 100 Hz. After a dedicated phase of …
:view less
Event-Priori-Based Vision-Language Model for Efficient Visual Understanding
2025
Haotong Qin, Cheng Hu, Michele Magno
International Joint Conference on Artificial Intelligence, 16-30
:read more
Authors:Haotong Qin, Cheng Hu, Michele Magno
Publication date:08/15/2025
Journal:International Joint Conference on Artificial Intelligence
Pages:16-30
Publisher:Springer Nature Singapore
Description:Large Language Model (LLM)-based Vision-Language Models (VLMs) have substantially extended the boundaries of visual understanding capabilities. However, their high computational demands hinder deployment on resource-constrained edge devices. A key source of inefficiency stems from the VLM’s need to process dense and redundant visual information. Visual inputs contain significant regions irrelevant to text semantics, rendering the associated computations ineffective for inference. This paper introduces a novel Event-Priori-Based Vision-Language Model, termed EP-VLM. Its core contribution is a novel mechanism leveraging motion priors derived from dynamic event vision to enhance VLM efficiency. Inspired by human visual cognition, EP-VLM first employs event data to guide the patch-wise sparsification of RGB visual inputs, progressively concentrating VLM computation on salient regions of the …
Resources:[PDF] from arxiv.org
:view less
SQ-VDiT: Accurate Quantized Video Diffusion Transformer with Salient Data and Sparse Token Distillation
2025
Weilun Feng, Haotong Qin, Chuanguang Yang, Xiangqi Li, Han Yang, Yuqi Li, Zhulin An, Li…
arXiv preprint arXiv:2508.04016
:read more
Authors:Weilun Feng, Haotong Qin, Chuanguang Yang, Xiangqi Li, Han Yang, Yuqi Li, Zhulin An, Libo Huang, Michele Magno, Yongjun Xu
Publication date:08/06/2025
Journal:arXiv preprint arXiv:2508.04016
Description:Diffusion transformers have emerged as the mainstream paradigm for video generation models. However, the use of up to billions of parameters incurs significant computational costs. Quantization offers a promising solution by reducing memory usage and accelerating inference. Nonetheless, we observe that the joint modeling of spatial and temporal information in video diffusion models (V-DMs) leads to extremely long token sequences, which introduces high calibration variance and learning challenges. To address these issues, we propose SQ-VDiT, a post-training quantization framework for V-DMs that leverages Salient data and Sparse token distillation. During the calibration phase, we identify that quantization performance is highly sensitive to the choice of calibration data. To mitigate this, we introduce textit{Hessian-aware Salient Data Selection}, which constructs high-quality calibration datasets by considering both diffusion and quantization characteristics unique to V-DMs. To tackle the learning challenges, we further analyze the sparse attention patterns inherent in V-DMs. Based on this observation, we propose textit{Attention-guided Sparse Token Distillation}, which exploits token-wise attention distributions to emphasize tokens that are more influential to the model's output. Under W4A6 quantization, SQ-VDiT achieves lossless performance while delivering model compression and inference acceleration. Code will be available at https://github.com/wlfeng0509/s2q-vdit.
:view less
Bridging Generalization and Personalization in Wearable Human Activity Recognition via On-Device Few-Shot Learning
2025
Pixi Kang, Julian Moosmann, Mengxi Liu, Bo Zhou, Michele Magno, Paul Lukowicz, Sizhen Bian
arXiv e-prints, arXiv: 2508.15413
:read more
Authors:Pixi Kang, Julian Moosmann, Mengxi Liu, Bo Zhou, Michele Magno, Paul Lukowicz, Sizhen Bian
Publication date:08/01/2025
Journal:arXiv e-prints
Pages:arXiv: 2508.15413
Description:Human Activity Recognition (HAR) using wearable devices has advanced significantly in recent years, yet its generalization remains limited when models are deployed to new users. This degradation in performance is primarily due to user-induced concept drift (UICD), highlighting the importance of efficient personalization. In this paper, we present a hybrid framework that first generalizes across users and then rapidly adapts to individual users using few-shot learning directly on-device. By updating only the classifier layer with user-specific data, our method achieves robust personalization with minimal computational and memory overhead. We implement this framework on the energy-efficient RISC-V-based GAP9 microcontroller and validate it across three diverse HAR scenarios: RecGym, QVAR-Gesture, and Ultrasound-Gesture. Post-deployment adaptation yields consistent accuracy improvements of 3.73%, 17 …
:view less
ElectraSight: Fully Onboard Eye Tracking for Smart Glasses With Hybrid EOG (hEOG)
2025
Nicolas Schärer, Federico Villani, Aishwarya Melatur, Steven Peter, Tommaso Polonelli, …
IEEE Internet of Things Journal
:read more
Authors:Nicolas Schärer, Federico Villani, Aishwarya Melatur, Steven Peter, Tommaso Polonelli, Michele Magno
Publication date:07/30/2025
Journal:IEEE Internet of Things Journal
Publisher:IEEE
Description:Smart glasses with integrated eye tracking technology are revolutionizing diverse fields, from immersive augmented reality experiences to cutting-edge health monitoring solutions. However, traditional eye tracking systems rely heavily on cameras and significant computational power, leading to high-energy demand and privacy issues. Alternatively, systems based on electrooculography (EOG) provide superior battery life but are less accurate and primarily effective for detecting blinks, while being highly invasive. To bridge this gap, the paper introduces ElectraSight, a system built upon a new concept we define as hybrid Electrooculography (hEOG). This approach combines contact and contactless electrodes to create a robust, low-power, and truly non-invasive eye tracking system. To validate our approach, we collected a comprehensive dataset from 20 participants, using a commercial eye-tracker for ground-truth …
Resources:[PDF] from ethz.ch
:view less
Residual Koopman Model Predictive Control for Enhanced Vehicle Dynamics with Small On-Track Data Input
2025
Yonghao Fu, Cheng Hu, Haokun Xiong, Zhanpeng Bao, Wenyuan Du, Edoardo Ghignone, Michele…
arXiv preprint arXiv:2507.18396
:read more
Authors:Yonghao Fu, Cheng Hu, Haokun Xiong, Zhanpeng Bao, Wenyuan Du, Edoardo Ghignone, Michele Magno, Lei Xie, Hongye Su
Publication date:07/24/2025
Journal:arXiv preprint arXiv:2507.18396
Description:In vehicle trajectory tracking tasks, the simplest approach is the Pure Pursuit (PP) Control. However, this single-point preview tracking strategy fails to consider vehicle model constraints, compromising driving safety. Model Predictive Control (MPC) as a widely adopted control method, optimizes control actions by incorporating mechanistic models and physical constraints. While its control performance critically depends on the accuracy of vehicle modeling. Traditional vehicle modeling approaches face inherent trade-offs between capturing nonlinear dynamics and maintaining computational efficiency, often resulting in reduced control performance. To address these challenges, this paper proposes Residual Koopman Model Predictive Control (RKMPC) framework. This method uses two linear MPC architecture to calculate control inputs: a Linear Model Predictive Control (LMPC) computes the baseline control input based on the vehicle kinematic model, and a neural network-based RKMPC calculates the compensation input. The final control command is obtained by adding these two components. This design preserves the reliability and interpretability of traditional mechanistic model while achieving performance optimization through residual modeling. This method has been validated on the Carsim-Matlab joint simulation platform and a physical 1:10 scale F1TENTH racing car. Experimental results show that RKMPC requires only 20% of the training data needed by traditional Koopman Model Predictive Control (KMPC) while delivering superior tracking performance. Compared to traditional LMPC, RKMPC reduces lateral error by 11.7%-22.1 …
Cited by:1
Resources:[PDF] from arxiv.org
:view less
First-Order Error Matters: Accurate Compensation for Quantized Large Language Models
2025
Xingyu Zheng, Haotong Qin, Yuye Li, Jiakai Wang, Jinyang Guo, Michele Magno, Xianglong Liu
arXiv preprint arXiv:2507.11017
:read more
Authors:Xingyu Zheng, Haotong Qin, Yuye Li, Jiakai Wang, Jinyang Guo, Michele Magno, Xianglong Liu
Publication date:07/15/2025
Journal:arXiv preprint arXiv:2507.11017
Description:Post-training quantization (PTQ) offers an efficient approach to compressing large language models (LLMs), significantly reducing memory access and computational costs. Existing compensation-based weight calibration methods often rely on a second-order Taylor expansion to model quantization error, under the assumption that the first-order term is negligible in well-trained full-precision models. However, we reveal that the progressive compensation process introduces accumulated first-order deviations between latent weights and their full-precision counterparts, making this assumption fundamentally flawed. To address this, we propose FOEM, a novel PTQ method that explicitly incorporates first-order gradient terms to improve quantization error compensation. FOEM approximates gradients by directly computing the difference between latent and full-precision weights, avoiding the high cost and limited generalization of backpropagation-based gradient computation. This approach introduces minimal additional computational overhead. Moreover, FOEM leverages precomputed Cholesky factors to efficiently recover the inverse of Hessian submatrices in real time. Extensive experiments across a wide range of models and benchmarks demonstrate that FOEM consistently outperforms the classical GPTQ method. In 3-bit weight-only quantization, FOEM reduces the perplexity of Llama3-8B by 89.6%, and improves the 5-shot MMLU accuracy of Llama3-70B from 51.7% to 74.9%, approaching the full-precision performance of 78.6%. Furthermore, FOEM can be seamlessly integrated with advanced techniques such as GPTAQ and SpinQuant …
Resources:[PDF] from arxiv.org
:view less
A Cost-effective Occupancy Estimation System for Energy-efficient Buildings in Africa
2025
Godwin Adordie, Denis Kyalo Muuo, Philipp Schilk, Lukas Schulthess, Nathan Amanquah, Mi…
2025 IEEE Sensors Applications Symposium (SAS), 1-6
:read more
Authors:Godwin Adordie, Denis Kyalo Muuo, Philipp Schilk, Lukas Schulthess, Nathan Amanquah, Michele Magno
Publication date:07/08/2025
Journal:2025 IEEE Sensors Applications Symposium (SAS)
Pages:1-6
Publisher:IEEE
Description:Intelligent energy management in buildings is essential to optimize the use of Heating, Ventilation, and Air Conditioning (HVAC) systems, reducing their power consumption and operational costs. Traditional approaches to energy management in buildings rely on fixed schedules, static thresholds, or simple sensor-based control, which are often not aware of momentary power needs and thus fail to optimize energy use effectively. On the other hand, efficient management is crucial, especially in Africa, where high energy costs and unreliable or limited electricity supply necessitate cost-effective energy-saving solutions.This paper presents a robust, cost-effective, easy-to-install intelligent occupancy detection system based on widely adopted and cost-efficient HC-SR04 ultrasonic sensors. One of the main contributions of this paper is a quantized and lightweight machine learning algorithm designed to match the …
:view less
A Small Flying IoT Node for Real-Time Spectral Monitoring in Smart Agriculture
2025
Tobias Mächler, Hanna Müller, Philip Wiese, Michele Magno, Victor Kartsch, Luca Benini
2025 IEEE Sensors Applications Symposium (SAS), 1-6
:read more
Authors:Tobias Mächler, Hanna Müller, Philip Wiese, Michele Magno, Victor Kartsch, Luca Benini
Publication date:07/08/2025
Journal:2025 IEEE Sensors Applications Symposium (SAS)
Pages:1-6
Publisher:IEEE
Description:The rapid advancement of Internet of Things (IoT) technologies is driving a paradigm shift in smart agriculture. Spectrometers play a crucial role in modern agriculture and, when integrated with robotic mobile platforms such as nano-drones, enable flexible, precise, and cost-effective monitoring of crops and greenhouses. However, until recently, spectrometers were bulky and heavy, preventing their integration into small flying platforms due to weight constraints. In this work, we leverage the latest generation of mini-spectrometers to introduce, for the first time, a nano Unmanned Aerial Vehicle (UAV)-based smart sensor node capable of real-time spectral data sampling and processing. To achieve this, we designed a lightweight sensor shield featuring the C12880MA mini-spectrometer from Hamamatsu Photonics (2.53 cm3, spectral range 340–850 nm), compatible with a small and lightweight (27 g, 10 cm diameter …
:view less
Energy-Neutral Ultra-Wideband Asset Tracking Tag for Museums
2025
Jonah Imfeld, Philipp Mayer, Zahra Soltani, Sanjeev Kumar, John L Buckley, Brendan O’Fl…
2025 IEEE Sensors Applications Symposium (SAS), 1-6
:read more
Authors:Jonah Imfeld, Philipp Mayer, Zahra Soltani, Sanjeev Kumar, John L Buckley, Brendan O’Flynn, Michele Magno
Publication date:07/08/2025
Journal:2025 IEEE Sensors Applications Symposium (SAS)
Pages:1-6
Publisher:IEEE
Description:Asset tracking is particularly important in museums, as it enhances security and simplifies the management of valuable artworks in both exhibition and storage. This paper details the development and evaluation of a custom-designed asset tracking tag that meets museum-specific requirements. To ensure energy-neutral operation, enabling minimal maintenance, the suggested implementation utilizes indoor light harvesting and event-based sampling. The presented tag operates at an ultra-low quiescent current of just 504 nA in motion-detection mode. For on-demand sampling, an energy-efficient wake-up receiver (WuR) enables remote activation at a total system current consumption as low as 2 µA. Localization samples were optimized to only consume 1.3 mJ per 2D-localization. The expected battery-life was assessed through simulations using a low-light indoor lighting dataset over the span of one year with a …
:view less
CUPIDO: An Analog Ultra-Low-Power and Contactless Eye Blink Detector for Smart Glasses
2025
Daniele M Crafa, Tommaso Polonelli, Marco Carminati, Michele Magno
2025 IEEE Sensors Applications Symposium (SAS), 1-6
:read more
Authors:Daniele M Crafa, Tommaso Polonelli, Marco Carminati, Michele Magno
Publication date:07/08/2025
Journal:2025 IEEE Sensors Applications Symposium (SAS)
Pages:1-6
Publisher:IEEE
Description:This paper presents CUPIDO (Circuit for Unobtrusive Palpebral Interpretation and Detection Optimization), a µW contactless eye blink detection system optimized for wearable applications. The core of CUPIDO is a miniaturized, high-impedance analog front-end and a low-power digital front-end designed to extract event-based features from electrostatic signals produced by the movements of eyelids. Therefore, CUPIDO behaves as a wake-up event-based trigger without requiring a dedicated Microcontroller Unit (MCU). As reported by preliminary in-field measurements, CUPIDO achieves ultra-low-power consumption (385.1µW of peak) and high sensitivity (up to 90.5%) in a fully contactless setup, enabling non-invasive eyelid movement and blink detection. With 1ms latency, CUPIDO offers a low-power, real-time solution for eye blink monitoring and event-based triggering. This makes it ideal for Human-Machine …
:view less
Towards Event-Driven Aerodynamic Monitoring of Wind Turbine Blades Using PVDF and MEMS Sensors
2025
Lisa Odermatt, Nicolas Schärer, Tommaso Polonelli, Julien Deparday, Michele Magno
2025 IEEE Sensors Applications Symposium (SAS), 1-6
:read more
Authors:Lisa Odermatt, Nicolas Schärer, Tommaso Polonelli, Julien Deparday, Michele Magno
Publication date:07/08/2025
Journal:2025 IEEE Sensors Applications Symposium (SAS)
Pages:1-6
Publisher:IEEE
Description:Wind power generation is essential for transitioning to sustainable energy, requiring continuous advancements in turbine efficiency and operational monitoring. Understanding the aerodynamics of rotating blades, particularly flow separation, is both crucial and challenging due to installation constraints on operating wind turbines. This paper presents a flexible and modular monitoring system that integrates Polyvinylidene Fluoride (PVDF) piezoelectric sensors with Micro-Electromechanical Systems (MEMS) barometers to detect key aerodynamic parameters, such as Angle of Attack (AoA) and flow detachment. We demonstrate that PVDF sensors can be employed as event-driven triggers, reducing power consumption by activating high-precision measurements only when necessary. An experimental wind tunnel evaluation of a scaled wind turbine blade demonstrates that this hybrid approach achieves a precision of …
Cited by:1
Resources:[PDF] from ethz.ch
:view less
TinyEEGConformer: An Attention-Based EEG Decoding Model for Embedded Systems
2025
Nana Ofosu Asante, Lan Mei, Xiaying Wang, Michele Magno
2025 IEEE Sensors Applications Symposium (SAS), 1-6
:read more
Authors:Nana Ofosu Asante, Lan Mei, Xiaying Wang, Michele Magno
Publication date:07/08/2025
Journal:2025 IEEE Sensors Applications Symposium (SAS)
Pages:1-6
Publisher:IEEE
Description:Brain-Machine Interfaces (BMIs) are crucial in prosthesis control and motor rehabilitation. Processing real-time electroencephalographic (EEG) data on edge devices, such as low-power microcontroller units (MCUs) positioned close to the sensors, is an emerging and important trend. In fact, this approach enhances user experience and preserves data privacy. However, due to the limited computational resources of the low-power processors, having adequate performance of AI-driven EEG decoding models on low-power devices is still challenging. This paper presents TinyEEGConformer, a novel attention-based EEG decoding model targeting resource-constrained embedded systems for real-time processing at the edge. The proposed model is designed to meet the computational constraints of a low-power processor while maintaining optimal classification performance. The model achieves an average accuracy of …
:view less
Position Estimation Algorithms for Head-Mounted UWB Tags: A Comparative Analysis for Embedded Systems
2025
Aurelio Teliti, Tommaso Polonelli, Francesca Palermo, Giacomo Gervasoni, Michele Magno,…
2025 IEEE Sensors Applications Symposium (SAS), 1-6
:read more
Authors:Aurelio Teliti, Tommaso Polonelli, Francesca Palermo, Giacomo Gervasoni, Michele Magno, Diana Trojaniello
Publication date:07/08/2025
Journal:2025 IEEE Sensors Applications Symposium (SAS)
Pages:1-6
Publisher:IEEE
Description:Wearable Ultra-wideband (UWB) positioning systems are increasingly popular for indoor localization due to their resistance to interference and multipath signals. Those features enable improved accuracy over Bluetooth and WiFi on the other side UWB is still affected by noise and Non-Line-of-Sight (NLOS) conditions. Addressing these challenges, particularly in head-mounted devices like smart glasses, requires the analysis of crucial factors such as NLOS interference from the head itself and optimizing algorithm choice for real-time performance. This paper quantifies the ranging errors in head-mounted UWB systems, considering the head as an NLOS element, and it evaluates robust on-device localization algorithms to identify the best options for energy-efficient, real-time onboard execution. According to our evaluation, the mean filter demonstrates superior accuracy (MAEs of 6.0–11.0 cm under moderate NLOS …
:view less
Mpq-dmv2: Flexible residual mixed precision quantization for low-bit diffusion models with temporal distillation
2025
Weilun Feng, Chuanguang Yang, Haotong Qin, Yuqi Li, Xiangqi Li, Zhulin An, Libo Huang, …
arXiv preprint arXiv:2507.04290
:read more
Authors:Weilun Feng, Chuanguang Yang, Haotong Qin, Yuqi Li, Xiangqi Li, Zhulin An, Libo Huang, Boyu Diao, Fuzhen Zhuang, Michele Magno, Yongjun Xu, Yingli Tian, Tingwen Huang
Publication date:07/06/2025
Journal:arXiv preprint arXiv:2507.04290
Description:Diffusion models have demonstrated remarkable performance on vision generation tasks. However, the high computational complexity hinders its wide application on edge devices. Quantization has emerged as a promising technique for inference acceleration and memory reduction. However, existing quantization methods do not generalize well under extremely low-bit (2-4 bit) quantization. Directly applying these methods will cause severe performance degradation. We identify that the existing quantization framework suffers from the outlier-unfriendly quantizer design, suboptimal initialization, and optimization strategy. We present MPQ-DMv2, an improved textbf{M}ixed textbf{P}recision textbf{Q}uantization framework for extremely low-bit textbf{D}iffusion textbf{M}odels. For the quantization perspective, the imbalanced distribution caused by salient outliers is quantization-unfriendly for uniform quantizer. We propose textit{Flexible Z-Order Residual Mixed Quantization} that utilizes an efficient binary residual branch for flexible quant steps to handle salient error. For the optimization framework, we theoretically analyzed the convergence and optimality of the LoRA module and propose textit{Object-Oriented Low-Rank Initialization} to use prior quantization error for informative initialization. We then propose textit{Memory-based Temporal Relation Distillation} to construct an online time-aware pixel queue for long-term denoising temporal information distillation, which ensures the overall temporal consistency between quantized and full-precision model. Comprehensive experiments on various generation tasks show that our MPQ-DMv2 …
Cited by:3
Resources:[PDF] from arxiv.org
:view less
LynX: An Event-Based Gesture Dataset for Egocentric Interaction in Extended Reality
2025
Pietro Bartoli, Varsha Jayaprakash, Julian Moosmann, Philipp Mayer, Franco Zappa, Miche…
2025 10th International Workshop on Advances in Sensors and Interfaces (IWASI), 1-6
:read more
Authors:Pietro Bartoli, Varsha Jayaprakash, Julian Moosmann, Philipp Mayer, Franco Zappa, Michele Magno
Publication date:07/03/2025
Journal:2025 10th International Workshop on Advances in Sensors and Interfaces (IWASI)
Pages:1-6
Publisher:IEEE
Description:Hand gesture recognition is a cornerstone of intuitive human–computer interaction (HCI), particularly for wearable and extended reality (XR) systems. Today’s gesture recognition solutions are predominantly based on frame-based cameras. However, these systems underperform in challenging lighting conditions, and require substantial computational power not always available on battery-powered wearable devices. This limitation can significantly hinder real-time processing performance. A promising alternative is the use of emerging Dynamic Vision Sensors (DVS), which perform exceptionally well in high-dynamic lighting environments. These sensors adjust energy consumption based on scene activity, yielding sparse yet semantically rich data, enabling efficient battery operation and supporting real-time processing. However, current event-based gesture datasets generally include only temporal segmentation …
:view less
An IoT Sensor Platform for Predictive Maintenance of High Voltage Circuit Breakers
2025
Zoltán Marcsek, Tino Gfrörer, Tommaso Polonelli, Chi-Ching Hsu, Michele Magno, Christia…
2025 10th International Workshop on Advances in Sensors and Interfaces (IWASI), 1-6
:read more
Authors:Zoltán Marcsek, Tino Gfrörer, Tommaso Polonelli, Chi-Ching Hsu, Michele Magno, Christian M Franck
Publication date:07/03/2025
Journal:2025 10th International Workshop on Advances in Sensors and Interfaces (IWASI)
Pages:1-6
Publisher:IEEE
Description:This paper presents the design, implementation, and validation of an IoT-based sensor platform for predictive maintenance of high-voltage circuit breakers (HVCBs), essential components in power transmission systems. Mechanical failures account for more than half of major HVCB failures, emphasizing the need for reliable, long-term condition monitoring. The proposed platform is specifically developed for real-world deployment and enables non-intrusive, synchronized measurement of vibration and coil current signals during switching events, sampled at 100 ksps and 10 ksps, respectively. Triggering of the measurement is achieved via hardware detection of coil current with a response time below 115 µs. Data is recorded directly to a microSD card, with optional USB streaming for testing and Wi-Fi transfer to a gateway connected to cloud storage. The system supports virtually unlimited recording duration and …
:view less
Pushing Wi-Fi HaLow to the Extreme Edge: A Performance Study on a Low-Power IoT Node
2025
Nicolas Schärer, Tommaso Polonelli, Michele Magno
2025 10th International Workshop on Advances in Sensors and Interfaces (IWASI), 1-6
:read more
Authors:Nicolas Schärer, Tommaso Polonelli, Michele Magno
Publication date:07/03/2025
Journal:2025 10th International Workshop on Advances in Sensors and Interfaces (IWASI)
Pages:1-6
Publisher:IEEE
Description:Wi-Fi HaLow (IEEE 802.11ah) is a novel emerging wireless standard designed for low-power, long-range data communication for Internet of Things (IoT) applications [1]. This paper presents a practical performance evaluation of Wi-Fi HaLow (IEEE 802.11ah) using off-the-shelf hardware, focusing on application-level energy efficiency and throughput across varying distances emulated via the free-space path loss (FSPL) model. Our experiments demonstrate energy per bit (EPB) as low as 27nJbit−1 (and 45nJbit−1 at an equivalent 158m) and effective bit rates (EBR) from 0.15Mbits−1 to 18Mbits−1 over FSPL-calculated distances up to nearly 50km. A key contribution is the quantitative analysis of HaLow’s potential to enhance a wind turbine blade monitoring Wireless Sensor Network (WSN), projecting a two-fold EPB reduction and a tenfold EBR increase compared to BLE. These findings provide critical benchmarks …
Resources:[PDF] from ethz.ch
:view less
Sub-Millisecond Event-Based Eye Tracking on a Resource-Constrained Microcontroller
2025
Marco Giordano, Pietro Bonazzi, Luca Benini, Michele Magno
2025 10th International Workshop on Advances in Sensors and Interfaces (IWASI), 1-6
:read more
Authors:Marco Giordano, Pietro Bonazzi, Luca Benini, Michele Magno
Publication date:07/03/2025
Journal:2025 10th International Workshop on Advances in Sensors and Interfaces (IWASI)
Pages:1-6
Publisher:IEEE
Description:This paper presents a novel event-based eye-tracking system deployed on a resource-constrained microcontroller, addressing the challenges of real-time, low-latency, and low-power performance in embedded systems. The system leverages a Dynamic Vision Sensor (DVS), specifically the DVXplorer Micro, with an average temporal resolution of 200µs, to capture rapid eye movements with extremely low latency. The system is implemented on a novel low-power and high-performance microcontroller from STMicroelectronics, the STM32N6. The microcontroller features an 800MHz Arm Cortex-M55 core and AI hardware accelerator, the Neural-ART Accelerator, enabling real-time inference with milliwatt power consumption. The paper propose a hardware-aware and sensor-aware compact Convolutional Neuron Network (CNN) optimized for event-based data, deployed at the edge, achieving a mean pupil prediction …
Resources:[PDF] from arxiv.org
:view less
Validation of a Hybrid Deep Learning Model for Real Time Monitoring of Blood Pressure
2025
Chiara Botrugno, Kanika Dheman, Pietro Bonazzi, Giulio Trono, Pasquale Tondo, Vincenzo …
2025 10th International Workshop on Advances in Sensors and Interfaces (IWASI), 1-4
:read more
Authors:Chiara Botrugno, Kanika Dheman, Pietro Bonazzi, Giulio Trono, Pasquale Tondo, Vincenzo Scarola, Donato Lacedonia, Michele Magno, Francesco Dell’Olio
Publication date:07/03/2025
Journal:2025 10th International Workshop on Advances in Sensors and Interfaces (IWASI)
Pages:1-4
Publisher:IEEE
Description:Continuous and non-invasive blood pressure (BP) monitoring is increasingly recognized as a key tool for early detection of cardiovascular disorders and real-time patient management. Traditional cuff-based methods, although accurate, are unsuitable for continuous monitoring due to their intermittent nature and discomfort during prolonged use. To address these limitations, we developed a hybrid deep learning model combining a Convolutional Neural Network (CNN) with a Support Vector Regression (SVR) correction phase, trained to predict systolic and diastolic BP from multi-wavelength photoplethysmography (PPG) signals. In this study, we specifically evaluated the model’s ability to track rapid physiological BP changes induced by the Valsalva maneuver, a standard test provoking transient cardiovascular adjustment. BP values were recorded and predicted immediately before and after the maneuver in 6 …
:view less
Embedded 2D LiDAR-Based Person Tracking for Safe Navigation in Assistive Autonomous Robots
2025
Davide Plozza, Steven Marty, Cyril Scherrer, Simon Schwartz, Stefan Zihlmann, Michele M…
2025 10th International Workshop on Advances in Sensors and Interfaces (IWASI), 1-6
:read more
Authors:Davide Plozza, Steven Marty, Cyril Scherrer, Simon Schwartz, Stefan Zihlmann, Michele Magno
Publication date:07/03/2025
Journal:2025 10th International Workshop on Advances in Sensors and Interfaces (IWASI)
Pages:1-6
Publisher:IEEE
Description:This paper presents a fully embedded real-time person tracking pipeline for assistive quadrupedal robots supporting safe navigation for visually impaired users. Our approach combines a deep learning-based 2D LiDAR person detector with a lightweight multi-object tracker and integrates it into a Guide Dog Robot (GDR) navigation framework. A novel detection post-processing scheme is proposed, reducing detector latency by 52.38% compared to state-of-the-art voting-based methods while preserving accuracy. The improved latency enables the entire pipeline to operate reliably at 20 Hz on a resource-constrained mobile robotic embedded platform based on the NVIDIA Jetson Xavier NX. The experimental setup shows that our system tracks dynamic obstacles and continuously localizes the user holding the robot’s handle, enabling a dynamic safety footprint for proactive collision avoidance. Under the tested …
:view less
EdgeCodec: Onboard Lightweight High Fidelity Neural Compressor with Residual Vector Quantization
2025
Benjamin Hodo, Tommaso Polonelli, Amirhossein Moallemi, Luca Benini, Michele Magno
2025 10th International Workshop on Advances in Sensors and Interfaces (IWASI), 1-6
:read more
Authors:Benjamin Hodo, Tommaso Polonelli, Amirhossein Moallemi, Luca Benini, Michele Magno
Publication date:07/03/2025
Journal:2025 10th International Workshop on Advances in Sensors and Interfaces (IWASI)
Pages:1-6
Publisher:IEEE
Description:Data Compression is a staple of data processing and storage. Sending and storing data more efficiently is an open challenge in the Internet-of-Things (IoT), with devices typically characterized by limited availability of energy and computing power. The problem tackled in this paper is the massive amounts of sensor data collected and sent uncompressed by IoT-devices. We address this issue by compressing local data using a neural network supplemented with the Residual Vector Quantization (RVQ) technique. This paper, inspired by lossy neural compressors for audio like Google Soundstream and Meta EnCodec, proposes EdgeCodec: a lightweight lossy neural compressor specifically designed to run at the edge on low-power and resource constrained Microcontroller Units (MCUs). EdgeCodec processes multi-channel data with a flexible end-to-end learnable pipeline. We evaluate EdgeCodec in a real-life …
Resources:[PDF] from arxiv.org
:view less
BiVM: Accurate Binarized Neural Network for Efficient Video Matting
2025
Haotong Qin, Xianglong Liu, Xudong Ma, Lei Ke, Yulun Zhang, Jie Luo, Michele Magno
IEEE Transactions on Pattern Analysis and Machine Intelligence
:read more
Authors:Haotong Qin, Xianglong Liu, Xudong Ma, Lei Ke, Yulun Zhang, Jie Luo, Michele Magno
Publication date:07/02/2025
Journal:IEEE Transactions on Pattern Analysis and Machine Intelligence
Publisher:IEEE
Description:Deep neural networks for real-time video matting suffer significant computational limitations on edge devices, hindering their adoption in widespread applications such as online conferences and short-form video production. Binarization emerges as one of the most common neural network compression approaches, substantially curbing computational and memory requirements through compact 1-bit parameters and efficient bitwise operations. However, the empirical observation reveals that accuracy and efficiency limitations exist in the binarized video matting network due to its degenerated encoder and redundant decoder. Following a theoretical analysis based on the information bottleneck principle, the limitations are mainly caused by the degradation of prediction-relevant information in the intermediate features and the redundant computation in prediction-irrelevant areas. We present BiVM, an accurate and …
Cited by:4
Resources:[PDF] from arxiv.org
:view less
PuLsE: Accurate and Robust Ultrasound-Based Continuous Heart-Rate Monitoring on a Wrist-Worn IoT Device
2025
Marco Giordano, Christoph Leitner, Christian Vogt, Luca Benini, Michele Magno
IEEE Internet of Things Journal
:read more
Authors:Marco Giordano, Christoph Leitner, Christian Vogt, Luca Benini, Michele Magno
Publication date:06/25/2025
Journal:IEEE Internet of Things Journal
Publisher:IEEE
Description:This work explores the feasibility of employing ultrasound (US) technology in a wrist-worn Internet of Things (IoT) device for low-power, high-fidelity heart rate (HR) extraction. US offers deep tissue penetration and can monitor pulsatile arterial blood flow in large vessels and the surrounding tissue, potentially improving robustness and accuracy compared to photoplethysmogram (PPG). We present an IoT wearable system prototype utilizing a commercial microcontroller (MCU) employing the onboard analog-digital converters (ADC) to capture high-frequency US signals and an innovative low-power US pulser. An envelope filter lowers the bandwidth of the US signal by a factor of , reducing the system’s acquisition requirements without compromising accuracy (correlation coefficient between HR extracted from enveloped and raw signals, r(92) , p ). The full signal processing pipeline is ported to fixed-point …
Cited by:2
Resources:[PDF] from ieee.org
:view less
PicoSAM2: Low-Latency Segmentation In-Sensor for Edge Vision Applications
2025
Pietro Bonazzi, Nicola Farronato, Stefan Zihlmann, Haotong Qin, Michele Magno
arXiv preprint arXiv:2506.18807
:read more
Authors:Pietro Bonazzi, Nicola Farronato, Stefan Zihlmann, Haotong Qin, Michele Magno
Publication date:06/23/2025
Journal:arXiv preprint arXiv:2506.18807
Description:Real-time, on-device segmentation is critical for latency-sensitive and privacy-aware applications like smart glasses and IoT devices. We introduce PicoSAM2, a lightweight (1.3M parameters, 336M MACs) promptable segmentation model optimized for edge and in-sensor execution, including the Sony IMX500. It builds on a depthwise separable U-Net, with knowledge distillation and fixed-point prompt encoding to learn from the Segment Anything Model 2 (SAM2). On COCO and LVIS, it achieves 51.9% and 44.9% mIoU, respectively. The quantized model (1.22MB) runs at 14.3 ms on the IMX500-achieving 86 MACs/cycle, making it the only model meeting both memory and compute constraints for in-sensor deployment. Distillation boosts LVIS performance by +3.5% mIoU and +5.1% mAP. These results demonstrate that efficient, promptable segmentation is feasible directly on-camera, enabling privacy-preserving vision without cloud or host processing.
Resources:[PDF] from arxiv.org
:view less
M-Predictive Spliner: Enabling Spatiotemporal Multi-Opponent Overtaking for Autonomous Racing
2025
Nadine Imholz, Maurice Brunner, Nicolas Baumann, Edoardo Ghignone, Michele Magno
arXiv preprint arXiv:2506.16301
:read more
Authors:Nadine Imholz, Maurice Brunner, Nicolas Baumann, Edoardo Ghignone, Michele Magno
Publication date:06/19/2025
Journal:arXiv preprint arXiv:2506.16301
Description:Unrestricted multi-agent racing presents a significant research challenge, requiring decision-making at the limits of a robot's operational capabilities. While previous approaches have either ignored spatiotemporal information in the decision-making process or been restricted to single-opponent scenarios, this work enables arbitrary multi-opponent head-to-head racing while considering the opponents' future intent. The proposed method employs a KF-based multi-opponent tracker to effectively perform opponent ReID by associating them across observations. Simultaneously, spatial and velocity GPR is performed on all observed opponent trajectories, providing predictive information to compute the overtaking maneuvers. This approach has been experimentally validated on a physical 1:10 scale autonomous racing car, achieving an overtaking success rate of up to 91.65% and demonstrating an average 10.13%-point improvement in safety at the same speed as the previous SotA. These results highlight its potential for high-performance autonomous racing.
Resources:[PDF] from arxiv.org
:view less
Post-Training Quantization for Video Matting
2025
Tianrui Zhu, Houyuan Chen, Ruihao Gong, Michele Magno, Haotong Qin, Kai Zhang
arXiv preprint arXiv:2506.10840
:read more
Authors:Tianrui Zhu, Houyuan Chen, Ruihao Gong, Michele Magno, Haotong Qin, Kai Zhang
Publication date:06/12/2025
Journal:arXiv preprint arXiv:2506.10840
Description:Video matting is crucial for applications such as film production and virtual reality, yet deploying its computationally intensive models on resource-constrained devices presents challenges. Quantization is a key technique for model compression and acceleration. As an efficient approach, Post-Training Quantization (PTQ) is still in its nascent stages for video matting, facing significant hurdles in maintaining accuracy and temporal coherence. To address these challenges, this paper proposes a novel and general PTQ framework specifically designed for video matting models, marking, to the best of our knowledge, the first systematic attempt in this domain. Our contributions include: (1) A two-stage PTQ strategy that combines block-reconstruction-based optimization for fast, stable initial quantization and local dependency capture, followed by a global calibration of quantization parameters to minimize accuracy loss. (2) A Statistically-Driven Global Affine Calibration (GAC) method that enables the network to compensate for cumulative statistical distortions arising from factors such as neglected BN layer effects, even reducing the error of existing PTQ methods on video matting tasks up to 20%. (3) An Optical Flow Assistance (OFA) component that leverages temporal and semantic priors from frames to guide the PTQ process, enhancing the model's ability to distinguish moving foregrounds in complex scenes and ultimately achieving near full-precision performance even under ultra-low-bit quantization. Comprehensive quantitative and visual results show that our PTQ4VM achieves the state-of-the-art accuracy performance across different bit-widths …
Resources:[PDF] from arxiv.org
:view less
Q-SAM2: Accurate Quantization for Segment Anything Model 2
2025
Nicola Farronato, Florian Scheidegger, Mattia Rigotti, Cristiano Malossi, Michele Magno…
arXiv preprint arXiv:2506.09782
:read more
Authors:Nicola Farronato, Florian Scheidegger, Mattia Rigotti, Cristiano Malossi, Michele Magno, Haotong Qin
Publication date:06/11/2025
Journal:arXiv preprint arXiv:2506.09782
Description:The Segment Anything Model 2 (SAM2) has gained significant attention as a foundational approach for promptable image and video segmentation. However, its expensive computational and memory consumption poses a severe challenge for its application in resource-constrained scenarios. In this paper, we propose an accurate low-bit quantization method for efficient SAM2, termed Q-SAM2. To address the performance degradation caused by the singularities in weight and activation distributions during quantization, Q-SAM2 introduces two novel technical contributions. We first introduce a linear layer calibration method for low-bit initialization of SAM2, which minimizes the Frobenius norm over a small image batch to reposition weight distributions for improved quantization. We then propose a Quantization-Aware Training (QAT) pipeline that applies clipping to suppress outliers and allows the network to adapt to quantization thresholds during training. Our comprehensive experiments demonstrate that Q-SAM2 allows for highly accurate inference while substantially improving efficiency. Both quantitative and visual results show that our Q-SAM2 surpasses existing state-of-the-art general quantization schemes, especially for ultra-low 2-bit quantization. While designed for quantization-aware training, our proposed calibration technique also proves effective in post-training quantization, achieving up to a 66% mIoU accuracy improvement over non-calibrated models.
:view less
R-CARLA: High-Fidelity Sensor Simulations with Interchangeable Dynamics for Autonomous Racing
2025
Maurice Brunner, Edoardo Ghignone, Nicolas Baumann, Michele Magno
arXiv preprint arXiv:2506.09629
:read more
Authors:Maurice Brunner, Edoardo Ghignone, Nicolas Baumann, Michele Magno
Publication date:06/11/2025
Journal:arXiv preprint arXiv:2506.09629
Description:Autonomous racing has emerged as a crucial testbed for autonomous driving algorithms, necessitating a simulation environment for both vehicle dynamics and sensor behavior. Striking the right balance between vehicle dynamics and sensor accuracy is crucial for pushing vehicles to their performance limits. However, autonomous racing developers often face a trade-off between accurate vehicle dynamics and high-fidelity sensor simulations. This paper introduces R-CARLA, an enhancement of the CARLA simulator that supports holistic full-stack testing, from perception to control, using a single system. By seamlessly integrating accurate vehicle dynamics with sensor simulations, opponents simulation as NPCs, and a pipeline for creating digital twins from real-world robotic data, R-CARLA empowers researchers to push the boundaries of autonomous racing development. Furthermore, it is developed using CARLA's rich suite of sensor simulations. Our results indicate that incorporating the proposed digital-twin framework into R-CARLA enables more realistic full-stack testing, demonstrating a significant reduction in the Sim-to-Real gap of car dynamics simulation by 42% and by 82% in the case of sensor simulation across various testing scenarios.
Cited by:2
Resources:[PDF] from arxiv.org
:view less
Self-Sustaining Multi-Sensor LoRa-Based Activity Monitoring for Community Workout Parks
2025
Victor Luder, Michele Magno
arXiv preprint arXiv:2506.03203
:read more
Authors:Victor Luder, Michele Magno
Publication date:06/02/2025
Journal:arXiv preprint arXiv:2506.03203
Description:With the rise of the Internet of Things (IoT), more sensors are deployed around us, covering a wide range of applications from industry and agriculture to urban environments such as smart cities. Throughout these applications the sensors collect data of various characteristics and support city planners and decision-makers in their work processes, ultimately maximizing the impact of public funds. This paper introduces the design and implementation of a self-sustaining wireless sensor node designed to continuously monitor the utilization of community street workout parks. The proposed sensor node monitors activity by leveraging acceleration data capturing micro-vibrations that propagate through the steel structures of the workout equipment. This allows us to detect activity duration with an average measured error of only 2.8 seconds. The sensor is optimized with an energy-aware, adaptive sampling and transmission algorithm which, in combination with the Long Range Wide Area Network (LoRaWAN), reduces power consumption to just 1.147 mW in normal operation and as low as 0.712 mW in low-power, standby mode allowing 46 days of battery runtime. In addition, the integrated energy-harvesting circuit was tested in the field. By monitoring the battery voltage for multiple days, it was shown that the sensor is capable of operating sustainably year-round without external power sources. To evaluate the sensor effectiveness, we conducted a week-long field test in Zurich, placing sensors at various street workout parks throughout the city. Analysis of the collected data revealed clear patterns in park usage depending on day and location. This …
Resources:[PDF] from arxiv.org
:view less
Planar Velocity Estimation for Fast-Moving Mobile Robots Using Event-Based Optical Flow
2025
Liam Boyle, Jonas Kühne, Nicolas Baumann, Niklas Bastuck, Michele Magno
IEEE Robotics and Automation Letters
:read more
Authors:Liam Boyle, Jonas Kühne, Nicolas Baumann, Niklas Bastuck, Michele Magno
Publication date:06/02/2025
Journal:IEEE Robotics and Automation Letters
Publisher:IEEE
Description:Accurate velocity estimation is critical in mobile robotics, particularly for driver assistance systems and autonomous driving. Wheel odometry fused with Inertial Measurement Unit (IMU) data is a widely used method for velocity estimation, however, it typically requires strong assumptions, such as non-slip steering, or complex vehicle dynamics models that do not hold under varying environmental conditions, like slippery surfaces. We introduce an approach to velocity estimation that is decoupled from wheel-to-surface traction assumptions by leveraging planar kinematics in combination with optical flow from event cameras pointed perpendicularly at the ground. The asynchronous -second latency and high dynamic range of event cameras make them highly robust to motion blur, a common challenge in vision-based perception techniques for autonomous driving. The proposed method is evaluated through in-field …
Resources:[PDF] from arxiv.org
:view less
ForzaETH Race Stack—Scaled Autonomous Head‐to‐Head Racing on Fully Commercial Off‐the‐Shelf Hardware
2025
Nicolas Baumann, Edoardo Ghignone, Jonas Kühne, Niklas Bastuck, Jonathan Becker, Nadine…
Journal of Field Robotics 42 (4), 1037-1079
:read more
Authors:Nicolas Baumann, Edoardo Ghignone, Jonas Kühne, Niklas Bastuck, Jonathan Becker, Nadine Imholz, Tobias Kränzlin, Tian Yi Lim, Michael Lötscher, Luca Schwarzenbach, Luca Tognoni, Christian Vogt, Andrea Carron, Michele Magno
Publication date:06/01/2025
Journal:Journal of Field Robotics
Volume:42
Issue:4
Pages:1037-1079
Description:Autonomous racing in robotics combines high‐speed dynamics with the necessity for reliability and real‐time decision‐making. While such racing pushes software and hardware to their limits, many existing full‐system solutions necessitate complex, custom hardware and software, and usually focus on Time‐TrIals rather than full unrestricted Head‐to‐head racing, due to financial and safety constraints. This limits their reproducibility, making advancements and replication feasible mostly for well‐resourced laboratories with comprehensive expertise in mechanical, electrical, and robotics fields. Researchers interested in the autonomy domain but with only partial experience in one of these fields, need to spend significant time with familiarization and integration. The ForzaETH Race Stack addresses this gap by providing an autonomous racing software platform designed for F1TENTH, a 1:10 scaled Head‐to‐Head …
Cited by:32
Resources:[PDF] from arxiv.org
:view less
AniTrack: A Power-Efficient, Time-Slotted and Robust UWB Localization System for Animal Tracking in a Controlled Setting
2025
Victor Luder, Lukas Schulthess, Silvano Cortesi, Leyla Rivero Davis, Michele Magno
arXiv preprint arXiv:2506.00216
:read more
Authors:Victor Luder, Lukas Schulthess, Silvano Cortesi, Leyla Rivero Davis, Michele Magno
Publication date:05/30/2025
Journal:arXiv preprint arXiv:2506.00216
Description:Accurate localization is essential for a wide range of applications, including asset tracking, smart agriculture, and an- imal monitoring. While traditional localization methods, such as Global Navigation Satellite System (GNSS), Wi-Fi, and Bluetooth Low Energy (BLE), offer varying levels of accuracy and coverage, they have drawbacks regarding power consumption, infrastruc- ture requirements, and deployment flexibility. Ultra-Wideband (UWB) is emerging as an alternative, offering centimeter-level accuracy and energy efficiency, especially suitable for medium to large field monitoring with capabilities to work indoors and outdoors. However, existing UWB localization systems require infrastructure with mains power to supply the anchors, which impedes their scalability and ease of deployment. This under- scores the need for a fully battery-powered and energy-efficient localization system. This paper presents an energy-optimized, battery-operated UWB localization system that leverages Long Range Wide Area Network (LoRaWAN) for data transmission to a server backend. By employing single-sided two-way ranging (SS-TWR) in a time- slotted localization approach, the power consumption both on the anchor and the tag is reduced, while maintaining high accuracy. With a low average power consumption of 20.44 mW per anchor and 7.19 mW per tag, the system allows fully battery- powered operation for up to 25 days, achieving average accuracy of 13.96 cm with self-localizing anchors on a 600 m2 testing ground. To validate its effectiveness and ease of installation in a challenging application scenario, ten anchors and two tags were …
Resources:[PDF] from arxiv.org
:view less
DTR: Delaunay Triangulation-based Racing for Scaled Autonomous Racing
2025
Luca Tognoni, Neil Reichlin, Edoardo Ghignone, Nicolas Baumann, Steven Marty, Liam Boyl…
arXiv preprint arXiv:2505.24320
:read more
Authors:Luca Tognoni, Neil Reichlin, Edoardo Ghignone, Nicolas Baumann, Steven Marty, Liam Boyle, Michele Magno
Publication date:05/30/2025
Journal:arXiv preprint arXiv:2505.24320
Description:Reactive controllers for autonomous racing avoid the computational overhead of full ee-Think-Act autonomy stacks by directly mapping sensor input to control actions, eliminating the need for localization and planning. A widely used reactive strategy is FTG, which identifies gaps in LiDAR range measurements and steers toward a chosen one. While effective on fully bounded circuits, FTG fails in scenarios with incomplete boundaries and is prone to driving into dead-ends, known as FTG-traps. This work presents DTR, a reactive controller that combines Delaunay triangulation, from raw LiDAR readings, with track boundary segmentation to extract a centerline while systematically avoiding FTG-traps. Compared to FTG, the proposed method achieves lap times that are 70% faster and approaches the performance of map-dependent methods. With a latency of 8.95 ms and CPU usage of only 38.85% on the robot's OBC, DTR is real-time capable and has been successfully deployed and evaluated in field experiments.
Cited by:1
Resources:[PDF] from arxiv.org
:view less
Ultra-Lightweight Collaborative SLAM for Robot Swarms
2025
Vlad Niculescu, Tommaso Polonelli, Michele Magno, Luca Benini
IEEE Access
:read more
Authors:Vlad Niculescu, Tommaso Polonelli, Michele Magno, Luca Benini
Publication date:05/28/2025
Journal:IEEE Access
Publisher:IEEE
Description:A key requirement in robotics is the ability to simultaneously self-localize and map a previously unknown environment, relying primarily on onboard sensing and computation. Achieving fully onboard accurate simultaneous localization and mapping (SLAM) is feasible for high-end robotic platforms, whereas small and inexpensive robots face challenges due to constrained hardware, therefore frequently resorting to external infrastructure for sensing and computation. The challenge is further exacerbated in swarms of robots, where coordination, scalability, and latency are crucial concerns. This work introduces a decentralized and lightweight collaborative SLAM approach that enables mapping on virtually any robot, even those equipped with low-cost hardware and only detect-weight=true, detect-family=true, mode=text1.5of memory, including miniaturized insect-size devices. Moreover, the proposed solution supports …
Resources:[PDF] from ieee.org
:view less
Q-VDiT: Towards Accurate Quantization and Distillation of Video-Generation Diffusion Transformers
2025
Weilun Feng, Chuanguang Yang, Haotong Qin, Xiangqi Li, Yu Wang, Zhulin An, Libo Huang, …
arXiv preprint arXiv:2505.22167
:read more
Authors:Weilun Feng, Chuanguang Yang, Haotong Qin, Xiangqi Li, Yu Wang, Zhulin An, Libo Huang, Boyu Diao, Zixiang Zhao, Yongjun Xu, Michele Magno
Publication date:05/28/2025
Journal:arXiv preprint arXiv:2505.22167
Description:Diffusion transformers (DiT) have demonstrated exceptional performance in video generation. However, their large number of parameters and high computational complexity limit their deployment on edge devices. Quantization can reduce storage requirements and accelerate inference by lowering the bit-width of model parameters. Yet, existing quantization methods for image generation models do not generalize well to video generation tasks. We identify two primary challenges: the loss of information during quantization and the misalignment between optimization objectives and the unique requirements of video generation. To address these challenges, we present Q-VDiT, a quantization framework specifically designed for video DiT models. From the quantization perspective, we propose the Token-aware Quantization Estimator (TQE), which compensates for quantization errors in both the token and feature dimensions. From the optimization perspective, we introduce Temporal Maintenance Distillation (TMD), which preserves the spatiotemporal correlations between frames and enables the optimization of each frame with respect to the overall video context. Our W3A6 Q-VDiT achieves a scene consistency of 23.40, setting a new benchmark and outperforming current state-of-the-art quantization methods by 1.9. Code will be available at https://github.com/cantbebetter2/Q-VDiT.
Cited by:7
Resources:[PDF] from arxiv.org
:view less
A Low-Power, Non-Invasive and Contactless Eye Blink Detection Sensor Enabling Human-Machine Interfaces for Smart Eyewear Applications
2025
Daniele Maria Crafa, Tommaso Polonelli, Carlo Pezzoli, Marco Carminati, Michele Magno
Proceedings of the 2025 Symposium on Eye Tracking Research and Applications, 1-6
:read more
Authors:Daniele Maria Crafa, Tommaso Polonelli, Carlo Pezzoli, Marco Carminati, Michele Magno
Publication date:05/26/2025
Journal:Proceedings of the 2025 Symposium on Eye Tracking Research and Applications
Pages:1-6
Description:CUPIDO (Circuit for Unobtrusive Palpebral Interpretation and Detection Optimization) is an ultra-low-power electrostatic sensor able to convert eye blinks into digital events with a detection sensitivity up to . It can be easily integrated into the rims of smart glasses allowing for contactless interaction without compromising comfort and privacy (since no camera is used). Thanks to its extremely low power consumption ( at peak during the blink), CUPIDO can extend battery life in smart glasses, allowing for continuous and real-time (detection latency of approximately 1 ms) monitoring applications like hands-free glasses control, assistive technologies, augmented reality, and drowsiness monitoring while driving.
Resources:[PDF] from acm.org
:view less
WakeMod: A 6.9 uW Wake-Up Radio Module with-72.6 dBm Sensitivity for On-Demand IoT
2025
Lukas Schulthess, Silvano Cortesi, Michele Magno
arXiv preprint arXiv:2505.21529
:read more
Authors:Lukas Schulthess, Silvano Cortesi, Michele Magno
Publication date:05/23/2025
Journal:arXiv preprint arXiv:2505.21529
Description:Large-scale Internet of Things (IoT) applications, such as asset tracking and remote sensing, demand multi-year battery lifetimes to minimize maintenance and operational costs. Traditional wireless protocols often employ duty cycling, introducing a tradeoff between latency and idle consumption - both unsuitable for event-driven and ultra-low power systems. A promising approach to address these issues is the integration of always-on wake-up radios (WuRs). They provide asynchronous, ultra-low power communication to overcome these constraints. This paper presents WakeMod, an open-source wake-up transceiver module for the 868MHz ISM band. Designed for easy integration and ultra-low power consumption, it leverages the -75dBm sensitive FH101RF WuR. WakeMod achieves a low idle power consumption of 6.9uW while maintaining responsiveness with a sensitivity of -72.6dBm. Reception of a wake-up call is possible from up to 130m of distance with a -2.1dBi antenna, consuming 17.7uJ with a latency below 54.3ms. WakeMod's capabilities have further been demonstrated in an e-ink price tag application, achieving 7.17uW idle consumption and enabling an estimated 8-year battery life with daily updates on a standard CR2032 coin cell. WakeMod offers a practical solution for energy-constrained, long-term IoT deployments, requiring low-latency, and on-demand communication.
Resources:[PDF] from arxiv.org
:view less
Robust Reinforcement Learning-Based Locomotion for Resource-Constrained Quadrupeds with Exteroceptive Sensing
2025
Davide Plozza, Patricia Apostol, Paul Joseph, Simon Schläpfer, Michele Magno
arXiv preprint arXiv:2505.12537
:read more
Authors:Davide Plozza, Patricia Apostol, Paul Joseph, Simon Schläpfer, Michele Magno
Publication date:05/18/2025
Journal:arXiv preprint arXiv:2505.12537
Description:Compact quadrupedal robots are proving increasingly suitable for deployment in real-world scenarios. Their smaller size fosters easy integration into human environments. Nevertheless, real-time locomotion on uneven terrains remains challenging, particularly due to the high computational demands of terrain perception. This paper presents a robust reinforcement learning-based exteroceptive locomotion controller for resource-constrained small-scale quadrupeds in challenging terrains, which exploits real-time elevation mapping, supported by a careful depth sensor selection. We concurrently train both a policy and a state estimator, which together provide an odometry source for elevation mapping, optionally fused with visual-inertial odometry (VIO). We demonstrate the importance of positioning an additional time-of-flight sensor for maintaining robustness even without VIO, thus having the potential to free up computational resources. We experimentally demonstrate that the proposed controller can flawlessly traverse steps up to 17.5 cm in height and achieve an 80% success rate on 22.5 cm steps, both with and without VIO. The proposed controller also achieves accurate forward and yaw velocity tracking of up to 1.0 m/s and 1.5 rad/s respectively. We open-source our training code at github.com/ETH-PBL/elmap-rl-controller.
Resources:[PDF] from arxiv.org
:view less
Drive Fast, Learn Faster: On-Board RL for High Performance Autonomous Racing
2025
Benedict Hildisch, Edoardo Ghignone, Nicolas Baumann, Cheng Hu, Andrea Carron, Michele …
arXiv preprint arXiv:2505.07321
:read more
Authors:Benedict Hildisch, Edoardo Ghignone, Nicolas Baumann, Cheng Hu, Andrea Carron, Michele Magno
Publication date:05/12/2025
Journal:arXiv preprint arXiv:2505.07321
Description:Autonomous racing presents unique challenges due to its non-linear dynamics, the high speed involved, and the critical need for real-time decision-making under dynamic and unpredictable conditions. Most traditional Reinforcement Learning (RL) approaches rely on extensive simulation-based pre-training, which faces crucial challenges in transfer effectively to real-world environments. This paper introduces a robust on-board RL framework for autonomous racing, designed to eliminate the dependency on simulation-based pre-training enabling direct real-world adaptation. The proposed system introduces a refined Soft Actor-Critic (SAC) algorithm, leveraging a residual RL structure to enhance classical controllers in real-time by integrating multi-step Temporal-Difference (TD) learning, an asynchronous training pipeline, and Heuristic Delayed Reward Adjustment (HDRA) to improve sample efficiency and training stability. The framework is validated through extensive experiments on the F1TENTH racing platform, where the residual RL controller consistently outperforms the baseline controllers and achieves up to an 11.5 % reduction in lap times compared to the State-of-the-Art (SotA) with only 20 min of training. Additionally, an End-to-End (E2E) RL controller trained without a baseline controller surpasses the previous best results with sustained on-track learning. These findings position the framework as a robust solution for high-performance autonomous racing and a promising direction for other real-time, dynamic autonomous systems.
Resources:[PDF] from arxiv.org
:view less
RGB-Event Fusion with Self-Attention for Collision Prediction
2025
Pietro Bonazzi, Christian Vogt, Michael Jost, Haotong Qin, Lyes Khacef, Federico Parede…
arXiv preprint arXiv:2505.04258
:read more
Authors:Pietro Bonazzi, Christian Vogt, Michael Jost, Haotong Qin, Lyes Khacef, Federico Paredes-Valles, Michele Magno
Publication date:05/07/2025
Journal:arXiv preprint arXiv:2505.04258
Description:Ensuring robust and real-time obstacle avoidance is critical for the safe operation of autonomous robots in dynamic, real-world environments. This paper proposes a neural network framework for predicting the time and collision position of an unmanned aerial vehicle with a dynamic object, using RGB and event-based vision sensors. The proposed architecture consists of two separate encoder branches, one for each modality, followed by fusion by self-attention to improve prediction accuracy. To facilitate benchmarking, we leverage the ABCD [8] dataset collected that enables detailed comparisons of single-modality and fusion-based approaches. At the same prediction throughput of 50Hz, the experimental results show that the fusion-based model offers an improvement in prediction accuracy over single-modality approaches of 1% on average and 10% for distances beyond 0.5m, but comes at the cost of +71% in memory and + 105% in FLOPs. Notably, the event-based model outperforms the RGB model by 4% for position and 26% for time error at a similar computational cost, making it a competitive alternative. Additionally, we evaluate quantized versions of the event-based models, applying 1- to 8-bit quantization to assess the trade-offs between predictive performance and computational efficiency. These findings highlight the trade-offs of multi-modal perception using RGB and event-based cameras in robotic applications.
Cited by:1
Resources:[PDF] from arxiv.org
:view less
RobotxR1: Enabling Embodied Robotic Intelligence on Large Language Models through Closed-Loop Reinforcement Learning
2025
Liam Boyle, Nicolas Baumann, Paviththiren Sivasothilingam, Michele Magno, Luca Benini
arXiv preprint arXiv:2505.03238
:read more
Authors:Liam Boyle, Nicolas Baumann, Paviththiren Sivasothilingam, Michele Magno, Luca Benini
Publication date:05/06/2025
Journal:arXiv preprint arXiv:2505.03238
Description:Future robotic systems operating in real-world environments will require on-board embodied intelligence without continuous cloud connection, balancing capabilities with constraints on computational power and memory. This work presents an extension of the R1-zero approach, which enables the usage of low parameter-count Large Language Models (LLMs) in the robotic domain. The R1-Zero approach was originally developed to enable mathematical reasoning in LLMs using static datasets. We extend it to the robotics domain through integration in a closed-loop Reinforcement Learning (RL) framework. This extension enhances reasoning in Embodied Artificial Intelligence (Embodied AI) settings without relying solely on distillation of large models through Supervised Fine-Tuning (SFT). We show that small-scale LLMs can achieve effective reasoning performance by learning through closed-loop interaction with their environment, which enables tasks that previously required significantly larger models. In an autonomous driving setting, a performance gain of 20.2%-points over the SFT-based baseline is observed with a Qwen2.5-1.5B model. Using the proposed training procedure, Qwen2.5-3B achieves a 63.3% control adaptability score, surpassing the 58.5% obtained by the much larger, cloud-bound GPT-4o. These results highlight that practical, on-board deployment of small LLMs is not only feasible but can outperform larger models if trained through environmental feedback, underscoring the importance of an interactive learning framework for robotic Embodied AI, one grounded in practical experience rather than static supervision.
Cited by:1
Resources:[PDF] from arxiv.org
:view less
Efficient Continual Learning in Keyword Spotting using Binary Neural Networks
2025
Quynh Nguyen-Phuong Vu, Luciano Sebastian Martinez-Rau, Yuxuan Zhang, Nho-Duc Tran, Ben…
arXiv preprint arXiv:2505.02469
:read more
Authors:Quynh Nguyen-Phuong Vu, Luciano Sebastian Martinez-Rau, Yuxuan Zhang, Nho-Duc Tran, Bengt Oelmann, Michele Magno, Sebastian Bader
Publication date:05/05/2025
Journal:arXiv preprint arXiv:2505.02469
Description:Keyword spotting (KWS) is an essential function that enables interaction with ubiquitous smart devices. However, in resource-limited devices, KWS models are often static and can thus not adapt to new scenarios, such as added keywords. To overcome this problem, we propose a Continual Learning (CL) approach for KWS built on Binary Neural Networks (BNNs). The framework leverages the reduced computation and memory requirements of BNNs while incorporating techniques that enable the seamless integration of new keywords over time. This study evaluates seven CL techniques on a 16-class use case, reporting an accuracy exceeding 95% for a single additional keyword and up to 86% for four additional classes. Sensitivity to the amount of training samples in the CL phase, and differences in computational complexities are being evaluated. These evaluations demonstrate that batch-based algorithms are more sensitive to the CL dataset size, and that differences between the computational complexities are insignificant. These findings highlight the potential of developing an effective and computationally efficient technique for continuously integrating new keywords in KWS applications that is compatible with resource-constrained devices.
Resources:[PDF] from arxiv.org
:view less
An empirical study of qwen3 quantization
2025
Xingyu Zheng, Yuye Li, Haoran Chu, Yue Feng, Xudong Ma, Jie Luo, Jinyang Guo, Haotong Q…
arXiv preprint arXiv:2505.02214
:read more
Authors:Xingyu Zheng, Yuye Li, Haoran Chu, Yue Feng, Xudong Ma, Jie Luo, Jinyang Guo, Haotong Qin, Michele Magno, Xianglong Liu
Publication date:05/04/2025
Journal:arXiv preprint arXiv:2505.02214
Description:The Qwen series has emerged as a leading family of open-source Large Language Models (LLMs), demonstrating remarkable capabilities in natural language understanding tasks. With the recent release of Qwen3, which exhibits superior performance across diverse benchmarks, there is growing interest in deploying these models efficiently in resource-constrained environments. Low-bit quantization presents a promising solution, yet its impact on Qwen3's performance remains underexplored. This study conducts a systematic evaluation of Qwen3's robustness under various quantization settings, aiming to uncover both opportunities and challenges in compressing this state-of-the-art model. We rigorously assess 5 existing classic post-training quantization techniques applied to Qwen3, spanning bit-widths from 1 to 8 bits, and evaluate their effectiveness across multiple datasets. Our findings reveal that while Qwen3 maintains competitive performance at moderate bit-widths, it experiences notable degradation in linguistic tasks under ultra-low precision, underscoring the persistent hurdles in LLM compression. These results emphasize the need for further research to mitigate performance loss in extreme quantization scenarios. We anticipate that this empirical analysis will provide actionable insights for advancing quantization methods tailored to Qwen3 and future LLMs, ultimately enhancing their practicality without compromising accuracy. Our project is released on https://github.com/Efficient-ML/Qwen3-Quantization and https://huggingface.co/collections/Efficient-ML/qwen3-quantization-68164450decb1c868788cb2b.
Cited by:10
Resources:[PDF] from arxiv.org
:view less
Efficient Continual Learning in Keyword Spotting using Binary Neural Networks
2025
Quynh Nguyen-Phuong Vu, Luciano Sebastian Martinez-Rau, Yuxuan Zhang, Nho-Duc Tran, Ben…
arXiv e-prints, arXiv: 2505.02469
:read more
Authors:Quynh Nguyen-Phuong Vu, Luciano Sebastian Martinez-Rau, Yuxuan Zhang, Nho-Duc Tran, Bengt Oelmann, Michele Magno, Sebastian Bader
Publication date:05/01/2025
Journal:arXiv e-prints
Pages:arXiv: 2505.02469
Description:Keyword spotting (KWS) is an essential function that enables interaction with ubiquitous smart devices. However, in resource-limited devices, KWS models are often static and can thus not adapt to new scenarios, such as added keywords. To overcome this problem, we propose a Continual Learning (CL) approach for KWS built on Binary Neural Networks (BNNs). The framework leverages the reduced computation and memory requirements of BNNs while incorporating techniques that enable the seamless integration of new keywords over time. This study evaluates seven CL techniques on a 16-class use case, reporting an accuracy exceeding 95% for a single additional keyword and up to 86% for four additional classes. Sensitivity to the amount of training samples in the CL phase, and differences in computational complexities are being evaluated. These evaluations demonstrate that batch-based algorithms are …
:view less
Sparse Gaussian process-based strategies for two-layer model predictive control in autonomous vehicle drifting
2025
Cheng Hu, Yangyang Xie, Lei Xie, Michele Magno
Transportation Research Part C: Emerging Technologies 174, 105065
:read more
Authors:Cheng Hu, Yangyang Xie, Lei Xie, Michele Magno
Publication date:05/01/2025
Journal:Transportation Research Part C: Emerging Technologies
Volume:174
Pages:105065
Publisher:Pergamon
Description:Vehicle safety is paramount in autonomous driving, particularly when managing vehicles at extreme side-slip angles—a challenge often overlooked by conventional controllers. Recent studies have focused on vehicle drift control under such extreme conditions. However, tracking complex trajectories while drifting is challenging, especially in the presence of a model mismatch. This paper proposes a two-layer model predictive controller based on sparse variational Gaussian processes. The first layer is responsible for computing the optimal drift equilibrium points, while the second layer is tasked with tracking these points. A variational free energy-based Gaussian process is utilized to compensate for errors in the upper-layer drift equilibrium point calculations and mismatches in the lower-layer controller model. Moreover, the vehicle’s state is determined to be either in transit drift or deep drift based on whether the slip …
Cited by:5
Resources:[PDF] from github.io
:view less
Wakeloc: an ultra-low power, accurate and scalable on-demand rtls using wake-up radios
2025
Silvano Cortesi, Christian Vogt, Michele Magno
arXiv preprint arXiv:2504.20545
:read more
Authors:Silvano Cortesi, Christian Vogt, Michele Magno
Publication date:04/29/2025
Journal:arXiv preprint arXiv:2504.20545
Description:For future large scale robotic moon missions, the availability of infrastructure-less, cheap and low power real-time locating systems (RTLSs) is critical. Traditional RTLS face significant trade-offs between power consumption and localization latency, often requiring anchors to be connected to the power grid or sacrificing speed for energy efficiency. This paper proposes WakeLoc, an on-demand RTLS based on ultra-wideband (UWB), enabling both low-latency and ultra-low power consumption by leveraging UWB wake-up radios (WuRs). In WakeLoc, tags independently start a localization procedure by sending a wake-up call (WuC) to anchors, before performing the actual localization. Distributed tags equipped with WuRs listen to the WuC and use passive listening of the UWB messages to determine their own position. Experimental measurements demonstrate that the localization accuracy in a 2D setup achieves less than 12.9cm error, both for the active and the passive tag. Additional power simulations based on real-world measurements were performed in a realistic environment, showing that anchors can achieve a power consumption as low as 15.53{mu}W while the RTLS performs one on-demand localization per minute for 5 tags, thus operate up to 5.01 years on a single coin cell battery (690mWh).
Cited by:3
Resources:[PDF] from arxiv.org
:view less
Enhancing autonomous driving systems with on-board deployed large language models
2025
Nicolas Baumann, Cheng Hu, Paviththiren Sivasothilingam, Haotong Qin, Lei Xie, Michele …
arXiv preprint arXiv:2504.11514
:read more
Authors:Nicolas Baumann, Cheng Hu, Paviththiren Sivasothilingam, Haotong Qin, Lei Xie, Michele Magno, Luca Benini
Publication date:04/15/2025
Journal:arXiv preprint arXiv:2504.11514
Description:Neural Networks (NNs) trained through supervised learning struggle with managing edge-case scenarios common in real-world driving due to the intractability of exhaustive datasets covering all edge-cases, making knowledge-driven approaches, akin to how humans intuitively detect unexpected driving behavior, a suitable complement to data-driven methods. This work proposes a hybrid architecture combining low-level Model Predictive Controller (MPC) with locally deployed Large Language Models (LLMs) to enhance decision-making and Human Machine Interaction (HMI). The DecisionxLLM module evaluates robotic state information against natural language instructions to ensure adherence to desired driving behavior. The MPCxLLM module then adjusts MPC parameters based on LLM-generated insights, achieving control adaptability while preserving the safety and constraint guarantees of traditional MPC systems. Further, to enable efficient on-board deployment and to eliminate dependency on cloud connectivity, we shift processing to the on-board computing platform: We propose an approach that exploits Retrieval Augmented Generation (RAG), Low Rank Adaptation (LoRA) fine-tuning, and quantization. Experimental results demonstrate that these enhancements yield significant improvements in reasoning accuracy by up to 10.45%, control adaptability by as much as 52.2%, and up to 10.5x increase in computational efficiency (tokens/s), validating the proposed framework's practicality for real-time deployment even on down-scaled robotic platforms. This work bridges high-level decision-making with low-level control adaptability …
Cited by:3
Resources:[PDF] from arxiv.org
:view less
TinyCenterSpeed: Efficient Center-Based Object Detection for Autonomous Racing
2025
Neil Reichlin, Nicolas Baumann, Edoardo Ghignone, Michele Magno
arXiv preprint arXiv:2504.08655
:read more
Authors:Neil Reichlin, Nicolas Baumann, Edoardo Ghignone, Michele Magno
Publication date:04/11/2025
Journal:arXiv preprint arXiv:2504.08655
Description:Perception within autonomous driving is nearly synonymous with Neural Networks (NNs). Yet, the domain of autonomous racing is often characterized by scaled, computationally limited robots used for cost-effectiveness and safety. For this reason, opponent detection and tracking systems typically resort to traditional computer vision techniques due to computational constraints. This paper introduces TinyCenterSpeed, a streamlined adaptation of the seminal CenterPoint method, optimized for real-time performance on 1:10 scale autonomous racing platforms. This adaptation is viable even on OBCs powered solely by Central Processing Units (CPUs), as it incorporates the use of an external Tensor Processing Unit (TPU). We demonstrate that, compared to Adaptive Breakpoint Detector (ABD), the current State-of-the-Art (SotA) in scaled autonomous racing, TinyCenterSpeed not only improves detection and velocity estimation by up to 61.38% but also supports multi-opponent detection and estimation. It achieves real-time performance with an inference time of just 7.88 ms on the TPU, significantly reducing CPU utilization 8.3-fold.
Resources:[PDF] from arxiv.org
:view less
Mpq-dm: Mixed precision quantization for extremely low bit diffusion models
2025
Weilun Feng, Haotong Qin, Chuanguang Yang, Zhulin An, Libo Huang, Boyu Diao, Fei Wang, …
Proceedings of the AAAI Conference on Artificial Intelligence 39 (16), 16595-16603
:read more
Authors:Weilun Feng, Haotong Qin, Chuanguang Yang, Zhulin An, Libo Huang, Boyu Diao, Fei Wang, Renshuai Tao, Yongjun Xu, Michele Magno
Publication date:04/11/2025
Journal:Proceedings of the AAAI Conference on Artificial Intelligence
Volume:39
Issue:16
Pages:16595-16603
Description:Diffusion models have received wide attention in generation tasks. However, the expensive computation cost prevents the application of diffusion models in resource-constrained scenarios. Quantization emerges as a practical solution that significantly saves storage and computation by reducing the bit-width of parameters. However, the existing quantization methods for diffusion models still cause severe degradation in performance, especially under extremely low bit-widths (2-4 bit). The primary decrease in performance comes from the significant discretization of activation values at low bit quantization. Too few activation candidates are unfriendly for outlier significant weight channel quantization, and the discretized features prevent stable learning over different time steps of the diffusion model. This paper presents MPQ-DM, a Mixed-Precision Quantization method for Diffusion Models. The proposed MPQ-DM mainly relies on two techniques:(1) To mitigate the quantization error caused by outlier severe weight channels, we propose an Outlier-Driven Mixed Quantization (OMQ) technique that uses Kurtosis to quantify outlier salient channels and apply optimized intra-layer mixed-precision bit-width allocation to recover accuracy performance within target efficiency.(2) To robustly learn representations crossing time steps, we construct a Time-Smoothed Relation Distillation (TRD) scheme between the quantized diffusion model and its full-precision counterpart, transferring discrete and continuous latent to a unified relation space to reduce the representation inconsistency. Comprehensive experiments demonstrate that MPQ-DM achieves significant …
Cited by:11
Resources:[PDF] from aaai.org
:view less
GP-enhanced Autonomous Drifting Framework using ADMM-based iLQR
2025
Yangyang Xie, Cheng Hu, Nicolas Baumann, Edoardo Ghignone, Michele Magno, Lei Xie
arXiv preprint arXiv:2503.11083
:read more
Authors:Yangyang Xie, Cheng Hu, Nicolas Baumann, Edoardo Ghignone, Michele Magno, Lei Xie
Publication date:03/14/2025
Journal:arXiv preprint arXiv:2503.11083
Description:Autonomous drifting is a complex challenge due to the highly nonlinear dynamics and the need for precise real-time control, especially in uncertain environments. To address these limitations, this paper presents a hierarchical control framework for autonomous vehicles drifting along general paths, primarily focusing on addressing model inaccuracies and mitigating computational challenges in real-time control. The framework integrates Gaussian Process (GP) regression with an Alternating Direction Method of Multipliers (ADMM)-based iterative Linear Quadratic Regulator (iLQR). GP regression effectively compensates for model residuals, improving accuracy in dynamic conditions. ADMM-based iLQR not only combines the rapid trajectory optimization of iLQR but also utilizes ADMM's strength in decomposing the problem into simpler sub-problems. Simulation results demonstrate the effectiveness of the proposed framework, with significant improvements in both drift trajectory tracking and computational efficiency. Our approach resulted in a 38 reduction in RMSE lateral error and achieved an average computation time that is 75 lower than that of the Interior Point OPTimizer (IPOPT).
Resources:[PDF] from arxiv.org
:view less
Smart Feeding Station: Non-Invasive, Automated IoT Monitoring of Goodman’s Mouse Lemurs in a Semi-Natural Rainforest Habitat
2025
Jonas Peter, Victor Luder, Leyla Rivero Davis, Lukas Schulthess, Michele Magno
arXiv preprint arXiv:2503.09238
:read more
Authors:Jonas Peter, Victor Luder, Leyla Rivero Davis, Lukas Schulthess, Michele Magno
Publication date:03/12/2025
Journal:arXiv preprint arXiv:2503.09238
Description:In recent years, zoological institutions have made significant strides to reimagine ex situ animal habitats, moving away from traditional single-species enclosures towards expansive multi-species environments, more closely resembling semi-natural ecosystems. This paradigm shift, driven by a commitment to animal welfare, encourages a broader range of natural behaviors through abiotic and biotic interactions. This laudable progression nonetheless introduces challenges for population monitoring, adapting daily animal care, and automating data collection for long-term research studies. This paper presents an IoT-enabled wireless smart feeding station tailored to Goodman's mouse lemurs (Microcebus lehilahytsara). System design integrates a precise Radio Frequency Identification (RFID) reader to identify the animals' implanted RFID chip simultaneously recording body weight and visit duration. Leveraging sophisticated electronic controls, the station can selectively activate a trapping mechanism for individuals with specific tags when needed. Collected data or events like a successful capture are forwarded over the Long Range Wide Area Network (LoRaWAN) to a web server and provided to the animal caretakers. To validate functionality and reliability under harsh conditions of a tropical climate, the feeding station was tested in the semi-natural Masoala rainforest biome at Zoo Zurich over two months. The station detected an animal's RFID chip when visiting the box with 98.68 % reliability, a LoRaWAN transmission reliability of 97.99 %, and a deviation in weighing accuracy below 0.41 g. Beyond its immediate application, this system …
Cited by:2
Resources:[PDF] from arxiv.org
:view less
FSDP: Fast and Safe Data-Driven Overtaking Trajectory Planning for Head-to-Head Autonomous Racing Competitions
2025
Cheng Hu, Jihao Huang, Wule Mao, Yonghao Fu, Xuemin Chi, Haotong Qin, Nicolas Baumann, …
arXiv preprint arXiv:2503.06075
:read more
Authors:Cheng Hu, Jihao Huang, Wule Mao, Yonghao Fu, Xuemin Chi, Haotong Qin, Nicolas Baumann, Zhitao Liu, Michele Magno, Lei Xie
Publication date:03/08/2025
Journal:arXiv preprint arXiv:2503.06075
Description:Generating overtaking trajectories in autonomous racing is a challenging task, as the trajectory must satisfy the vehicle's dynamics and ensure safety and real-time performance running on resource-constrained hardware. This work proposes the Fast and Safe Data-Driven Planner to address this challenge. Sparse Gaussian predictions are introduced to improve both the computational efficiency and accuracy of opponent predictions. Furthermore, the proposed approach employs a bi-level quadratic programming framework to generate an overtaking trajectory leveraging the opponent predictions. The first level uses polynomial fitting to generate a rough trajectory, from which reference states and control inputs are derived for the second level. The second level formulates a model predictive control optimization problem in the Frenet frame, generating a trajectory that satisfies both kinematic feasibility and safety. Experimental results on the F1TENTH platform show that our method outperforms the State-of-the-Art, achieving an 8.93% higher overtaking success rate, allowing the maximum opponent speed, ensuring a smoother ego trajectory, and reducing 74.04% computational time compared to the Predictive Spliner method. The code is available at: https://github.com/ZJU-DDRX/FSDP.
Cited by:1
Resources:[PDF] from arxiv.org
:view less
Guest Editorial Special Issue on Energy-Efficient Embedded Intelligent Sensor Systems (S1)
2025
Michele Magno, Daniela de Venuto, Giuseppe Ferri, Seonyeong Heo
IEEE Sensors Journal 25 (5), 7733-7733
:read more
Authors:Michele Magno, Daniela de Venuto, Giuseppe Ferri, Seonyeong Heo
Publication date:03/05/2025
Journal:IEEE Sensors Journal
Volume:25
Issue:5
Pages:7733-7733
Publisher:IEEE
Description:THE Special Issue on Energy-Efficient Embedded Intelli-gent Sensor Systems is motivated by the growing demand for low-power, highly integrated sensor technologies that can operate autonomously in diverse applications. The scope covers innovative circuit and system designs, novel materials and device architectures, advanced signal processing and artificial intelligence techniques for resource-constrained environments, and real-world implementations in areas such as healthcare, environmental monitoring, industrial automation, and smart cities. A broad call for papers (CFP) was issued to the global research community, focusing on topics such as energy harvesting and power management for sensors, ultra-low-power circuitry, embedded AI and edge computing, novel sensing principles, high-density sensor integration, and sustainable deployment strategies. We received manuscript submissions from …
:view less
BodySense: An Expandable and Wearable-Sized Wireless Evaluation Platform for Human Body Communication
2025
Lukas Schulthess, Philipp Mayer, Christian Vogt, Luca Benini, Michele Magno
arXiv preprint arXiv:2503.13462
:read more
Authors:Lukas Schulthess, Philipp Mayer, Christian Vogt, Luca Benini, Michele Magno
Publication date:02/07/2025
Journal:arXiv preprint arXiv:2503.13462
Description:Wearable, wirelessly connected sensors have become a common part of daily life and have the potential to play a pivotal role in shaping the future of personalized healthcare. A key challenge in this evolution is designing long-lasting and unobtrusive devices. These design requirements inherently demand smaller batteries, inevitably increasing the need for energy-sensitive wireless communication interfaces. Capacitive Human Body Communication (HBC) is a promising, power-efficient alternative to traditional RF-based communication, enabling point-to-multipoint data and energy exchange. However, as this concept relies on capacitive coupling to the surrounding area, it is naturally influenced by uncontrollable environmental factors, making testing with classical setups particularly challenging. This work presents a customizable, wearable-sized, wireless evaluation platform for capacitive HBC, designed to enable realistic evaluation of wearable-to-wearable applications. Comparative measurements of channel gains were conducted using classical grid-connected and wireless Data Acquisition (DAQ) across various transmission distances within the frequency range of 4 MHz to 64 MHz and revealed an average overestimation of 18.15 dB over all investigated distances in the classical setup.
Resources:[PDF] from arxiv.org
:view less
RLPP: A Residual Method for Zero-Shot Real-World Autonomous Racing on Scaled Platforms
2025
Edoardo Ghignone, Nicolas Baumann, Cheng Hu, Jonathan Wang, Lei Xie, Andrea Carron, Mic…
arXiv preprint arXiv:2501.17311
:read more
Authors:Edoardo Ghignone, Nicolas Baumann, Cheng Hu, Jonathan Wang, Lei Xie, Andrea Carron, Michele Magno
Publication date:01/28/2025
Journal:arXiv preprint arXiv:2501.17311
Description:Autonomous racing presents a complex environment requiring robust controllers capable of making rapid decisions under dynamic conditions. While traditional controllers based on tire models are reliable, they often demand extensive tuning or system identification. Reinforcement Learning (RL) methods offer significant potential due to their ability to learn directly from interaction, yet they typically suffer from the sim-to-real gap, where policies trained in simulation fail to perform effectively in the real world. In this paper, we propose RLPP, a residual RL framework that enhances a Pure Pursuit (PP) controller with an RL-based residual. This hybrid approach leverages the reliability and interpretability of PP while using RL to fine-tune the controller's performance in real-world scenarios. Extensive testing on the F1TENTH platform demonstrates that RLPP improves lap times of the baseline controllers by up to 6.37 %, closing the gap to the State-of-the-Art methods by more than 52 % and providing reliable performance in zero-shot real-world deployment, overcoming key challenges associated with the sim-to-real transfer and reducing the performance gap from simulation to reality by more than 8-fold when compared to the baseline RL controller. The RLPP framework is made available as an open-source tool, encouraging further exploration and advancement in autonomous racing research. The code is available at: www.github.com/forzaeth/rlpp.
Cited by:1
Resources:[PDF] from arxiv.org
:view less
Learning-based on-track system identification for scaled autonomous racing in under a minute
2025
Onur Dikici, Edoardo Ghignone, Cheng Hu, Nicolas Baumann, Lei Xie, Andrea Carron, Miche…
IEEE Robotics and Automation Letters
:read more
Authors:Onur Dikici, Edoardo Ghignone, Cheng Hu, Nicolas Baumann, Lei Xie, Andrea Carron, Michele Magno, Matteo Corno
Publication date:01/08/2025
Journal:IEEE Robotics and Automation Letters
Publisher:IEEE
Description:Accurate tire modeling is crucial for optimizing autonomous racing vehicles, as State-of-the-Art (SotA) model-based techniques rely on precise knowledge of the vehicle's parameters, yet system identification in dynamic racing conditions is challenging due to varying track and tire conditions. Traditional methods require extensive operational ranges, often impractical in racing scenarios. Machine Learning (ML)-based methods, while improving performance, struggle with generalization and depend on accurate initialization. This paper introduces a novel on-track system identification algorithm, incorporating a Neural Network (NN) for error correction, which is then employed for traditional system identification with virtually generated data. Crucially, the process is iteratively reapplied, with tire parameters updated at each cycle, leading to notable improvements in accuracy in tests on a scaled vehicle. Experiments show …
Cited by:8
Resources:[PDF] from arxiv.org
:view less
Towards Low-Latency Event-based Obstacle Avoidance on a FPGA-Drone
2025
Pietro Bonazzi, Christian Vogt, Michael Jost, Lyes Khacef, Federico Paredes-Vallés, Mic…
Proceedings of the Computer Vision and Pattern Recognition Conference, 4938-4946
:read more
Authors:Pietro Bonazzi, Christian Vogt, Michael Jost, Lyes Khacef, Federico Paredes-Vallés, Michele Magno
Publication date:01/01/2025
Journal:Proceedings of the Computer Vision and Pattern Recognition Conference
Pages:4938-4946
Description:This work quantitatively evaluates the performance of event-based vision systems (EVS) against conventional RGB-based models for action prediction in collision avoidance on an FPGA accelerator. Our experiments demonstrate that the EVS model achieves a significantly higher effective frame rate (1 kHz) and lower temporal (-20 ms) and spatial prediction errors (-20 mm) compared to the RGB-based model, particularly when tested on out-of-distribution data. The EVS model also exhibits superior robustness in selecting optimal evasion maneuvers. In particular, in distinguishing between movement and stationary states, it achieves a 59 percentage point advantage in precision (78% vs. 19%) and a substantially higher F1 score (0.73 vs. 0.06), highlighting the susceptibility of the RGB model to overfitting. Further analysis in different combinations of spatial classes confirms the consistent performance of the EVS model in both test data sets. Finally, we evaluated the system end-to-end and achieved a latency of approximately 2.14 ms, with event aggregation (1 ms) and inference on the processing unit (0.94 ms) accounting for the largest components. These results underscore the advantages of event-based vision for real-time collision avoidance and demonstrate its potential for deployment in resource-constrained environments.
Cited by:1
Resources:[PDF] from thecvf.com
:view less
Development of an implantable sensor system for in vivo strain, temperature, and pH monitoring: comparative evaluation of titanium and resorbable magnesium plates
2025
Andrea M Rich, Wolfgang Rubin, Stefan Rickli, Tatiana Akhmetshina, Jacopo Cossu, Leopol…
Bioactive Materials 43, 603-618
:read more
Authors:Andrea M Rich, Wolfgang Rubin, Stefan Rickli, Tatiana Akhmetshina, Jacopo Cossu, Leopold Berger, Michele Magno, Katja M Nuss, Benoît Schaller, Jörg F Löffler
Publication date:01/01/2025
Journal:Bioactive Materials
Volume:43
Pages:603-618
Publisher:Elsevier
Description:Biodegradable magnesium is a highly desired material for fracture fixation implants because of its good mechanical properties and ability to completely dissolve in the body over time, eliminating the need for a secondary surgery to remove the implant. Despite extensive research on these materials, there remains a dearth of information regarding critical factors that affect implant performance in clinical applications, such as the in vivo pH and mechanical loading conditions. We developed a measurement system with implantable strain, temperature, pH and motion sensors to characterize magnesium and titanium plates, fixating bilateral zygomatic arch osteotomies in three Swiss alpine sheep for eight weeks. pH 1–2 mm above titanium plates was 6.6 ± 0.4, while for magnesium plates it was slightly elevated to 7.4 ± 0.8. Strains on magnesium plates were higher than on titanium plates, possibly due to the lower Young …
Cited by:6
Resources:[HTML] from sciencedirect.com
:view less
An empirical study of llama3 quantization: From llms to mllms
2024
Wei Huang, Xingyu Zheng, Xudong Ma, Haotong Qin, Chengtao Lv, Hong Chen, Jie Luo, Xiaoj…
Visual Intelligence 2 (1), 36
:read more
Authors:Wei Huang, Xingyu Zheng, Xudong Ma, Haotong Qin, Chengtao Lv, Hong Chen, Jie Luo, Xiaojuan Qi, Xianglong Liu, Michele Magno
Publication date:12/30/2024
Journal:Visual Intelligence
Volume:2
Issue:1
Pages:36
Publisher:Springer Nature Singapore
Description:The LLaMA family, a collection of foundation language models ranging from 7B to 65B parameters, has become one of the most powerful open-source large language models (LLMs) and the popular LLM backbone of multi-modal large language models (MLLMs), widely used in computer vision and natural language understanding tasks. In particular, LLaMA3 models have recently been released and have achieved impressive performance in various domains with super-large scale pre-training on over 15T tokens of data. Given the wide application of low-bit quantization for LLMs in resource-constrained scenarios, we explore LLaMA3’s capabilities when quantized to low bit-width. This exploration can potentially provide new insights and challenges for the low-bit quantization of LLaMA3 and other future LLMs, especially in addressing performance degradation issues that suffer in LLM compression. Specifically, we …
Cited by:48
Resources:[HTML] from springer.com
Full View
:view less
ElectraSight: smart glasses with fully onboard non-invasive eye tracking using hybrid contact and contactless EOG
2024
Nicolas Schärer, Federico Villani, Aishwarya Melatur, Steven Peter, Tommaso Polonelli, …
arXiv preprint arXiv:2412.14848
:read more
Authors:Nicolas Schärer, Federico Villani, Aishwarya Melatur, Steven Peter, Tommaso Polonelli, Michele Magno
Publication date:12/19/2024
Journal:arXiv preprint arXiv:2412.14848
Description:Smart glasses with integrated eye tracking technology are revolutionizing diverse fields, from immersive augmented reality experiences to cutting-edge health monitoring solutions. However, traditional eye tracking systems rely heavily on cameras and significant computational power, leading to high-energy demand and privacy issues. Alternatively, systems based on electrooculography (EOG) provide superior battery life but are less accurate and primarily effective for detecting blinks, while being highly invasive. The paper introduces ElectraSight, a non-invasive plug-and-play low-power eye tracking system for smart glasses. The hardware-software co-design of the system is detailed, along with the integration of a hybrid EOG (hEOG) solution that incorporates both contact and contactless electrodes. Within 79 kB of memory, the proposed tinyML model performs real-time eye movement classification with 81% accuracy for 10 classes and 92% for 6 classes, not requiring any calibration or user-specific fine-tuning. Experimental results demonstrate that ElectraSight delivers high accuracy in eye movement and blink classification, with minimal overall movement detection latency (90% within 60 ms) and an ultra-low computing time (301 {mu}s). The power consumption settles down to 7.75 mW for continuous data acquisition and 46 mJ for the tinyML inference. This efficiency enables continuous operation for over 3 days on a compact 175 mAh battery. This work opens new possibilities for eye tracking in commercial applications, offering an unobtrusive solution that enables advancements in user interfaces, health diagnostics, and hands-free control …
Cited by:6
Resources:[PDF] from arxiv.org
:view less
Predictive spliner: Data-driven overtaking in autonomous racing using opponent trajectory prediction
2024
Nicolas Baumann, Edoardo Ghignone, Cheng Hu, Benedict Hildisch, Tino Hämmerle, Alessand…
IEEE Robotics and Automation Letters
:read more
Authors:Nicolas Baumann, Edoardo Ghignone, Cheng Hu, Benedict Hildisch, Tino Hämmerle, Alessandro Bettoni, Andrea Carron, Lei Xie, Michele Magno
Publication date:12/18/2024
Journal:IEEE Robotics and Automation Letters
Publisher:IEEE
Description:Head-to-head racing against opponents is a challenging and emerging topic in the domain of autonomous racing. We propose Predictive Spliner, a data-driven overtaking planner designed to enhance competitive performance by anticipating opponent behavior. Using Gaussian Process (GP) regression, the method learns and predicts the opponent's trajectory, enabling the ego vehicle to calculate safe and effective overtaking maneuvers. Experimentally validated on a 1:10 scale autonomous racing platform, Predictive Spliner outperforms commonly employed overtaking algorithms by overtaking opponents at up to 83.1% of its own speed, being on average 8.4% faster than the previous best-performing method. Additionally, it achieves an average success rate of 84.5%, which is 47.6% higher than the previous best-performing method. The proposed algorithm maintains computational efficiency with a Central …
Cited by:4
Resources:[PDF] from arxiv.org
:view less
BatDeck–Ultra Low-power Ultrasonic Ego-velocity Estimation and Obstacle Avoidance on Nano-drones
2024
Hanna Müller, Victor Kartsch, Michele Magno, Luca Benini
arXiv preprint arXiv:2412.10048
:read more
Authors:Hanna Müller, Victor Kartsch, Michele Magno, Luca Benini
Publication date:12/13/2024
Journal:arXiv preprint arXiv:2412.10048
Description:Nano-drones, with their small, lightweight design, are ideal for confined-space rescue missions and inherently safe for human interaction. However, their limited payload restricts the critical sensing needed for ego-velocity estimation and obstacle detection to single-bean laser-based time-of-flight (ToF) and low-resolution optical sensors. Although those sensors have demonstrated good performance, they fail in some complex real-world scenarios, especially when facing transparent or reflective surfaces (ToFs) or when lacking visual features (optical-flow sensors). Taking inspiration from bats, this paper proposes a novel two-way ranging-based method for ego-velocity estimation and obstacle avoidance based on down-and-forward facing ultra-low-power ultrasonic sensors, which improve the performance when the drone faces reflective materials or navigates in complete darkness. Our results demonstrate that our new sensing system achieves a mean square error of 0.019 m/s on ego-velocity estimation and allows exploration for a flight time of 8 minutes while covering 136 m on average in a challenging environment with transparent and reflective obstacles. We also compare ultrasonic and laser-based ToF sensing techniques for obstacle avoidance, as well as optical flow and ultrasonic-based techniques for ego-velocity estimation, denoting how these systems and methods can be complemented to enhance the robustness of nano-drone operations.
Resources:[PDF] from arxiv.org
:view less
Tc-driver: A trajectory conditioned reinforcement learning approach to zero-shot autonomous racing
2024
Edoardo Ghignone, Nicolas Baumann, Michele Magno
IEEE Transactions on Field Robotics
:read more
Authors:Edoardo Ghignone, Nicolas Baumann, Michele Magno
Publication date:11/15/2024
Journal:IEEE Transactions on Field Robotics
Publisher:IEEE
Description:Autonomous racing challenges perception, planning, and control algorithms, serving as a testbed for general autonomous driving. While traditional methods, such as model predictive control (MPC), can generate optimal control sequences, they are sensitive to modeling parameter accuracy. This article introduces trajectory-conditioned RL controller (TC-Driver), a reinforcement learning (RL) approach for robust control in autonomous racing, addressing tire parameter modeling inaccuracies. TC-Driver is conditioned by a trajectory from any high-level planner, combining RL’s learning capabilities with the reliability of traditional planning. Trained under varying tire conditions, it aims to generalize across different model parameters, enhancing real-world racing performance. Experimental results show TC-Driver improves generalization robustness compared with a state-of-the-art (SotA) end-to-end architecture. It …
Cited by:19
Resources:[PDF] from ieee.org
:view less
Gwq: Gradient-aware weight quantization for large language models
2024
Yihua Shao, Yan Gu, Siyu Chen, Haiyang Liu, Zixian Zhu, Zijian Ling, Minxi Yan, Ziyang …
arXiv preprint arXiv:2411.00850
:read more
Authors:Yihua Shao, Yan Gu, Siyu Chen, Haiyang Liu, Zixian Zhu, Zijian Ling, Minxi Yan, Ziyang Yan, Chenyu Zhang, Michele Magno, Haotong Qin, Yan Wang, Jingcai Guo, Ling Shao, Hao Tang
Publication date:10/30/2024
Journal:arXiv preprint arXiv:2411.00850
Description:Large language models (LLMs) show impressive performance in solving complex language tasks. However, its large number of parameters presents significant challenges for the deployment. So, compressing LLMs to low bits can enable to deploy on resource-constrained devices. To address this problem, we propose gradient-aware weight quantization (GWQ), the first quantization approach for low-bit weight quantization that leverages gradients to localize outliers, requiring only a minimal amount of calibration data for outlier detection. GWQ retains the top 1% outliers preferentially at FP16 precision, while the remaining non-outlier weights are stored in a low-bit. We widely evaluate GWQ on different task include language modeling, grounding detection, massive multitask language understanding and vision-language question and answering. Results show that models quantified by GWQ performs better than other quantization method. During quantization process, GWQ only need one calibration set to realize effective quant. Also, GWQ achieves 1.2x inference speedup in comparison to the original model and effectively reduces the inference memory.
Cited by:12
Resources:[PDF] from arxiv.org
:view less
SuperBat-Advancing Obstacle Avoidance on Nano-UAVs by Fusing Ultrasonic and Laser-based Time-of-Flight Sensors
2024
Laurent Schroeder, Hanna Müller, Tommaso Polonelli, Michele Magno, Luca Benini
2024 IEEE International Symposium on Systems Engineering (ISSE), 1-8
:read more
Authors:Laurent Schroeder, Hanna Müller, Tommaso Polonelli, Michele Magno, Luca Benini
Publication date:10/16/2024
Journal:2024 IEEE International Symposium on Systems Engineering (ISSE)
Pages:1-8
Publisher:IEEE
Description:Nano-Unmanned Aerial Vehicles (UAVs) hold significant promise in various applications, such as exploring ducts or aiding rescue missions in proximity to humans. Their small dimensions make them ideal to operate indoor but pose challenges in terms of payload capacity and onboard computation power. Establishing a robust Obstacle Avoidance (OA) onboard algorithm, able to operate reliably across diverse environments with various materials including transparent and reflective surfaces, is still an open challenge. Recent approaches have pointed to sensor fusion as a path towards reliable OA. In this paper, we fuse a 64-pixel laser-based Time-of-Flight (ToF) sensor (VL53L5CX) and an ultrasonic sensor (ICU-30201) in our computationally lightweight navigation policy to achieve robust and efficient OA. The field tests are based on the Crazyflie 2.1 platform (CF), resulting in a total flight mass of 38 g …
Cited by:1
:view less
SwiftEagle: An Advanced Open-Source, Miniaturized FPGA UAS Platform with Dual DVS/Frame Camera for Cutting-Edge Low-Latency Autonomous Algorithms
2024
Christian Vogt, Michael Jost, Michele Magno
2024 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 8134-8140
:read more
Authors:Christian Vogt, Michael Jost, Michele Magno
Publication date:10/14/2024
Journal:2024 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)
Pages:8134-8140
Publisher:IEEE
Description:Low-latency sensing and decision-making processing are critical requirements for the highly dynamic control and perception applications often found in Unmanned Areal Systems (UASs). Novel sensors such as Dynamic Vision Sensors (DVSs) are enhancing the pure performance of the perception component with orders of magnitude lower latency. However, they are typically not optimally integrated with the computing hardware, which effectively reduces the potential in both latency and power consumption. In addition to the non-optimal integration, low latency processing of such high data rate generating sensors is often challenging on resource-constrained platforms. Here, Field Programmable Gate Arrays (FPGAs) platforms offer a promising set of features, including low-level access to hardware and memories, as well as high-speed interfaces. On the other hand, FPGA platforms are not as popular on UASs due …
Cited by:3
:view less
A Proximity-Based Approach for Dynamically Matching Industrial Assets and Their Operators Using Low-Power IoT Devices
2024
Silvano Cortesi, Michele Crabolu, Prodromos-Vasileios Mekikis, Giovanni Bellusci, Chris…
IEEE Internet of Things Journal
:read more
Authors:Silvano Cortesi, Michele Crabolu, Prodromos-Vasileios Mekikis, Giovanni Bellusci, Christian Vogt, Michele Magno
Publication date:10/14/2024
Journal:IEEE Internet of Things Journal
Publisher:IEEE
Description:Asset tracking solutions have proven their significance in industrial contexts, as evidenced by their successful commercialization (e.g., Hilti On!Track). However, a seamless solution for matching assets with their users, such as operators of construction power tools, is still missing. By enabling asset-user matching, organizations gain valuable insights that can be used to optimize user health and safety, asset utilization, and maintenance. This article introduces a novel approach to address this gap by leveraging existing Bluetooth low energy (BLE)-enabled low-power Internet of Things (IoT) devices. The proposed framework comprises the following components: 1) a wearable device; 2) an IoT device attached to or embedded in the assets; 3) an algorithm to estimate the distance between assets and operators by exploiting simple received signal strength indicator (RSSI) measurements via an extended Kalman filter …
Cited by:2
Resources:[PDF] from arxiv.org
:view less
CR3DT: camera-radar fusion for 3D detection and tracking
2024
Nicolas Baumann, Michael Baumgartner, Edoardo Ghignone, Jonas Kühne, Tobias Fischer, Yu…
2024 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 4926-4933
:read more
Authors:Nicolas Baumann, Michael Baumgartner, Edoardo Ghignone, Jonas Kühne, Tobias Fischer, Yung-Hsu Yang, Marc Pollefeys, Michele Magno
Publication date:10/14/2024
Journal:2024 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)
Pages:4926-4933
Publisher:IEEE
Description:To enable self-driving vehicles accurate detection and tracking of surrounding objects is essential. While Light Detection and Ranging (LiDAR) sensors have set the benchmark for high-performance systems, the appeal of camera-only solutions lies in their cost-effectiveness. Notably, despite the prevalent use of Radio Detection and Ranging (RADAR) sensors in automotive systems, their potential in 3D detection and tracking has been largely disregarded due to data sparsity and measurement noise. As a recent development, the combination of RADARs and cameras is emerging as a promising solution. This paper presents Camera-RADAR 3D Detection and Tracking (CR3DT), a camera-RADAR fusion model for 3D object detection, and Multi-Object Tracking (MOT). Building upon the foundations of the State-of-the-Art (SotA) camera-only BEVDet architecture, CR3DT demonstrates substantial improvements in both …
Cited by:15
Resources:[PDF] from arxiv.org
:view less
On-device learning of EEGNet-based network for wearable motor imagery Brain-Computer Interface
2024
Sizhen Bian, Pixi Kang, Julian Moosmann, Mengxi Liu, Pietro Bonazzi, Roman Rosipal, Mic…
Proceedings of the 2024 ACM International Symposium on Wearable Computers, 9-16
:read more
Authors:Sizhen Bian, Pixi Kang, Julian Moosmann, Mengxi Liu, Pietro Bonazzi, Roman Rosipal, Michele Magno
Publication date:10/05/2024
Journal:Proceedings of the 2024 ACM International Symposium on Wearable Computers
Pages:9-16
Description:Electroencephalogram (EEG)-based Brain-Computer Interfaces (BCIs) have garnered significant interest across various domains, including rehabilitation and robotics. Despite advancements in neural network-based EEG decoding, maintaining performance across diverse user populations remains challenging due to feature distribution drift. This paper presents an effective approach to address this challenge by implementing a lightweight and efficient on-device learning engine for wearable motor imagery recognition. The proposed approach, applied to the well-established EEGNet architecture, enables real-time and accurate adaptation to EEG signals from unregistered users. Leveraging the newly released low-power parallel RISC-V-based processor, GAP9 from Greeenwaves, and the Physionet EEG Motor Imagery dataset, we demonstrate a remarkable accuracy gain of up to 7.31% with respect to the baseline …
Cited by:10
Resources:[PDF] from arxiv.org
:view less
Earable and wrist-worn setup for accurate step counting utilizing body-area electrostatic sensing
2024
Sizhen Bian, Rakita Strahinja, Philipp Schilk, Clénin Marc-André, Silvano Cortesi, Kani…
Companion of the 2024 on ACM International Joint Conference on Pervasive and Ubiquitous…
:read more
Authors:Sizhen Bian, Rakita Strahinja, Philipp Schilk, Clénin Marc-André, Silvano Cortesi, Kanika Dheman, Elio Reinschmidt, Michele Magno
Publication date:10/05/2024
Journal:Companion of the 2024 on ACM International Joint Conference on Pervasive and Ubiquitous Computing
Pages:904-910
Description:Step-counting has been widely implemented in wrist-worn devices and is accepted by end users as a quantitative indicator of everyday exercise. However, existing counting approach (mostly on wrist-worn setup) lacks robustness and thus introduces inaccuracy issues in certain scenarios like brief intermittent walking bouts and random arm motions or static arm status while walking (no clear correlation of motion pattern between arm and leg). This paper proposes a low-power step-counting solution utilizing the body area electric field acquired by a novel electrostatic sensing unit, consuming only 87.3 µW of power, hoping to strengthen the robustness of current dominant solution. We designed two wearable devices for on-the-wrist and in-the-ear deployment and collected body-area electric field-derived motion signals from ten volunteers. Four walking scenarios are considered: in the parking lot/shopping center with …
Cited by:6
Resources:[PDF] from arxiv.org
:view less
Ultra-efficient on-device object detection on ai-integrated smart glasses with tinyissimoyolo
2024
Julian Moosmann, Pietro Bonazzi, Yawei Li, Sizhen Bian, Philipp Mayer, Luca Benini, Mic…
European Conference on Computer Vision, 262-280
:read more
Authors:Julian Moosmann, Pietro Bonazzi, Yawei Li, Sizhen Bian, Philipp Mayer, Luca Benini, Michele Magno
Publication date:09/29/2024
Journal:European Conference on Computer Vision
Pages:262-280
Publisher:Springer Nature Switzerland
Description:Smart glasses are rapidly gaining advanced functions thanks to cutting-edge computing technologies, especially accelerated hardware architectures, and tiny Artificial IntelligenceAI algorithms. However, integrating AI into smart glasses featuring a small form factor and limited battery capacity remains challenging for a satisfactory user experience. To this end, this paper proposes the design of a smart glasses platform for always-on on-device object detection with an all-day battery lifetime. The proposed platform is based on GAP9, a novel multi-core RISC-V processor from Greenwaves Technologies. Additionally, a family of sub-million parameter TinyissimoYOLO networks are proposed. They are benchmarked on established datasets, capable of differentiating up to 80 classes on MS-COCO. Evaluations on the smart glasses prototype demonstrate TinyissimoYOLO’s inference latency of only 17 ms and consuming 1 …
Cited by:25
Resources:[PDF] from arxiv.org
:view less
A survey of low-bit large language models: Basics, systems, and algorithms
2024
Ruihao Gong, Yifu Ding, Zining Wang, Chengtao Lv, Xingyu Zheng, Jinyang Du, Haotong Qin…
arXiv preprint arXiv:2409.16694
:read more
Authors:Ruihao Gong, Yifu Ding, Zining Wang, Chengtao Lv, Xingyu Zheng, Jinyang Du, Haotong Qin, Jinyang Guo, Michele Magno, Xianglong Liu
Publication date:09/25/2024
Journal:arXiv preprint arXiv:2409.16694
Description:Large language models (LLMs) have achieved remarkable advancements in natural language processing, showcasing exceptional performance across various tasks. However, the expensive memory and computational requirements present significant challenges for their practical deployment. Low-bit quantization has emerged as a critical approach to mitigate these challenges by reducing the bit-width of model parameters, activations, and gradients, thus decreasing memory usage and computational demands. This paper presents a comprehensive survey of low-bit quantization methods tailored for LLMs, covering the fundamental principles, system implementations, and algorithmic strategies. An overview of basic concepts and new data formats specific to low-bit LLMs is first introduced, followed by a review of frameworks and systems that facilitate low-bit LLMs across various hardware platforms. Then, we categorize and analyze techniques and toolkits for efficient low-bit training and inference of LLMs. Finally, we conclude with a discussion of future trends and potential advancements of low-bit LLMs. Our systematic overview from basic, system, and algorithm perspectives can offer valuable insights and guidelines for future works to enhance the efficiency and applicability of LLMs through low-bit quantization.
Cited by:25
Resources:[PDF] from arxiv.org
:view less
FPGA-Accelerated Hybrid Lossless and Lossy Compression for Next-Generation Portable Optoacoustic Platforms
2024
Federico Villani, Sevrin Mathys, Çağla Özsoy, Xosé Luís Deán-Ben, Andrea Cossettini, Mi…
2024 IEEE Ultrasonics, Ferroelectrics, and Frequency Control Joint Symposium (UFFC-JS),…
:read more
Authors:Federico Villani, Sevrin Mathys, Çağla Özsoy, Xosé Luís Deán-Ben, Andrea Cossettini, Michele Magno, Daniel Razansky, Luca Benini
Publication date:09/22/2024
Journal:2024 IEEE Ultrasonics, Ferroelectrics, and Frequency Control Joint Symposium (UFFC-JS)
Pages:1-5
Publisher:IEEE
Description:Optoacoustic (OA) imaging combines optical excitation and ultrasound beamforming to render images of deep tissues with functional contrast and high spatial and temporal resolution; however, its high data rates and large channel count pose significant challenges to developing portable OA systems with limited bandwidth and computational resources. In this context, on-device data compression is required to maximize the information throughput. Traditional lossless compression (LLC) preserves image fidelity but is characterized by non-constant compression ratios that can result in bandwidth saturation. On the other hand, lossy compression (LC) achieves higher and controlled compression at the expense of image quality. This work presents an FPGA-based hybrid compression algorithm that dynamically combines LLC and LC to adapt to bandwidth constraints in real-time, ensuring consistent data transmission …
Cited by:1
:view less
Evaluation of encoding schemes on ubiquitous sensor signal for spiking neural network
2024
Sizhen Bian, Elisa Donati, Michele Magno
IEEE Sensors Journal
:read more
Authors:Sizhen Bian, Elisa Donati, Michele Magno
Publication date:09/10/2024
Journal:IEEE Sensors Journal
Publisher:IEEE
Description:Spiking neural networks (SNNs), a brain-inspired computing paradigm, are emerging for their inference performance, particularly in terms of energy efficiency and latency attributed to the plasticity in signal processing. To deploy SNNs in ubiquitous computing systems, signal encoding of sensors is crucial for achieving high accuracy and robustness. Using inertial sensor readings for gym activity recognition as a case study, this work comprehensively evaluates four main encoding schemes and deploys the corresponding SNN on the neuromorphic processor Loihi2 for postdeployment encoding assessment. Rate encoding, time-to-first-spike (TTFS) encoding, binary encoding, and delta modulation are evaluated using metrics such as average fire rate, signal-to-noise ratio (SNR), classification accuracy, robustness, and inference latency and energy. In this case study, the TTFS encoding required the lowest firing rate …
Cited by:13
Resources:[PDF] from arxiv.org
:view less
Aerodynamic Performance and Impact Analysis of a MEMS-Based Non-Invasive Monitoring System for Wind Turbine Blades
2024
Nicolas Schärer, Denis Mikhaylov, Cédric Sievi, Badoui Hanna, Caroline Braud, Julien De…
arXiv preprint arXiv:2408.11458
:read more
Authors:Nicolas Schärer, Denis Mikhaylov, Cédric Sievi, Badoui Hanna, Caroline Braud, Julien Deparday, Sarah Barber, Tommaso Polonelli, Michele Magno
Publication date:08/21/2024
Journal:arXiv preprint arXiv:2408.11458
Description:Wind power generation plays a crucial role in transitioning away from fossil fuel-dependent energy sources, contributing significantly to the mitigation of climate change. Monitoring and evaluating the aerodynamics of large wind turbine rotors is crucial to enable more wind energy deployment. This is necessary to achieve the European climate goal of a reduction in net greenhouse gas emissions by at least 55% by 2030, compared to 1990 levels. This paper presents a comparison between two measurement systems for evaluating the aerodynamic performance of wind turbine rotor blades on a full-scale wind tunnel test. One system uses an array of ten commercial compact ultra-low power micro-electromechanical systems (MEMS) pressure sensors placed on the blade surface, while the other employs high-accuracy lab-based pressure scanners embedded in the airfoil. The tests are conducted at a Reynolds number of 3.5 x 10^6, which represents typical operating conditions for wind turbines. MEMS sensors are of particular interest, as they can enable real-time monitoring which would be impossible with the ground truth system. This work provides an accurate quantification of the impact of the MEMS system on the blade aerodynamics and its measurement accuracy. Our results indicate that MEMS sensors, with a total sensing power below 1.6 mW, can measure key aerodynamic parameters like Angle of Attack (AoA) and flow separation with a precision of 1{deg}. Although there are minor differences in measurements due to sensor encapsulation, the MEMS system does not significantly compromise blade aerodynamics, with a maximum shift in …
Cited by:1
Resources:[PDF] from arxiv.org
:view less
i-CardiAx: Wearable IoT-Driven System for Early Sepsis Detection Through Long-Term Vital Sign Monitoring
2024
Kanika Dheman, Marco Giordano, Cyriac Thomas, Philipp Schilk, Michele Magno
arXiv preprint arXiv:2407.21433
:read more
Authors:Kanika Dheman, Marco Giordano, Cyriac Thomas, Philipp Schilk, Michele Magno
Publication date:07/31/2024
Journal:arXiv preprint arXiv:2407.21433
Description:Sepsis is a significant cause of early mortality, high healthcare costs, and disability-adjusted life years. Digital interventions like continuous cardiac monitoring can help detect early warning signs and facilitate effective interventions. This paper introduces i-CardiAx, a wearable sensor utilizing low-power high-sensitivity accelerometers to measure vital signs crucial for cardiovascular health: heart rate (HR), blood pressure (BP), and respiratory rate (RR). Data collected from 10 healthy subjects using the i-CardiAx chest patch were used to develop and evaluate lightweight vital sign measurement algorithms. The algorithms demonstrated high performance: RR (-0.11 0.77 breathsmin), HR (0.82 2.85 beatsmin), and systolic BP (-0.08 6.245 mmHg). These algorithms are embedded in an ARM Cortex-M33 processor with Bluetooth Low Energy (BLE) support, achieving inference times of 4.2 ms for HR and RR, and 8.5 ms for BP. Additionally, a multi-channel quantized Temporal Convolutional Neural (TCN) Network, trained on the open-source HiRID dataset, was developed to detect sepsis onset using digitally acquired vital signs from i-CardiAx. The quantized TCN, deployed on i-CardiAx, predicted sepsis with a median time of 8.2 hours and an energy per inference of 1.29 mJ. The i-CardiAx wearable boasts a sleep power of 0.152 mW and an average power consumption of 0.77 mW, enabling a 100 mAh battery to last approximately two weeks (432 hours) with continuous monitoring of HR, BP, and RR at 30 measurements per hour and running inference every 30 minutes. In conclusion, i-CardiAx offers an energy-efficient, high-sensitivity …
Cited by:7
Resources:[PDF] from arxiv.org
:view less
Noise Analysis and Modeling of the PMD Flexx2 Depth Camera for Robotic Applications
2024
Yuke Cai, Davide Plozza, Steven Marty, Paul Joseph, Michele Magno
2024 IEEE International Conference on Omni-layer Intelligent Systems (COINS), 1-6
:read more
Authors:Yuke Cai, Davide Plozza, Steven Marty, Paul Joseph, Michele Magno
Publication date:07/29/2024
Journal:2024 IEEE International Conference on Omni-layer Intelligent Systems (COINS)
Pages:1-6
Publisher:IEEE
Description:Ahstract-Time of Flight (ToF) cameras, renowned for their ability to capture real-time 3D information, have become indispensable for agile mobile robotics. These cameras utilize light signals to accurately measure distances, enabling robots to navigate complex environments with precision. Innovative depth cameras, characterized by their compact size and lightweight design, such as the recently released PMD Flexx2, are particularly suited for mobile robots. Capable of achieving high frame rates while capturing depth information, this innovative sensor is suitable for tasks such as robot navigation and terrain mapping. Operating on the ToF measurement principle, the sensor offers multiple benefits over classic stereo-based depth cameras. However, the depth images produced by the camera are subject to noise from multiple sources, complicating their simulation. This paper proposes an accurate quantification and …
Cited by:3
Resources:[PDF] from arxiv.org
:view less
Gaze-Guided Semi-Autonomous Quadruped Robot for Enhanced Assisted Living
2024
Paul Joseph, Davide Plozza, Luca Pascarella, Michele Magno
2024 IEEE Sensors Applications Symposium (SAS), 1-6
:read more
Authors:Paul Joseph, Davide Plozza, Luca Pascarella, Michele Magno
Publication date:07/23/2024
Journal:2024 IEEE Sensors Applications Symposium (SAS)
Pages:1-6
Publisher:IEEE
Description:Robotic automation represents mankind's next leap. While the industry has already embraced robotization, robot-driven domestic aid is only at the beginning of the revolution. Dealing with unconstrained daily environments is more challenging than automating manufacturing production lines. The growing diffusion of semi-autonomous assistive quadrupedal robots that can handle obstacles triggered the change. Nonetheless, robot control still requires active human supervision, which can be tedious in ordinary surroundings or even impossible in clinical circumstances. This paper tackles the robot control challenge and introduces the deployment of gaze-controlled semi-autonomous assistive quadrupedal robots. We focus on noninvasive gaze-tracking performed on smart glasses to guide a semi-autonomous assistive quadrupedal robot toward the user's focused remote object. Specifically, we propose (i) a …
Cited by:3
Resources:[PDF] from ethz.ch
:view less
On-Sensor TinyML Event-Based Fault Detection Strategies on Wind Turbine Blades
2024
Denis Mikhaylov, Tommaso Polonelli, Michele Magno
2024 IEEE Sensors Applications Symposium (SAS), 1-6
:read more
Authors:Denis Mikhaylov, Tommaso Polonelli, Michele Magno
Publication date:07/23/2024
Journal:2024 IEEE Sensors Applications Symposium (SAS)
Pages:1-6
Publisher:IEEE
Description:With the advent of wireless low-power Internet of Things (IoT) devices, Structural Health Monitoring (SHM), in which structures or machines are monitored using sensors, has become increasingly important to reduce costs and increase structure longevity. On-sensor machine learning represents a significant leap forward in addressing the challenge of managing the copious amounts of data these SHM systems generate. Novel sensors such as the ISM330IS Inertial Measurement Unit (IMU) from STMicroelectronics feature an onboard Intelligent Sensor Processing Unit (ISPU) enabling some of the required data processing to be computed onboard the sensor, reducing the need to run the main processor and ensuring only interesting data is collected, e.g., when a fault occurs. Using an existing state-of-the-art monitoring system as a baseline, this work investigates the power consumption, bandwidth requirements, and …
Cited by:5
Resources:[PDF] from ethz.ch
:view less
Autonomous Navigation in Dynamic Human Environments with an Embedded 2D LiDAR-based Person Tracker
2024
Davide Plozza, Steven Marty, Cyril Scherrer, Simon Schwartz, Stefan Zihlmann, Michele M…
2024 IEEE Sensors Applications Symposium (SAS), 1-6
:read more
Authors:Davide Plozza, Steven Marty, Cyril Scherrer, Simon Schwartz, Stefan Zihlmann, Michele Magno
Publication date:07/23/2024
Journal:2024 IEEE Sensors Applications Symposium (SAS)
Pages:1-6
Publisher:IEEE
Description:In the rapidly evolving landscape of autonomous mobile robots, the emphasis on seamless human-robot interactions has shifted towards autonomous decision-making. This paper delves into the intricate challenges associated with robotic auton-omy, focusing on navigation in dynamic environments shared with humans. It introduces an embedded real-time tracking pipeline, integrated into a navigation planning framework for effective person tracking and avoidance, adapting a state-of-the-art 2D LiDAR-based human detection network and an efficient multi-object tracker. By addressing the key components of detection, tracking, and planning separately, the proposed approach high-lights the modularity and transferability of each component to other applications. Our tracking approach is validated on a quadruped robot equipped with 270°2D-LiDAR against motion capture system data, with the preferred …
Cited by:3
Resources:[PDF] from arxiv.org
:view less
Tiny On-Device Structural Health Monitoring for Wind Turbines Using MEMS Pressure Sensors
2024
Elias von Däniken, Denis Mikhaylov, Amirhossein Moallemi, Tommaso Polonelli, Michele Ma…
2024 IEEE Sensors Applications Symposium (SAS), 1-6
:read more
Authors:Elias von Däniken, Denis Mikhaylov, Amirhossein Moallemi, Tommaso Polonelli, Michele Magno
Publication date:07/23/2024
Journal:2024 IEEE Sensors Applications Symposium (SAS)
Pages:1-6
Publisher:IEEE
Description:Wind turbines are extensively used as a renewable source of energy. These turbines are exposed to turbulence and highly variable weather conditions such as wind, rain, and ice, which can cause significant damage and degraded power generation performance if not detected in time. The emergence of the Industry 4.0 paradigm enables a reduction in maintenance costs and increased efficiency. Recent research has demonstrated the possibility of monitoring the aerodynamic performance of the wind turbine directly from the blades with today's state-of-the-art wireless monitoring systems. However, these need external support to process and analyze the collected data. This paper proposes an effective tiny machine learning approach to monitor the blade structural integrity directly onboard the sensor node, requiring only 3 kB of RAM and 35 kB of Flash running on a low-power ARM Cortex-M4F at 48MHz. We …
Cited by:4
Resources:[PDF] from ethz.ch
:view less
Batdeck: advancing nano-drone navigation with low-power ultrasound-based obstacle avoidance
2024
Hanna Müller, Victor Kartsch, Michele Magno, Luca Benini
2024 IEEE Sensors Applications Symposium (SAS), 1-6
:read more
Authors:Hanna Müller, Victor Kartsch, Michele Magno, Luca Benini
Publication date:07/23/2024
Journal:2024 IEEE Sensors Applications Symposium (SAS)
Pages:1-6
Publisher:IEEE
Description:Nano-drones, distinguished by their agility, minimal weight, and cost-effectiveness, are particularly well-suited for exploration in confined, cluttered and narrow spaces. Recognizing transparent, highly reflective or absorbing materials, such as glass and metallic surfaces is challenging, as classical sensors such as cameras or laser rangers often do not detect them. Inspired by bats, which can fly at high speeds in complete darkness with the help of ultrasound, this paper introduces BatDeck, a pioneering sensor-deck employing a lightweight and low-power ultrasonic sensor for nano-drone autonomous navigation. This paper first provides insights about sensor characteristics, highlighting the influence of motor noise on the ultrasound readings, then it introduces the results of extensive experimental tests for obstacle avoidance (OA) in a diverse environment. Results show that BatDeck allows exploration for a flight time …
Cited by:6
Resources:[PDF] from arxiv.org
:view less
DSORT-MCU: Detecting Small Objects in Real-Time on Microcontroller Units
2024
Liam Boyle, Julian Moosmann, Nicolas Baumann, Seonyeong Heo, Michele Magno
IEEE Sensors Journal
:read more
Authors:Liam Boyle, Julian Moosmann, Nicolas Baumann, Seonyeong Heo, Michele Magno
Publication date:07/16/2024
Journal:IEEE Sensors Journal
Publisher:IEEE
Description:Advances in lightweight neural networks have revolutionized computer vision in a broad range of Internet of Things (IoT) applications, encompassing remote monitoring and process automation. However, the detection of small objects, which is crucial for many of these applications, remains an underexplored area in current computer vision research, particularly for low-power embedded devices that host resource-constrained processors. To address the said gap, this article proposes an adaptive tiling method for lightweight and energy-efficient object detection networks, including You Only Look Once (YOLO)-based models and the popular Faster Objects More Objects (FOMO) network. The proposed tiling enables object detection on low-power microcontroller units (MCUs) with no compromise on accuracy compared to large-scale detection models. The benefit of the proposed method is demonstrated by applying it to FOMO and …
Cited by:4
:view less
i-Flow: Design and evaluation of a wearable uroflowmeter with non-invasive low power bio-impedance sensing
2024
Kanika Dheman, Manuel Glahn, Michele Magno
2024 46th Annual International Conference of the IEEE Engineering in Medicine and Biolo…
:read more
Authors:Kanika Dheman, Manuel Glahn, Michele Magno
Publication date:07/15/2024
Journal:2024 46th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC)
Pages:1-5
Publisher:IEEE
Description:Urological problems involving lower urinary tract symptoms (LUTS) such as urinary frequency, urgency, nocturia, and urine volume have a significant impact on patient health and quality of life. At present, clinical uroflowmeter tests and a urination frequency-volume chart (FVC) or bladder diary is recommended for monitoring the symptoms and the efficacy of treatment. However, these solutions are intermittent, needing high user compliance, repeated visits to the clinic and are inconvenient, especially for elderly patients. Such limitations lead to misdiagnosis and an inability to personalise treatments. This work proposes i-Flow, a low-power bio-impedance sensing system enabling wearable uroflowmetry. To demonstrate the effectiveness of the proposed solution, a preliminary dataset has been collected from 6 healthy subjects. Furthermore, the dataset acquired with a developed wearable system has been used to …
Cited by:1
:view less
Sepal: Sepsis alerts on low power wearables with digital biomarkers and on-device tiny machine learning
2024
Marco Giordano, Kanika Dheman, Michele Magno
IEEE Sensors Journal
:read more
Authors:Marco Giordano, Kanika Dheman, Michele Magno
Publication date:07/15/2024
Journal:IEEE Sensors Journal
Publisher:IEEE
Description:Sepsis is a lethal syndrome of organ dysfunction that is triggered by an infection and claims 11 million lives per year globally. Prognostic algorithms based on deep learning have shown promise in detecting the onset of sepsis hours before the actual event but use a large number of biomarkers, including vital signs and laboratory tests. The latter makes the deployment of such systems outside hospitals or in resource-limited environments extremely challenging. This article introduces SepAl, an energy-efficient and lightweight neural network, using only data from low-power wearable sensors, such as photoplethysmography (PPG), inertial measurement units (IMUs), and body temperature sensors, designed to deliver alerts in real time. SepAl leverages only six digitally acquirable vital signs and tiny machine learning (TinyML) algorithms, enabling on-device real-time sepsis prediction. SepAl uses a lightweight …
Cited by:10
Resources:[PDF] from arxiv.org
:view less
On-Device Training Empowered Transfer Learning For Human Activity Recognition
2024
Pixi Kang, Julian Moosmann, Sizhen Bian, Michele Magno
arXiv preprint arXiv:2407.03644
:read more
Authors:Pixi Kang, Julian Moosmann, Sizhen Bian, Michele Magno
Publication date:07/04/2024
Journal:arXiv preprint arXiv:2407.03644
Description:Human Activity Recognition (HAR) is an attractive topic to perceive human behavior and supplying assistive services. Besides the classical inertial unit and vision-based HAR methods, new sensing technologies, such as ultrasound and body-area electric fields, have emerged in HAR to enhance user experience and accommodate new application scenarios. As those sensors are often paired with AI for HAR, they frequently encounter challenges due to limited training data compared to the more widely IMU or vision-based HAR solutions. Additionally, user-induced concept drift (UICD) is common in such HAR scenarios. UICD is characterized by deviations in the sample distribution of new users from that of the training participants, leading to deteriorated recognition performance. This paper proposes an on-device transfer learning (ODTL) scheme tailored for energy- and resource-constrained IoT edge devices. Optimized on-device training engines are developed for two representative MCU-level edge computing platforms: STM32F756ZG and GAP9. Based on this, we evaluated the ODTL benefits in three HAR scenarios: body capacitance-based gym activity recognition, QVAR- and ultrasonic-based hand gesture recognition. We demonstrated an improvement of 3.73%, 17.38%, and 3.70% in the activity recognition accuracy, respectively. Besides this, we observed that the RISC-V-based GAP9 achieves 20x and 280x less latency and power consumption than STM32F7 MCU during the ODTL deployment, demonstrating the advantages of employing the latest low-power parallel computing devices for edge tasks.
Cited by:6
Resources:[PDF] from arxiv.org
:view less
Adaptive Image Reconstruction for Optoacoustic Tomography: A Partial FPGA Reconfiguration Approach
2024
Federico Villani, Çağla Özsoy, Christian Vogt, Andrea Cossettini, Xosé Luís Deán-Ben, M…
IEEE Sensors Letters 8 (8), 1-4
:read more
Authors:Federico Villani, Çağla Özsoy, Christian Vogt, Andrea Cossettini, Xosé Luís Deán-Ben, Michele Magno, Daniel Razansky, Luca Benini
Publication date:07/04/2024
Journal:IEEE Sensors Letters
Volume:8
Issue:8
Pages:1-4
Publisher:IEEE
Description:Widespread clinical adoption of optoacoustic tomography (OAT) depends on technological advancements in handheld probes that can offer immediate image feedback during the scanning process. Field programmable gate arrays (FPGA) can facilitate the design of lightweight, dynamically configurable handheld probes at an affordable cost and power envelope. Optimal image rendering from different areas of the body may involve adjustment of OAT image characteristics during a handheld scan, which requires the implementation of reconstruction algorithms that can be adjusted in real time. However, FPGA implementations of OAT reconstruction algorithms have been constrained by relatively low computational speed and limited flexibility for parameter adjustment. This work exploits FPGAs' partial reconfiguration (PR) capabilities to enable real-time OAT reconstruction and facilitate dynamic updates to data …
Cited by:4
:view less
Ultra-Lightweight Collaborative Mapping for Robot Swarms
2024
Vlad Niculescu, Tommaso Polonelli, Michele Magno, Luca Benini
arXiv preprint arXiv:2407.03136
:read more
Authors:Vlad Niculescu, Tommaso Polonelli, Michele Magno, Luca Benini
Publication date:07/03/2024
Journal:arXiv preprint arXiv:2407.03136
Description:A key requirement in robotics is the ability to simultaneously self-localize and map a previously unknown environment, relying primarily on onboard sensing and computation. Achieving fully onboard accurate simultaneous localization and mapping (SLAM) is feasible for high-end robotic platforms, whereas small and inexpensive robots face challenges due to constrained hardware, therefore frequently resorting to external infrastructure for sensing and computation. The challenge is further exacerbated in swarms of robots, where coordination, scalability, and latency are crucial concerns. This work introduces a decentralized and lightweight collaborative SLAM approach that enables mapping on virtually any robot, even those equipped with low-cost hardware and only 1.5 MB of memory, including miniaturized insect-size devices. Moreover, the proposed solution supports large swarm formations with the capability to coordinate hundreds of agents. To substantiate our claims, we have successfully implemented collaborative SLAM on centimeter-size drones weighing 46 g. Remarkably, we achieve a mapping accuracy below 30 cm, a result comparable to high-end state-of-the-art solutions while reducing the cost, memory, and computation requirements by two orders of magnitude. Our approach is innovative in three main aspects. First, it enables onboard infrastructure-less collaborative mapping with a lightweight and cost-effective ($20) solution in terms of sensing and computation. Second, we optimize the data traffic within the swarm to support hundreds of cooperative agents using standard wireless protocols such as ultra-wideband (UWB …
Cited by:2
Resources:[PDF] from arxiv.org
:view less
Ai-based multi-wavelength ppg device for blood pressure monitoring
2024
Chiara Botrugno, Kanika Dheman, Pietro Bonazzi, Francesco Dell'Olio, Michele Magno
2024 IEEE International Symposium on Medical Measurements and Applications (MeMeA), 1-6
:read more
Authors:Chiara Botrugno, Kanika Dheman, Pietro Bonazzi, Francesco Dell'Olio, Michele Magno
Publication date:06/26/2024
Journal:2024 IEEE International Symposium on Medical Measurements and Applications (MeMeA)
Pages:1-6
Publisher:IEEE
Description:Non-invasive vital signs monitoring, particularly blood pressure, plays a pivotal role in assessing overall health and detecting early signs of medical conditions. Photoplethysmogra-phy (PPG) is a non-invasive technology that is increasingly used in vital signs monitoring, carrying the advantage of continuously and accurately measuring a cardiac signal, relying on the sensitivity to blood volume changes in blood vessels, which allows the real-time recording of each heartbeat and the assessment of the presence of any abnormalities. This study explores the efficacy of machine learning models for arterial pressure prediction using the only photoplethysmography (PPG) signal, relying on a new dataset and multi-wavelength sensor technology, which provides signals derived from four different wavelengths (infrared, red, green and blue). The recruited population is made up of 88 people, performing a measurement with a …
Cited by:6
:view less
An Ultra-Thin 4.3 mm Generator for Energy Harvesting on Operating Wind Turbine Blades
2024
Tommaso Polonelli, Gian Hug, Michele Magno
2024 International Symposium on Power Electronics, Electrical Drives, Automation and Mo…
:read more
Authors:Tommaso Polonelli, Gian Hug, Michele Magno
Publication date:06/19/2024
Journal:2024 International Symposium on Power Electronics, Electrical Drives, Automation and Motion (SPEEDAM)
Pages:389-395
Publisher:IEEE
Description:Wind energy is a crucial technology for the shift from a world driven by fossil fuels to one driven by renewable energies. Wind turbine operators thus seek reduced maintenance costs and improved efficiency. In this direction, non-intrusive wireless sensor networks have been proposed to address the continuous monitoring of wind turbines. A wireless sensor node must operate for long periods, ideally perpetually. Previous works have focused mainly on photovoltaic and motion-based energy harvesting to provide a stable and reliable energy source. This work proposes an ultra-thin 4.3 mm surface wind-induced rotation electric generator as energy harvesting technology, enabling a self-sustaining wireless sensor node for wind turbine blade monitoring. In addition to theoretical considerations, three prototypes are realized and characterized, comparing different rotor sizes and magnets with an operative wind speed dynamic …
Cited by:1
:view less
A passive and asynchronous wake-up receiver for acoustic underwater communication
2024
Lukas Schulthess, Philipp Mayer, Luca Benini, Michele Magno
2024 International Symposium on Power Electronics, Electrical Drives, Automation and Mo…
:read more
Authors:Lukas Schulthess, Philipp Mayer, Luca Benini, Michele Magno
Publication date:06/19/2024
Journal:2024 International Symposium on Power Electronics, Electrical Drives, Automation and Motion (SPEEDAM)
Pages:480-485
Publisher:IEEE
Description:Establishing reliable data exchange in an underwater domain using energy and power-efficient communication methods is crucial and challenging. Radio frequencies are absorbed by the salty and mineral-rich water and optical signals are obstructed and scattered after short distances. In contrast, acoustic communication benefits from low absorption and enables communication over long distances. Underwater communication must match low power and energy requirements as underwater sensor systems must have a long battery lifetime and need to work reliably due to their deployment and maintenance cost. For long-term deployments, the sensors' overall power consumption is determined by the power consumption during idle state. It can be reduced by integrating asynchronous always-on wake-up circuits with nano-watt power consumption. However, this approach does reduce but not eliminate idle power …
Cited by:5
Resources:[PDF] from arxiv.org
:view less
A LoRa-based energy-efficient sensing system for urban data collection
2024
Lukas Schulthess, Tiago Salzmann, Christian Vogt, Michele Magno
arXiv preprint arXiv:2406.06404
:read more
Authors:Lukas Schulthess, Tiago Salzmann, Christian Vogt, Michele Magno
Publication date:06/10/2024
Journal:arXiv preprint arXiv:2406.06404
Description:Nowadays, cities provide much more than shopping opportunities or working spaces. Individual locations such as parks and squares are used as meeting points and local recreation areas by many people. To ensure that they remain attractive in the future, the design of such squares must be regularly adapted to the needs of the public. These utilization trends can be derived using public data collection. The more diverse and rich the data sets are, the easier it is to optimize public space design through data analysis. Traditional data collection methods such as questionnaires, observations, or videos are either labor intensive or cannot guarantee to preserve the individual's privacy. This work presents a privacy-preserving, low-power, and low-cost smart sensing system that is capable of anonymously collecting data about public space utilization by analyzing the occupancy distribution of public seating. To support future urban planning the sensor nodes are capable of monitoring environmental noise, chair utilization, and their position, temperature, and humidity and provide them over a city-wide Long Range Wide Area Network (LoRaWAN). The final sensing system's robust operation is proven in a trial run at two public squares in a city with 16 sensor nodes over a duration of two months. By consuming 33.65 mWh per day with all subsystems enabled, including sitting detection based on a continuous acceleration measurement operating on a robust and simple threshold algorithm, the custom-designed sensor node achieves continuous monitoring during the 2-month trial run. The evaluation of the experimental results clearly shows how the two …
Cited by:6
Resources:[PDF] from arxiv.org
:view less
Low latency visual inertial odometry with on-sensor accelerated optical flow for resource-constrained UAVs
2024
Jonas Kühne, Michele Magno, Luca Benini
IEEE Sensors Journal 25 (5), 7838-7847
:read more
Authors:Jonas Kühne, Michele Magno, Luca Benini
Publication date:06/04/2024
Journal:IEEE Sensors Journal
Volume:25
Issue:5
Pages:7838-7847
Publisher:IEEE
Description:Visual inertial odometry (VIO) is the task of estimating the movement trajectory of an agent from an onboard camera stream fused with additional inertial measurement unit (IMU) measurements. A crucial subtask within VIO is the tracking of features, which can be achieved through optical flow (OF). As the calculation of OF is a resource-demanding task in terms of computational load and memory footprint, which needs to be executed at low latency, especially in robotic applications, OF estimation is today performed on powerful CPUs or GPUs. This restricts its use in a broad spectrum of applications where the deployment of such powerful, power-hungry processors is unfeasible due to constraints related to cost, size, and power consumption. On-sensor hardware acceleration is a promising approach to enable low latency VIO even on resource-constrained devices such as nano drones. This article assesses the speed …
Cited by:10
Resources:[PDF] from arxiv.org
:view less
SliM-LLM: Salience-driven mixed-precision quantization for large language models
2024
Wei Huang, Haotong Qin, Yangdong Liu, Yawei Li, Qinshuo Liu, Xianglong Liu, Luca Benini…
arXiv preprint arXiv:2405.14917
:read more
Authors:Wei Huang, Haotong Qin, Yangdong Liu, Yawei Li, Qinshuo Liu, Xianglong Liu, Luca Benini, Michele Magno, Shiming Zhang, Xiaojuan Qi
Publication date:05/23/2024
Journal:arXiv preprint arXiv:2405.14917
Description:Post-training quantization (PTQ) is an effective technique for compressing large language models (LLMs). However, while uniform-precision quantization is computationally efficient, it often compromises model performance. To address this, we propose SliM-LLM, a salience-driven mixed-precision quantization framework that allocates bit-widths at the group-wise. Our approach leverages the observation that important weights follow a structured distribution and introduces two key components: textbf{1)} textit{Salience-Determined Bit Allocation} adaptively assigns bit-widths to groups within each layer based on their salience; and textbf{2)} textit{Salience-Weighted Quantizer Calibration} optimizes quantizer parameters by incorporating element-level salience. With its structured partitioning, SliM-LLM provides a hardware-friendly solution that matches the efficiency of uniform quantization methods while improving accuracy. Experiments show that SliM-LLM achieves superior performance across various LLMs at low bit-widths. For example, a 2-bit quantized LLaMA-7B model reduces memory usage by nearly 6x compared to the floating-point baseline, decreases perplexity by 48% compared to state-of-the-art gradient-free PTQ methods, and maintains GPU inference speed. Additionally, the extended version, SliM-LLM, which incorporates gradient-based quantization, further reduces perplexity by 35.1%. Our code is available at https://github.com/Aaronhuang-778/SliM-LLM
Cited by:29
Resources:[PDF] from arxiv.org
:view less
Flexible and fully quantized lightweight tinyissimoyolo for ultra-low-power edge systems
2024
Julian Moosmann, Hanna Müller, Nicky Zimmerman, Georg Rutishauser, Luca Benini, Michele…
IEEE Access 12, 75093-75107
:read more
Authors:Julian Moosmann, Hanna Müller, Nicky Zimmerman, Georg Rutishauser, Luca Benini, Michele Magno
Publication date:05/23/2024
Journal:IEEE Access
Volume:12
Pages:75093-75107
Publisher:IEEE
Description:This paper deploys and explores variants of TinyissimoYOLO, a highly flexible and fully quantized ultra-lightweight object detection network designed for edge systems with a power envelope of a few milliwatts. With experimental measurements, we present a comprehensive characterization of the network’s detection performance, exploring the impact of various parameters, including input resolution, number of object classes, and hidden layer adjustments. We deploy variants of TinyissimoYOLO on state-of-the-art ultra-low-power extreme edge platforms, presenting a detailed comparison on latency, energy efficiency, and their ability to efficiently parallelize the workload. In particular, the paper presents a comparison between a RISC-V-based parallel processor (GAP9 from GreenWaves Technologies) with and without use of its on-chip hardware accelerator, an ARM Cortex-M7 core (STM32H7 from ST Microelectronics), two ARM Cortex-M4 …
Cited by:21
Resources:[PDF] from ieee.org
:view less
A-79 dBm μ-Watt Wake-Up Receiver for Energy Efficient ISM and LoRa Communication
2024
Tommaso Polonelli, Vlad Niculescu, Thomas Burger, Michele Magno
2024 IEEE International Instrumentation and Measurement Technology Conference (I2MTC), 1-6
:read more
Authors:Tommaso Polonelli, Vlad Niculescu, Thomas Burger, Michele Magno
Publication date:05/20/2024
Journal:2024 IEEE International Instrumentation and Measurement Technology Conference (I2MTC)
Pages:1-6
Publisher:IEEE
Description:The landscape of the Internet of Things (IoT) and wireless sensor technologies is rapidly advancing, especially within industrial contexts. They present substantial potential for diverse applications, enabling precise and energy-efficient data acquisition. Despite those promising features, a key obstacle impedes the widespread integration of IoT and wireless sensors, particularly in battery-operated devices. The power consumption is primarily attributed to wireless Radio Frequency (RF) transceivers, where conventional approaches often rely on duty cycling to mitigate overall power usage, albeit at the cost of heightened latency. In acknowledgment of this challenge, this paper presents a low-power, high-sensitivity, and low-latency Wake-Up Radio (WUR) for ISM bands endowed with addressing capabilities crafted for ultra-low-power IoT devices. The proposed solution achieves a sensitivity of -79 dBm with power …
Cited by:1
:view less
A 36nw ultra-wideband wake-up receiver with-86dbm sensitivity and addressing capabilities
2024
Federico Villani, Enea Masina, Thomas Burger, Michele Magno
2024 IEEE International Symposium on Circuits and Systems (ISCAS), 1-5
:read more
Authors:Federico Villani, Enea Masina, Thomas Burger, Michele Magno
Publication date:05/19/2024
Journal:2024 IEEE International Symposium on Circuits and Systems (ISCAS)
Pages:1-5
Publisher:IEEE
Description:Ultra-wideband (UWB) technology has emerged as one of the most promising localization solutions, finding extensive use in industrial settings and a growing presence in the Internet of Things (IoT) and mobile devices, including smartphones. What sets UWB apart in the realm of localization and positioning is its impressive centimeter-level accuracy, enabling the development of highly secure, anti-spoofing applications. However, the primary challenge hindering the adoption of UWB in battery-operated and battery-less devices is its relatively high power consumption, especially during idle listening. Current approaches often adopt duty cycling, aiding in power conservation at the cost of increased latency. This paper presents a wake-up radio integrated circuit with addressing capabilities specifically designed for ultra-wideband communication and ranging. This wake-up radio seamlessly functions with any standard …
Cited by:3
:view less
Fully onboard low-power localization with semantic sensor fusion on a nano-UAV using floor plans
2024
Nicky Zimmerman, Hanna Müller, Michele Magno, Luca Benini
2024 IEEE International Conference on Robotics and Automation (ICRA), 11913-11919
:read more
Authors:Nicky Zimmerman, Hanna Müller, Michele Magno, Luca Benini
Publication date:05/13/2024
Journal:2024 IEEE International Conference on Robotics and Automation (ICRA)
Pages:11913-11919
Publisher:IEEE
Description:Nano-sized unmanned aerial vehicles (UAVs) are well-fit for indoor applications and for close proximity to humans. To enable autonomy, the nano-UAV must be able to self-localize in its operating environment. This is a particularly-challenging task due to the limited sensing and compute resources on board. This work presents an online and onboard approach for localization in floor plans annotated with semantic information. Unlike sensor-based maps, floor plans are readily-available, and do not increase the cost and time of deployment. To overcome the difficulty of localizing in sparse maps, the proposed approach fuses geometric information from miniaturized time-of-flight sensors and semantic cues. The semantic information is extracted from images by deploying a state-of-the-art object detection model on a high-performance multi-core microcontroller onboard the drone, consuming only 2.5mJ per frame and …
Cited by:6
Resources:[PDF] from arxiv.org
:view less
Q-Segment: Segmenting Images In-Sensor for Vessel-Based Medical Diagnosis
2024
Pietro Bonazzi, Yawei Li, Sizhen Bian, Michele Magno
2024 IEEE 6th International Conference on AI Circuits and Systems (AICAS), 517-521
:read more
Authors:Pietro Bonazzi, Yawei Li, Sizhen Bian, Michele Magno
Publication date:04/22/2024
Journal:2024 IEEE 6th International Conference on AI Circuits and Systems (AICAS)
Pages:517-521
Publisher:IEEE
Description:This paper addresses the growing interest in deploying deep learning models directly in-sensor. We present "Q-Segment", a quantized real-time segmentation algorithm, and conduct a comprehensive evaluation on a low-power edge vision platform with an in-sensors processor, the Sony IMX500. One of the main goals of the model is to achieve end-to-end image segmentation for vessel-based medical diagnosis. Deployed on the IMX500 platform, Q-Segment achieves ultra-low inference time in-sensor only 0.23 ms and power consumption of only 72mW. We compare the proposed network with state-of-the-art models, both float and quantized, demonstrating that the proposed solution outperforms existing networks on various platforms in computing efficiency, e.g., by a factor of 75x compared to ERFNet. The network employs an encoder-decoder structure with skip connections, and results in a binary accuracy of 97 …
Cited by:1
Resources:[PDF] from arxiv.org
:view less
Binarydm: Accurate weight binarization for efficient diffusion models
2024
Xingyu Zheng, Xianglong Liu, Haotong Qin, Xudong Ma, Mingyuan Zhang, Haojie Hao, Jiakai…
arXiv preprint arXiv:2404.05662
:read more
Authors:Xingyu Zheng, Xianglong Liu, Haotong Qin, Xudong Ma, Mingyuan Zhang, Haojie Hao, Jiakai Wang, Zixiang Zhao, Jinyang Guo, Michele Magno
Publication date:04/08/2024
Journal:arXiv preprint arXiv:2404.05662
Description:With the advancement of diffusion models (DMs) and the substantially increased computational requirements, quantization emerges as a practical solution to obtain compact and efficient low-bit DMs. However, the highly discrete representation leads to severe accuracy degradation, hindering the quantization of diffusion models to ultra-low bit-widths. This paper proposes a novel weight binarization approach for DMs, namely BinaryDM, pushing binarized DMs to be accurate and efficient by improving the representation and optimization. From the representation perspective, we present an Evolvable-Basis Binarizer (EBB) to enable a smooth evolution of DMs from full-precision to accurately binarized. EBB enhances information representation in the initial stage through the flexible combination of multiple binary bases and applies regularization to evolve into efficient single-basis binarization. The evolution only occurs in the head and tail of the DM architecture to retain the stability of training. From the optimization perspective, a Low-rank Representation Mimicking (LRM) is applied to assist the optimization of binarized DMs. The LRM mimics the representations of full-precision DMs in low-rank space, alleviating the direction ambiguity of the optimization process caused by fine-grained alignment. Comprehensive experiments demonstrate that BinaryDM achieves significant accuracy and efficiency gains compared to SOTA quantization methods of DMs under ultra-low bit-widths. With 1-bit weight and 4-bit activation (W1A4), BinaryDM achieves as low as 7.74 FID and saves the performance from collapse (baseline FID 10.87). As the first binarization …
Cited by:5
Resources:[PDF] from arxiv.org
:view less
Work In Progress: Linear Transformers for TinyML
2024
Moritz Scherer, Cristian Cioflan, Michele Magno, Luca Benini
2024 Design, Automation & Test in Europe Conference & Exhibition (DATE), 1-2
:read more
Authors:Moritz Scherer, Cristian Cioflan, Michele Magno, Luca Benini
Publication date:03/25/2024
Journal:2024 Design, Automation & Test in Europe Conference & Exhibition (DATE)
Pages:1-2
Publisher:IEEE
Description:We present the WaveFormer, a neural network architecture based on a linear attention transformer to enable long sequence inference for TinyML devices. Waveformer achieves a new state-of-the-art accuracy of 98.8 % and 99.1 % on the Google Speech V2 keyword spotting (KWS) dataset for the 12 and 35 class problems with only 130 kB of weight storage, compatible with MCU class devices. Top-1 accuracy is improved by 0.1 and 0.9 percentage points while reducing the model size and number of operations by 2.5× and 4.7× compared to the state of the art. We also propose a hardware-friendly 8-bit integer quantization algorithm for the linear attention operator, enabling efficient deployment on low-cost, ultra-low-power microcontrollers without loss of accuracy.
Cited by:5
Resources:[PDF] from date-conference.com
:view less
Frequency matters: Comparative analysis of low-power FMCW radars for vital sign monitoring
2024
Steven Marty, Andrea Ronco, Federico Pantanella, Kanika Dheman, Michele Magno
IEEE Transactions on Instrumentation and Measurement 73, 1-10
:read more
Authors:Steven Marty, Andrea Ronco, Federico Pantanella, Kanika Dheman, Michele Magno
Publication date:03/25/2024
Journal:IEEE Transactions on Instrumentation and Measurement
Volume:73
Pages:1-10
Publisher:IEEE
Description:Vital sign monitoring is a critical step in health assessment in clinical settings. A rising interest in contactless options is pushing for innovative solutions for heart rate (HR) and respiration rate (RR) estimation. Low-power millimeter-wave radars are emerging as a solution because of their invariance to lightning conditions, subject phenotype, and privacy guarantees. On the side, the robustness of radar-based systems is still a concern due to incomplete characterization of the systems, evaluation of different frequencies, and limited evaluation on human subjects. Moreover, low-power options have not been rigorously explored, despite their potential in ubiquitous deployment. This article evaluates three low-power frequency-modulated continuous wave (FMCW) radars with the frequencies of 24, 60, and 120 GHz, investigating their performance and the influence of the carrier frequency in vital sign estimation. An initial …
Cited by:15
Resources:[PDF] from ethz.ch
:view less
Robustness evaluation of localization techniques for autonomous racing
2024
Tian Yi Lim, Edoardo Ghignone, Nicolas Baumann, Michele Magno
2024 Design, Automation & Test in Europe Conference & Exhibition (DATE), 1-2
:read more
Authors:Tian Yi Lim, Edoardo Ghignone, Nicolas Baumann, Michele Magno
Publication date:03/25/2024
Journal:2024 Design, Automation & Test in Europe Conference & Exhibition (DATE)
Pages:1-2
Publisher:IEEE
Description:This work introduces SynPF, an MCL-based algorithm tailored for high-speed racing environments. Benchmarked against Cartographer, a state-of-the-art pose-graph SLAM algorithm, SynPF leverages synergies from previous particle-filtering methods and synthesizes them for the high-performance racing do-main. Our extensive in-field evaluations reveal that while Cartogra-pher excels under nominal conditions, it struggles when subjected to wheel-slip-a common phenomenon in a racing scenario due to varying grip levels and aggressive driving behaviour. Conversely, SynPF demonstrates robustness in these challenging conditions and a low-latency computation time of 1.25 ms on on-board computers without a GPU. Using the FITENTH platform, a 1:10 scaled autonomous racing vehicle, this work not only highlights the vulnerabilities of existing algorithms in high-speed scenarios, tested up until , but also …
Cited by:2
Resources:[PDF] from arxiv.org
:view less
Towards real-time fast unmanned aerial vehicle detection using dynamic vision sensors
2024
Jakub Mandula, Jonas Kühne, Luca Pascarella, Michele Magno
arXiv preprint arXiv:2403.11875
:read more
Authors:Jakub Mandula, Jonas Kühne, Luca Pascarella, Michele Magno
Publication date:03/18/2024
Journal:arXiv preprint arXiv:2403.11875
Description:Unmanned Aerial Vehicles (UAVs) are gaining popularity in civil and military applications. However, uncontrolled access to restricted areas threatens privacy and security. Thus, prevention and detection of UAVs are pivotal to guarantee confidentiality and safety. Although active scanning, mainly based on radars, is one of the most accurate technologies, it can be expensive and less versatile than passive inspections, e.g., object recognition. Dynamic vision sensors (DVS) are bio-inspired event-based vision models that leverage timestamped pixel-level brightness changes in fast-moving scenes that adapt well to low-latency object detection. This paper presents F-UAV-D (Fast Unmanned Aerial Vehicle Detector), an embedded system that enables fast-moving drone detection. In particular, we propose a setup to exploit DVS as an alternative to RGB cameras in a real-time and low-power configuration. Our approach leverages the high-dynamic range (HDR) and background suppression of DVS and, when trained with various fast-moving drones, outperforms RGB input in suboptimal ambient conditions such as low illumination and fast-moving scenes. Our results show that F-UAV-D can (i) detect drones by using less than <15 W on average and (ii) perform real-time inference (i.e., <50 ms) by leveraging the CPU and GPU nodes of our edge computer.
Cited by:8
Resources:[PDF] from arxiv.org
:view less
Body-area capacitive or electric field sensing for human activity recognition and human-computer interaction: A comprehensive survey
2024
Sizhen Bian, Mengxi Liu, Bo Zhou, Paul Lukowicz, Michele Magno
Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies 8 (…
:read more
Authors:Sizhen Bian, Mengxi Liu, Bo Zhou, Paul Lukowicz, Michele Magno
Publication date:03/06/2024
Journal:Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies
Volume:8
Issue:1
Pages:1-49
Publisher:ACM
Description:Due to the fact that roughly sixty percent of the human body is essentially composed of water, the human body is inherently a conductive object, being able to, firstly, form an inherent electric field from the body to the surroundings and secondly, deform the distribution of an existing electric field near the body. Body-area capacitive sensing, also called body-area electric field sensing, is becoming a promising alternative for wearable devices to accomplish certain tasks in human activity recognition (HAR) and human-computer interaction (HCI). Over the last decade, researchers have explored plentiful novel sensing systems backed by the body-area electric field, like the ring-form smart devices for sign language recognition, the room-size capacitive grid for indoor positioning, etc. On the other hand, despite the pervasive exploration of the body-area electric field, a comprehensive survey does not exist for an …
Cited by:26
Resources:[PDF] from arxiv.org
:view less
CycloWatt: An affordable, TinyML-enhanced IoT device revolutionizing cycling power metrics
2024
Victor Luder, Sizhen Bian, Michele Magno
arXiv preprint arXiv:2403.07915
:read more
Authors:Victor Luder, Sizhen Bian, Michele Magno
Publication date:02/27/2024
Journal:arXiv preprint arXiv:2403.07915
Description:Cycling power measurement is an indispensable metric with profound implications for cyclists' performance and fitness levels. It empowers riders with real-time feedback, supports precise training regimen planning, mitigates injury risks, and enhances muscular development. Despite these advantages, the widespread adoption of cycling power meters has been hampered by their prohibitive cost and deployment complexity. This paper pioneers a groundbreaking approach to power measurement in cycling, prioritizing affordability and user-friendliness. To achieve this goal, we introduce a cutting-edge Internet of Things (IoT) device that seamlessly integrates force signals with inertial sensor data while leveraging the power of edge machine learning techniques. In-field experimental evaluations demonstrate that our prototype can estimate power with remarkable accuracy, boasting a Mean Absolute Error (MAE) of only 12.29 Watts (4.1%). Notably, our design emphasizes energy efficiency, operating in a low-power mode that consumes a mere 50 milliwatts and offers an exceptional battery life of up to 25.8 hours in always-on active mode. With an ultra-low latency of 4.33 milliseconds for data processing and inference, our system ensures real-time power estimation during cycling activities. Incorporating IoT concepts and devices, this paper marks a significant milestone in developing cost-effective and accurate cycling power meters.
Cited by:5
Resources:[PDF] from arxiv.org
:view less
Fully onboard slam for distributed mapping with a swarm of nano-drones
2024
Carl Friess, Vlad Niculescu, Tommaso Polonelli, Michele Magno, Luca Benini
IEEE Internet of Things Journal 11 (20), 32363-32380
:read more
Authors:Carl Friess, Vlad Niculescu, Tommaso Polonelli, Michele Magno, Luca Benini
Publication date:02/19/2024
Journal:IEEE Internet of Things Journal
Volume:11
Issue:20
Pages:32363-32380
Publisher:IEEE
Description:The use of unmanned aerial vehicles (UAVs) is rapidly increasing in applications ranging from surveillance and first-aid missions to industrial automation involving cooperation with other machines or humans. To maximize area coverage and reduce mission latency, swarms of collaborating drones have become a significant research direction. However, this approach requires open challenges in positioning, mapping, and communications to be addressed. This work describes a distributed mapping system based on a swarm of nano-UAVs, characterized by a limited payload of 35 g and tightly constrained onboard sensing and computing capabilities. Each nano-UAV is equipped with four 64-pixel depth sensors that measure the relative distance to obstacles in four directions. The proposed system merges the information from the swarm and generates a coherent grid map without relying on any external infrastructure …
Cited by:17
Resources:[PDF] from arxiv.org
:view less
Accurate lora-finetuning quantization of llms via information retention
2024
Haotong Qin, Xudong Ma, Xingyu Zheng, Xiaoyang Li, Yang Zhang, Shouda Liu, Jie Luo, Xia…
arXiv preprint arXiv:2402.05445
:read more
Authors:Haotong Qin, Xudong Ma, Xingyu Zheng, Xiaoyang Li, Yang Zhang, Shouda Liu, Jie Luo, Xianglong Liu, Michele Magno
Publication date:02/08/2024
Journal:arXiv preprint arXiv:2402.05445
Description:The LoRA-finetuning quantization of LLMs has been extensively studied to obtain accurate yet compact LLMs for deployment on resource-constrained hardware. However, existing methods cause the quantized LLM to severely degrade and even fail to benefit from the finetuning of LoRA. This paper proposes a novel IR-QLoRA for pushing quantized LLMs with LoRA to be highly accurate through information retention. The proposed IR-QLoRA mainly relies on two technologies derived from the perspective of unified information: (1) statistics-based Information Calibration Quantization allows the quantized parameters of LLM to retain original information accurately; (2) finetuning-based Information Elastic Connection makes LoRA utilizes elastic representation transformation with diverse information. Comprehensive experiments show that IR-QLoRA can significantly improve accuracy across LLaMA and LLaMA2 families under 2-4 bit-widths, e.g., 4- bit LLaMA-7B achieves 1.4% improvement on MMLU compared with the state-of-the-art methods. The significant performance gain requires only a tiny 0.31% additional time consumption, revealing the satisfactory efficiency of our IR-QLoRA. We highlight that IR-QLoRA enjoys excellent versatility, compatible with various frameworks (e.g., NormalFloat and Integer quantization) and brings general accuracy gains. The code is available at https://github.com/htqin/ir-qlora.
Cited by:130
Resources:[PDF] from arxiv.org
:view less
Billm: Pushing the limit of post-training quantization for llms
2024
Wei Huang, Yangdong Liu, Haotong Qin, Ying Li, Shiming Zhang, Xianglong Liu, Michele Ma…
arXiv preprint arXiv:2402.04291
:read more
Authors:Wei Huang, Yangdong Liu, Haotong Qin, Ying Li, Shiming Zhang, Xianglong Liu, Michele Magno, Xiaojuan Qi
Publication date:02/06/2024
Journal:arXiv preprint arXiv:2402.04291
Description:Pretrained large language models (LLMs) exhibit exceptional general language processing capabilities but come with significant demands on memory and computational resources. As a powerful compression technology, binarization can extremely reduce model weights to a mere 1 bit, lowering the expensive computation and memory requirements. However, existing quantization techniques fall short of maintaining LLM performance under ultra-low bit-widths. In response to this challenge, we present BiLLM, a groundbreaking 1-bit post-training quantization scheme tailored for pretrained LLMs. Based on the weight distribution of LLMs, BiLLM first identifies and structurally selects salient weights, and minimizes the compression loss through an effective binary residual approximation strategy. Moreover, considering the bell-shaped distribution of the non-salient weights, we propose an optimal splitting search to group and binarize them accurately. BiLLM achieving for the first time high-accuracy inference (e.g. 8.41 perplexity on LLaMA2-70B) with only 1.08-bit weights across various LLMs families and evaluation metrics, outperforms SOTA quantization methods of LLM by significant margins. Moreover, BiLLM enables the binarization process of the LLM with 7 billion weights within 0.5 hours on a single GPU, demonstrating satisfactory time efficiency. Our code is available at https://github.com/Aaronhuang-778/BiLLM.
Cited by:160
Resources:[PDF] from arxiv.org
:view less
A leap into the future: Towards an augmented reality learning environment in ski-jumping
2024
Lukas Schulthess, Thorir Ingolfsson, Serin Huber, Marc Nölke, Michele Magno, Luca Benin…
Current Issues in Sport Science (CISS) 9 (2), 069-069
:read more
Authors:Lukas Schulthess, Thorir Ingolfsson, Serin Huber, Marc Nölke, Michele Magno, Luca Benini, Christoph Leitner
Publication date:02/06/2024
Journal:Current Issues in Sport Science (CISS)
Volume:9
Issue:2
Pages:069-069
Description:Introduction Professional sports are fiercely competitive. In ski jumping, for example, even small changes in take-off and flight can make a decisive difference between victory and defeat (Elfmark et al., 2022). Within the short time of a jump, athletes must learn to solve complex motor control problems while being exposed to harsh environmental conditions, e.g., wind, snow, and low temperatures. The actual take-off occurs within the blink of an eye (~300 ms) and an aerodynamically favourable and stable flight position should be attained immediately. Fine control of the centre of gravity in the in-run favours high speeds to generate optimum momentum during take-off (Müller, 2008). In flight, athletes can voluntarily influence aerodynamics by changing their body position. However, non-optimal flight positions occur unintentionally or due to incorrect behaviour. Furthermore, as a non-cyclical sport, ski jumping suffers from …
:view less
Stargate: Multimodal sensor fusion for autonomous navigation on miniaturized uavs
2024
Konstantin Kalenberg, Hanna Müller, Tommaso Polonelli, Alberto Schiaffino, Vlad Nicules…
IEEE Internet of Things Journal 11 (12), 21372-21390
:read more
Authors:Konstantin Kalenberg, Hanna Müller, Tommaso Polonelli, Alberto Schiaffino, Vlad Niculescu, Cristian Cioflan, Michele Magno, Luca Benini
Publication date:02/06/2024
Journal:IEEE Internet of Things Journal
Volume:11
Issue:12
Pages:21372-21390
Publisher:IEEE
Description:Autonomously navigating robots need to perceive and interpret their surroundings. Currently, cameras are among the most used sensors due to their high resolution and frame rates at relatively low-energy consumption and cost. In recent years, cutting-edge sensors, such as miniaturized depth cameras, have demonstrated strong potential, specifically for nano-size unmanned aerial vehicles (UAVs), where low-power consumption, lightweight hardware, and low-computational demand are essential. However, cameras are limited to working under good lighting conditions, while depth cameras have a limited range. To maximize robustness, we propose to fuse a millimeter form factor 64 pixel depth sensor and a low-resolution grayscale camera. In this work, a nano-UAV learns to detect and fly through a gate with a lightweight autonomous navigation system based on two tinyML convolutional neural network models …
Cited by:20
Resources:[PDF] from google.com
:view less
Mi-bminet: An efficient convolutional neural network for motor imagery brain–machine interfaces with eeg channel selection
2024
Xiaying Wang, Michael Hersche, Michele Magno, Luca Benini
IEEE Sensors Journal 24 (6), 8835-8847
:read more
Authors:Xiaying Wang, Michael Hersche, Michele Magno, Luca Benini
Publication date:01/18/2024
Journal:IEEE Sensors Journal
Volume:24
Issue:6
Pages:8835-8847
Publisher:IEEE
Description:A brain–machine interface (BMI) based on motor imagery (MI) enables the control of devices using brain signals while the subject imagines performing a movement. It plays a key role in prosthesis control and motor rehabilitation. To improve user comfort, preserve data privacy, and reduce the system’s latency, a new trend in wearable BMIs is to execute algorithms on low-power microcontroller units (MCUs) embedded on edge devices to process the electroencephalographic (EEG) data in real-time close to the sensors. However, most of the classification models presented in the literature are too resource-demanding for low-power MCUs. This article proposes an efficient convolutional neural network (CNN) for EEG-based MI classification that achieves comparable accuracy while being orders of magnitude less resource-demanding and significantly more energy-efficient than state-of-the-art (SoA) models. To further reduce …
Cited by:57
Resources:[PDF] from arxiv.org
:view less
Towards a non-Invasive Monitoring System for Wind Turbine Blades
2024
Nicolas Schärer, Tommaso Polonelli, Julien Deparday, Michele Magno
2024 IEEE International Instrumentation and Measurement Technology Conference (I2MTC)
:read more
Authors:Nicolas Schärer, Tommaso Polonelli, Julien Deparday, Michele Magno
Publication date:01/01/2024
Journal:2024 IEEE International Instrumentation and Measurement Technology Conference (I2MTC)
Publisher:IEEE
Description:Wind power generation plays a crucial role in transitioning away from fossil fuel-dependent energy sources, contributing significantly to the mitigation of climate change. Therefore, it is advantageous to enhance the adoption of wind energy while improving turbine conversion efficiency. Monitoring wind flow and operational parameters of wind turbines is a fundamental prerequisite for optimizing broad coverage and electrical conversion efficiency. The aerodynamics of the rotating blades are of particular interest but are very challenging to mea-sure due to the complexity of measurement system installations on operating wind turbines. This paper presents a flexible and modular system that enables real-time monitoring on the surface of wind turbine blades. Experimental results demonstrate the capability of extracting key aerodynamic parameters, such as Angle of Attack (AoA) and flow detachment, using an array of commercial low-power sensors, i.e., 10 absolute pressure sensors, 5 differential pressure sensors, and a MEMS vibrometer with a precision of 1°and a maximum power consumption below 50mW.
Cited by:5
Resources:[PDF] from ethz.ch
:view less
Tinyssimoradar: In-ear hand gesture recognition with ultra-low power mmwave radars
2024
Andrea Ronco, Philipp Schilk, Michele Magno
IoTDI 2024: Proceedings of the 9th ACM/IEEE Conference on Internet of Things Design and…
:read more
Authors:Andrea Ronco, Philipp Schilk, Michele Magno
Publication date:01/01/2024
Journal:IoTDI 2024: Proceedings of the 9th ACM/IEEE Conference on Internet of Things Design and Implementation
Pages:192-202
Publisher:IEEE
Description:Smart Internet of Things (IoT) devices are on the rise in popularity, with innovative use cases and applications emerging every year. Including intelligence in these novel systems presents the challenge of integrating interaction and communica tion in scenarios where traditional interfaces are not viable. Hand Gesture Recognition (HGR) has been proposed as an intuitive Human-Machine Interface, potentially suitable for controlling several classes of devices in the context of the Internet of Things. This paper proposes a low-power in-ear HGR system based on mm-wave radars, efficient spatial and temporal Convolutional Neural Networks and an energy-optimized hardware design. The design is suitable for battery-operated devices, with stringent size and energy constraints, enabling user interaction with wearable devices, but also suitable for home appliances and industrial applications. The proposed machine learning model is characterized thoroughly for robustness and generalization capabilities, achieving 94.9% (single subject) and 86.1% (Leave One-Out Cross-validation) accuracy on a set of 11+1 gestures with a model size of only 36 KiB and inference latency of 32.4 ms on a 64 MHz Cortex-M33 microcontroller, making it compatible with real-time applications. The system is demonstrated in a fully integrated, miniaturized in-ear device with a full-system average power consumption of 18.4 mW, a more than 6x improvement on the current state of the art.
Cited by:6
Resources:[PDF] from ethz.ch
:view less
How good are low-bit quantized llama3 models? an empirical study
2024
Wei Huang, Xudong Ma, Haotong Qin, Xingyu Zheng, Chengtao Lv, Hong Chen, Jie Luo, Xiaoj…
CoRR
:read more
Authors:Wei Huang, Xudong Ma, Haotong Qin, Xingyu Zheng, Chengtao Lv, Hong Chen, Jie Luo, Xiaojuan Qi, Xianglong Liu, Michele Magno
Publication date:01/01/2024
Journal:CoRR
Description:Meta's LLaMA family has become one of the most powerful open-source Large Language Model (LLM) series. Notably, LLaMA3 models have recently been released and achieve impressive performance across various with super-large scale pre-training on over 15T tokens of data. Given the wide application of low-bit quantization for LLMs in resource-limited scenarios, we explore LLaMA3's capabilities when quantized to low bit-width. This exploration holds the potential to unveil new insights and challenges for low-bit quantization of LLaMA3 and other forthcoming LLMs, especially in addressing performance degradation problems that suffer in LLM compression. Specifically, we evaluate the 10 existing post-training quantization and LoRA-finetuning methods of LLaMA3 on 1-8 bits and diverse datasets to comprehensively reveal LLaMA3's low-bit quantization performance. Our experiment results indicate that …
Cited by:68
:view less
Retina: Low-power eye tracking with event camera and spiking hardware
2024
Pietro Bonazzi, Sizhen Bian, Giovanni Lippolis, Yawei Li, Sadique Sheik, Michele Magno
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 5684…
:read more
Authors:Pietro Bonazzi, Sizhen Bian, Giovanni Lippolis, Yawei Li, Sadique Sheik, Michele Magno
Publication date:01/01/2024
Journal:Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition
Pages:5684-5692
Description:This paper introduces a neuromorphic dataset and methodology for eye tracking harnessing event data cap-tured streamed continuously by a Dynamic Vision Sensor (DVS). The framework integrates a directly trained Spiking Neuron Network (SNN) regression model and leverages a state-of-the-art low power edge neuromorphic processor-Speck. First it introduces a representative event-based eye-tracking dataset" Ini-30" which was collected with two glass-mounted DVS cameras from thirty volunteers. Then a SNN model based on Integrate And Fire (IAF) neurons named" Retina" is described featuring only 64k param-eters (6.63 x fewer than 3ET) and achieving pupil tracking error of only 3.24 pixels in a 64x64 DVS input. The con-tinuous regression output is obtained by means of tempo-ral convolution using a non-spiking 1D filter slided across the output spiking layer over time. Retina is evaluated on the neuromorphic processor showing an end-to-end power between 2.89-4.8 mW and a latency of 5.57-8.01 ms de-pendent on the time to slice the event-based video record-ing. The model is more precise than the latest event-based eye-tracking method" 3ET" on Ini-30 and shows compa-rable performance with significant model compression (35 times fewer MAC operations) in the synthetic dataset used in" 3ET". We hope this work will open avenues for further investigation of close-loop neuromorphic solutions and true event-based training pursuing edge performance.
Cited by:40
Resources:[PDF] from thecvf.com
:view less
Removing scattered light in biomedical images via an unsupervised deep neural network
2023
Yuanhao Gong, Meng Xu, Yawei Li, Michele Magno
2023 IEEE EMBS Special Topic Conference on Data Science and Engineering in Healthcare, …
:read more
Authors:Yuanhao Gong, Meng Xu, Yawei Li, Michele Magno
Publication date:12/07/2023
Journal:2023 IEEE EMBS Special Topic Conference on Data Science and Engineering in Healthcare, Medicine and Biology
Pages:65-66
Publisher:IEEE
Description:Scattered light is unavoidable during biomedical imaging, leading to downgraded images. Removing such scattered light, however, is challenging, because the imaging objects are complex and the light path is complicated. In this paper, we propose to use deep learning methods to computationally remove such scattered light. Inspired by the dehazing methods for natural images, we first developed a novel mathematical model for biomedical images. Then, we developed a deep neural network method to solve this model. Our network simultaneously estimates the clear image and the scattered light. Several experiments are conducted to confirm the network’s effectiveness and efficiency.
Cited by:4
:view less
Nanoslam: Enabling fully onboard slam for tiny robots
2023
Vlad Niculescu, Tommaso Polonelli, Michele Magno, Luca Benini
IEEE Internet of Things Journal 11 (8), 13584-13607
:read more
Authors:Vlad Niculescu, Tommaso Polonelli, Michele Magno, Luca Benini
Publication date:12/05/2023
Journal:IEEE Internet of Things Journal
Volume:11
Issue:8
Pages:13584-13607
Publisher:IEEE
Description:Perceiving and mapping the surroundings are essential for autonomous navigation in any robotic platform. The algorithm class that enables accurate mapping while correcting the odometry errors present in most robotics systems is simultaneous localization and mapping (SLAM). Today, fully onboard mapping is only achievable on robotic platforms that can host high-wattage processors, mainly due to the significant computational load and memory demands required for executing SLAM algorithms. For this reason, pocket-size hardware-constrained robots offload the execution of SLAM to external infrastructures. To address the challenge of enabling SLAM algorithms on resource-constrained processors, this article proposes NanoSLAM, a lightweight and optimized end-to-end SLAM approach specifically designed to operate on centimeter-size robots at a power budget of only 87.9 mW. We demonstrate the mapping …
Cited by:29
Resources:[PDF] from arxiv.org
:view less
A muscle pennation angle estimation framework from raw ultrasound data for wearable biomedical instrumentation
2023
Sergei Vostrikov, Thorir Mar Ingolfsson, Soley Hafthorsdottir, Christoph Leitner, Miche…
IEEE Transactions on Instrumentation and Measurement 73, 1-12
:read more
Authors:Sergei Vostrikov, Thorir Mar Ingolfsson, Soley Hafthorsdottir, Christoph Leitner, Michele Magno, Luca Benini, Andrea Cossettini
Publication date:11/28/2023
Journal:IEEE Transactions on Instrumentation and Measurement
Volume:73
Pages:1-12
Publisher:IEEE
Description:Measurement of muscle activity via wearable instrumentation is of great interest for medical and sport science applications: examples include the control of prostheses, robotics, or therapy and training. This article focuses on the measurement of pennation angles in lateral gastrocnemius (LG) muscles directly from raw ultrasound (US) data. We rely on a reduced number of channels (32) to demonstrate accurate and real-time-compatible predictions of pennation angles for low-power wearable US devices. B-mode images are reconstructed by means of a delay-and-sum beamformer, and an automated computer vision tool (AEPUS) is employed to perform annotations. The labels are then used as ground truth for training an XGBoost regressor based on statistical features extracted from raw US data. Feature importance analyses and deployment-oriented XGBoost model design allow reducing the memory footprint down to …
Cited by:6
:view less
From heat to power: Assessing thermoelectric energy harvesting for self-sustainable sensors
2023
Chiara Lenz, Sergei Vostrikov, Philipp Mayer, Michele Magno
2023 IEEE International Workshop on Technologies for Defense and Security (TechDefense)…
:read more
Authors:Chiara Lenz, Sergei Vostrikov, Philipp Mayer, Michele Magno
Publication date:11/20/2023
Journal:2023 IEEE International Workshop on Technologies for Defense and Security (TechDefense)
Pages:384-389
Publisher:IEEE
Description:Autonomy and self-sustainability are essential for the next generation of Internet of Things (IoT) and sensing devices. Harnessing electrical energy from temperature gradients, thermoelectric generators (TEGs) have great potential to power these devices for extended time periods. Analyzing the performance of transducers and converters is crucial for designing compact, low-power systems. This work highlights the importance of a comprehensive experimental evaluation of advanced low-voltage, high-efficiency conversion architectures in conjunction with TEGs. Characterization of multiple transducers and converters demonstrates the potential and limitations of thermoelectric energy harvesting (EH), showcasing the possibility of supplying a power of 0.65 W/cm2 harvested from a temperature gradient of only 1K and 150 W/cm2 for 10K. Conversion efficiencies of 75% are achievable despite high voltage …
Cited by:5
Resources:[PDF] from ethz.ch
:view less
A lora-based and maintenance-free cattle monitoring system for alpine pastures and remote locations
2023
Lukas Schulthess, Fabrice Longchamp, Christian Vogt, Michele Magno
Proceedings of the 11th International Workshop on Energy Harvesting & Energy-Neutral Se…
:read more
Authors:Lukas Schulthess, Fabrice Longchamp, Christian Vogt, Michele Magno
Publication date:11/12/2023
Journal:Proceedings of the 11th International Workshop on Energy Harvesting & Energy-Neutral Sensing Systems
Pages:44-50
Description:The advent of the Internet of Things (IoT) is boosting the proliferation of sensors and smart devices in industry and daily life. Continuous monitoring IoT systems are also finding application in agriculture, particularly in the realm of smart farming. The adoption of wearable sensors to record the activity of livestock has garnered increasing interest. Such a device enables farmers to locate, monitor, and constantly assess the health status of their cattle more efficiently and effectively, even in challenging terrain and remote locations. This work presents a maintenance-free and robust smart sensing system that is capable of tracking cattle in remote locations and collecting activity parameters, such as the individual's grazing- and resting time. To support the paradigm of smart farming, the cattle tracker is capable of monitoring the cow's activity by analyzing data from an accelerometer, magnetometer, temperature sensor, and …
Cited by:18
Resources:[PDF] from arxiv.org
:view less
Energy-aware adaptive sampling for self-sustainability in resource-constrained iot devices
2023
Marco Giordano, Silvano Cortesi, Prodromos-Vasileios Mekikis, Michele Crabolu, Giovanni…
Proceedings of the 11th International Workshop on Energy Harvesting & Energy-Neutral Se…
:read more
Authors:Marco Giordano, Silvano Cortesi, Prodromos-Vasileios Mekikis, Michele Crabolu, Giovanni Bellusci, Michele Magno
Publication date:11/12/2023
Journal:Proceedings of the 11th International Workshop on Energy Harvesting & Energy-Neutral Sensing Systems
Pages:65-71
Description:In the ever-growing Internet of Things (IoT) landscape, smart power management algorithms combined with energy harvesting solutions are crucial to obtain self-sustainability. This paper presents an energy-aware adaptive sampling rate algorithm designed for embedded deployment in resource-constrained, battery-powered IoT devices. The algorithm, based on a finite state machine (FSM) and inspired by Transmission Control Protocol (TCP) Reno's additive increase and multiplicative decrease, maximizes sensor sampling rates, ensuring power self-sustainability without risking battery depletion. Moreover, we characterized our solar cell with data acquired over 48 days and used the model created to obtain energy data from an open-source world-wide dataset. To validate our approach, we introduce the EcoTrack device, a versatile device with global navigation satellite system (GNSS) capabilities and Long-Term …
Cited by:14
Resources:[PDF] from arxiv.org
:view less
Towards Enhanced Bladder Volume Measurement with Context-Aware Bio-Impedance Sensor Fusion
2023
Kanika Dheman, Manuel Glahn, Michele Magno
2023 IEEE SENSORS, 1-4
:read more
Authors:Kanika Dheman, Manuel Glahn, Michele Magno
Publication date:10/29/2023
Journal:2023 IEEE SENSORS
Pages:1-4
Publisher:IEEE
Description:Urine volume is a vital parameter of health and its continuous monitoring is necessary for managing illness in various patient populations. State-of-the-art methods include invasive catheters or sporadic measures with ultrasound. Non-invasive urine volume measurement in vivo is challenging due to the confounding effects of muscle activity. This work proposes a multi-sensor wearable system based on non-invasive tetrapolar bio-impedance (BI) measurements along with the measurement of muscle activity by including electromyography (EMG) and novel low power charge variation (QVAR) sensing integrated into inertial measurements unit, placed on the lower abdomen. A comparison of the EMG and QVAR is conducted and revealed that the QVAR sensor had a correlation coefficient of 0.93 with the EMG and consumed a sixteenth of the power of the EMG, making it more suitable for long-term, multisensor and …
Cited by:4
:view less
Ultra-Wideband Technology: Unlocking the Potential of Low Power IoT with Precise Localization and Energy-Efficient Wake-Up Radio
2023
Michele Magno
2023 IEEE SENSORS, 1-1
:read more
Authors:Michele Magno
Publication date:10/29/2023
Journal:2023 IEEE SENSORS
Pages:1-1
Publisher:IEEE
Description:This work embarks on a journey through the world of Ultra-Wideband (UWB) technology, exploring its diverse applications and advancements that are reshaping the IoT landscape. Discovering how UWB's unique characteristics make it one of the most promising technologies for IoT applications, providing centimeter-accuracy for localization and positioning. We'll zoom on the novel concept of Angle of Arrival (AoA) measurements that are empowering novel devices with accurate and low-power localization. Transitioning into the realm of energy efficiency, we will explore novel UWB Wake-Up Radios benefit energy and latency versus conventional duty cycling approaches. Finally, we'll assemble the pieces of the puzzle to unveil a self-sustaining IoT system. Integrating UWB with energy-efficient wake-up radio and embedded processing creates an unobtrusive and accurate indoor location system. By adopting an …
:view less
Evaluation of a Non-Coherent Ultra-Wideband Transceiver for Micropower Sensor Nodes
2023
Jonah Imfeld, Silvano Cortesi, Philipp Mayer, Michele Magno
2023 IEEE SENSORS, 1-4
:read more
Authors:Jonah Imfeld, Silvano Cortesi, Philipp Mayer, Michele Magno
Publication date:10/29/2023
Journal:2023 IEEE SENSORS
Pages:1-4
Publisher:IEEE
Description:Spatial and contextual awareness has the potential to revolutionize sensor nodes, enabling spatially augmented data collection and location-based services. With its high bandwidth, superior energy efficiency, and precise time-of-flight measurements, ultra-wideband (UWB) technology emerges as an ideal solution for such devices. This paper presents an evaluation and comparison of a non-coherent UWB transceiver within the context of highly energy-constrained wireless sensing nodes and pervasive Internet of Things (IoT) devices. Experimental results highlight the unique properties of UWB transceivers, showcasing efficient data transfer ranging from 2 kbit /s to 7.2 Mbit /s while reaching an energy consumption of 0.29 nJ /bit and 1.39 nJ /bit for transmitting and receiving, respectively. Notably, a ranging accuracy of up to ±25 cm can be achieved. Moreover, the peak power consumption of the UWB transceiver is …
Cited by:1
Resources:[PDF] from arxiv.org
:view less
Enhancing lightweight neural networks for small object detection in iot applications
2023
Liam Boyle, Nicolas Baumann, Seonyeong Heo, Michele Magno
2023 IEEE SENSORS, 01-04
:read more
Authors:Liam Boyle, Nicolas Baumann, Seonyeong Heo, Michele Magno
Publication date:10/29/2023
Journal:2023 IEEE SENSORS
Pages:01-04
Publisher:IEEE
Description:Advances in lightweight neural networks have revolutionized computer vision in a broad range of Internet of Things (IoT) applications, encompassing remote monitoring and process automation. However, the detection of small objects, which is crucial for many of these applications, remains an underexplored area in current computer vision research, particularly for embedded devices. To address this gap, the paper proposes a novel adaptive tiling method that can be used on top of any existing object detector including the popular Faster Objects More Objects (FOMO) network for object detection on microcontrollers. Our experimental results show that the proposed tiling method can boost the F1-score by up to 225% while reducing the average object count error by up to 76%. Furthermore, the findings of this work suggest that using a soft F1 loss over the popular binary cross-entropy loss can significantly reduce the …
Cited by:7
Resources:[PDF] from arxiv.org
:view less
Quantitative Evaluation of a Multi-Modal Camera Setup for Fusing Event Data with RGB Images
2023
Julian Moosmann, Jakub Mandula, Philipp Mayer, Luca Benini, Michele Magno
2023 IEEE SENSORS, 1-4
:read more
Authors:Julian Moosmann, Jakub Mandula, Philipp Mayer, Luca Benini, Michele Magno
Publication date:10/29/2023
Journal:2023 IEEE SENSORS
Pages:1-4
Publisher:IEEE
Description:Event-based cameras, also called silicon retinas, potentially revolutionize computer vision by detecting and reporting significant changes in intensity asynchronous events, offering extended dynamic range, low latency, and low power consumption, enabling a wide range of applications from autonomous driving to longtime surveillance. As an emerging technology, there is a notable scarcity of publicly available datasets for event-based systems that also feature frame-based cameras, in order to exploit the benefits of both technologies. This work quantitatively evaluates a multi-modal camera setup for fusing high-resolution dynamic vision sensor (DVS) data with RGB image data by static camera alignment. The proposed setup, which is intended for semi-automatic DVS data labeling, combines two recently released Prophesee EVK4 DVS cameras and one global shutter XIMEA MQ022CG-CM RGB camera. After …
Cited by:2
Resources:[PDF] from arxiv.org
:view less
Tinytracker: Ultra-fast and ultra-low-power edge vision in-sensor for gaze estimation
2023
Pietro Bonazzi, Thomas Rüegg, Sizhen Bian, Yawei Li, Michele Magno
2023 IEEE SENSORS, 1-4
:read more
Authors:Pietro Bonazzi, Thomas Rüegg, Sizhen Bian, Yawei Li, Michele Magno
Publication date:10/29/2023
Journal:2023 IEEE SENSORS
Pages:1-4
Publisher:IEEE
Description:Intelligent edge vision tasks encounter the critical challenge of ensuring power and latency efficiency due to the typically heavy computational load they impose on edge platforms. This work leverages one of the first “Artificial Intelligence (AI) in sensor” vision platforms, IMX500 by Sony, to achieve ultra- fast and ultra-low-power end-to-end edge vision applications. We evaluate the IMX500 and compare it to other edge platforms, such as the Google Coral Dev Micro and Sony Spresense, by exploring gaze estimation as a case study. We propose TinyTracker, a highly efficient, fully quantized model for 2D gaze estimation designed to maximize the performance of the edge vision systems considered in this study. TinyTracker achieves a 41x size reduction (~ 600Kb) compared to iTracker [1] without significant loss in gaze estimation accuracy (maximum of 0.16 cm when fully quantized). TinyTracker's deployment on the …
Cited by:18
Resources:[PDF] from arxiv.org
:view less
A self-sustainable and micro-second time synchronized multi-node wireless system for aerodynamic monitoring on wind turbines
2023
Tommaso Polonelli, Amirhossein Moallemi, Weikang Kong, Hanna Müller, Julien Deparday, M…
IEEE Access 11, 119506-119522
:read more
Authors:Tommaso Polonelli, Amirhossein Moallemi, Weikang Kong, Hanna Müller, Julien Deparday, Michele Magno, Luca Benini
Publication date:10/25/2023
Journal:IEEE Access
Volume:11
Pages:119506-119522
Publisher:IEEE
Description:Wind energy generation plays a vital role in transitioning from fossil fuel-based energy sources and in alleviating the impacts of global warming. However, global wind energy coverage still needs to rise, while requiring a significant step up in conversion efficiency: monitoring wind flow and operational parameters of wind turbines is an essential prerequisite for coverage and conversion efficiency optimization. This paper presents a low-power, self-sustainable, and time-synchronised system for aerodynamic and acoustic measurements on operating wind turbines. It includes 40 high-accuracy barometers, 10 microphones, 5 differential pressure sensors, and implements a coarse time synchronisation on top of a Bluetooth Low Energy 5.1 protocol tuned for long-range communications. Moreover, we field-assessed the node capability to collect precise and accurate aerodynamic data with a multi-node setup. Outdoor …
Cited by:8
Resources:[PDF] from ieee.org
:view less
Noninvasive urinary bladder volume estimation with Artifact-Suppressed bioimpedance measurements
2023
Kanika Dheman, Stefan Walser, Philipp Mayer, Manuel Eggimann, Marko Kozomara, Denise Fr…
IEEE Sensors Journal 24 (2), 1633-1643
:read more
Authors:Kanika Dheman, Stefan Walser, Philipp Mayer, Manuel Eggimann, Marko Kozomara, Denise Franke, Thomas Hermanns, Hugo Sax, Simone Schürle, Michele Magno
Publication date:10/24/2023
Journal:IEEE Sensors Journal
Volume:24
Issue:2
Pages:1633-1643
Publisher:IEEE
Description:Urine output is a vital parameter to gauge kidney health. Current monitoring methods include manually written records, invasive urinary catheterization, or ultrasound measurements performed by highly skilled personnel. Catheterization bears high risks of infection while intermittent ultrasound measures and manual recording are time-consuming and might miss early signs of kidney malfunction. Bioimpedance (BI) measurements may serve as a noninvasive alternative for measuring urine volume in vivo. However, limited robustness has prevented its clinical translation. Here, a deep learning-based algorithm is presented that processes the local BI of the lower abdomen and suppresses artifacts to measure the bladder volume quantitatively, noninvasively, and without the continuous need for additional personnel. A tetrapolar BI wearable system was used to collect continuous bladder volume data from three healthy subjects to …
Cited by:10
Resources:[PDF] from arxiv.org
:view less
Towards a Novel Ultrasound System Based on Low-Frequency Feature Extraction From a Fully-Printed Flexible Transducer
2023
Marco Giordano, Kirill Keller, Francesco Greco, Luca Benini, Michele Magno, Christoph L…
2023 IEEE Biomedical Circuits and Systems Conference (BioCAS), 1-5
:read more
Authors:Marco Giordano, Kirill Keller, Francesco Greco, Luca Benini, Michele Magno, Christoph Leitner
Publication date:10/19/2023
Journal:2023 IEEE Biomedical Circuits and Systems Conference (BioCAS)
Pages:1-5
Publisher:IEEE
Description:Ultrasound is a key technology in healthcare, and it is being explored for non-invasive, wearable, continuous monitoring of vital signs. However, its widespread adoption in this scenario is still hindered by the size, complexity, and power consumption of current devices. Moreover, such an application demands adaptability to human anatomy, which is hard to achieve with current transducer technology. This paper presents a novel ultrasound system prototype based on a fully printed, lead-free, and flexible polymer ultrasound transducer, whose bending radius promises good adaptability to the human anatomy. Our application scenario focuses on continuous blood flow monitoring. We implemented a hardware envelope filter to efficiently transpose high-frequency ultrasound signals to a lower-frequency spectrum. This reduces computational and power demands with little to no degradation in the task proposed for this …
Cited by:3
Resources:[PDF] from arxiv.org
:view less
Skilog: A smart sensor system for performance analysis and biofeedback in ski jumping
2023
Lukas Schulthess, Thorir Mar Ingolfsson, Marc Nölke, Michele Magno, Luca Benini, Christ…
2023 IEEE Biomedical Circuits and Systems Conference (BioCAS), 1-5
:read more
Authors:Lukas Schulthess, Thorir Mar Ingolfsson, Marc Nölke, Michele Magno, Luca Benini, Christoph Leitner
Publication date:10/19/2023
Journal:2023 IEEE Biomedical Circuits and Systems Conference (BioCAS)
Pages:1-5
Publisher:IEEE
Description:In ski jumping, low repetition rates of jumps limit the effectiveness of training. Thus, increasing learning rate within every single jump is key to success. A critical element of athlete training is motor learning, which has been shown to be accelerated by feedback methods. In particular, a fine-grained control of the center of gravity in the in-run is essential. This is because the actual takeoff occurs within a blink of an eye (∼ 300 ms), thus any unbalanced body posture during the in-run will affect flight.This paper presents a smart, compact, and energy-efficient wireless sensor system for real-time performance analysis and biofeedback during ski jumping. The system operates by gauging foot pressures at three distinct points on the insoles of the ski boot at 100 Hz. Foot pressure data can either be directly sent to coaches to improve their feedback, or fed into a Machine Learning (ML) model to give athletes instantaneous in …
Cited by:4
Resources:[PDF] from arxiv.org
:view less
Advancing Freight Train Integrity Monitoring for Next-Generation Railway Signaling Using UWB Ranging
2023
Denis Mikhaylov, Fu Zheng, Philipp Mayer, Christian Vogt, Tommaso Polonelli, Michele Magno
2023 IEEE 9th World Forum on Internet of Things (WF-IoT), 1-6
:read more
Authors:Denis Mikhaylov, Fu Zheng, Philipp Mayer, Christian Vogt, Tommaso Polonelli, Michele Magno
Publication date:10/12/2023
Journal:2023 IEEE 9th World Forum on Internet of Things (WF-IoT)
Pages:1-6
Publisher:IEEE
Description:Reliable train integrity monitoring is crucial to enabling the implementation of state-of-the-art railway signaling and safety systems such as ETCS Level 3. However, train integrity monitoring presents a significant challenge for European freight trains, which currently consist of unpowered freight wagons and a locomotive, with only mechanical and pneumatic connections between them. This paper presents a study and experimental evaluation under static and dynamic conditions of the feasibility of using Ultra-WideBand (UWB) ranging to monitor train in-tegrity with a network of low-power and cost-optimized Internet of Things (IoT) devices. Static tests are performed on freight wagons to investigate the optimal UWB sensor positioning and the impact of Non-Line-of-Sight (NLoS) conditions on ranging accuracy. These tests show that positioning has a significant impact on the proportion of ranging attempts that are …
Cited by:1
:view less
Securing tiny transformer-based computer vision models: Evaluating real-world patch attacks
2023
Andrea Mattei, Moritz Scherer, Cristian Cioflan, Michele Magno, Luca Benini
2023 IEEE 9th World Forum on Internet of Things (WF-IoT), 1-7
:read more
Authors:Andrea Mattei, Moritz Scherer, Cristian Cioflan, Michele Magno, Luca Benini
Publication date:10/12/2023
Journal:2023 IEEE 9th World Forum on Internet of Things (WF-IoT)
Pages:1-7
Publisher:IEEE
Description:Transformers have significantly impacted the field of Computer Vision (CV) and the Internet of Things (IoT), sur-passing Convolutional Neural Networks (CNN) in various tasks. However, ensuring the security of CV models for critical real-world IoT applications such as autonomous driving, surveillance, and biomedical technologies is crucial. The adversarial robustness of these models has become a key research area, especially for edge processing. This work evaluates the robustness of Swin tiny and ConvNeXt tiny, specifically focusing on real-world patch attacks in Object Detection scenarios. To ensure a fair comparison, we establish a level playing field between Transformer-based and CNN architectures, examining their vulnerabilities and potential defenses. Experimental results demonstrate the susceptibility of the Swin tiny and ConvNeXt tiny models to patch attacks, resulting in a significant decrease in …
Cited by:2
Resources:[PDF] from ethz.ch
:view less
Optimizing iot-based asset and utilization tracking: Efficient activity classification with minirocket on resource-constrained devices
2023
Marco Giordano, Silvano Cortesi, Michele Crabolu, Lavinia Pedrollo, Giovanni Bellusci, …
2023 IEEE 9th World Forum on Internet of Things (WF-IoT), 1-8
:read more
Authors:Marco Giordano, Silvano Cortesi, Michele Crabolu, Lavinia Pedrollo, Giovanni Bellusci, Tommaso Bendinelli, Engin Türetken, Andrea Dunbar, Michele Magno
Publication date:10/12/2023
Journal:2023 IEEE 9th World Forum on Internet of Things (WF-IoT)
Pages:1-8
Publisher:IEEE
Description:This paper introduces an effective solution for retrofitting construction power tools with low-power Internet of Things (IoT) to enable accurate activity classification. We address the challenge of distinguishing between when a power tool is being moved and when it is actually being used. To achieve classification accuracy and power consumption preser-vation a newly released algorithm called MINImally RandOm Convolutional KErnel Transform (MINIROCKET) was employed. Known for its accuracy, scalability, and fast training for time-series classification, in this paper, it is proposed as a Tiny ML algorithm for inference on resource-constrained IoT devices. The paper demonstrates the portability and performance of MINIROCKET on a resource-constrained, ultra-low power sensor node for floating-point and fixed-point arithmetic, matching up to 1% of the floating-point accuracy. The hyperparameters of the algorithm …
Cited by:4
Resources:[PDF] from arxiv.org
:view less
Assessing the robustness of lidar, radar and depth cameras against ill-reflecting surfaces in autonomous vehicles: An experimental study
2023
Michael Lötscher, Nicolas Baumann, Edoardo Ghignone, Andrea Ronco, Michele Magno
2023 IEEE 9th World Forum on Internet of Things (WF-IoT), 1-6
:read more
Authors:Michael Lötscher, Nicolas Baumann, Edoardo Ghignone, Andrea Ronco, Michele Magno
Publication date:10/12/2023
Journal:2023 IEEE 9th World Forum on Internet of Things (WF-IoT)
Pages:1-6
Publisher:IEEE
Description:Range-measuring sensors play a critical role in autonomous driving systems. While Light Detection and Ranging ( LiDAR) technology has been dominant, its vulnerability to adverse weather conditions is well-documented. This paper focuses on secondary adverse conditions - the implications of ill-reflective surfaces on range measurement sensors. We assess the influence of this condition on the three primary ranging modalities used in autonomous mobile robotics: LiDAR, Radio Detection and Ranging (RADAR), and Depth-Camera. Based on accurate experimental evaluation the paper's findings reveal that under ill-reflectivity, LiDAR ranging performance drops significantly to 33% of its nominal operating conditions, whereas (RADAR) and Depth-Cameras maintain up to 100% of their nominal distance ranging capabilities. Additionally, we demonstrate on a 1:10 scaled autonomous racecar how ill-reflectivity …
Cited by:5
Resources:[PDF] from arxiv.org
:view less
Evaluating spiking neural network on neuromorphic platform for human activity recognition
2023
Sizhen Bian, Michele Magno
Proceedings of the 2023 ACM International Symposium on Wearable Computers, 82-86
:read more
Authors:Sizhen Bian, Michele Magno
Publication date:10/08/2023
Journal:Proceedings of the 2023 ACM International Symposium on Wearable Computers
Pages:82-86
Description: Energy efficiency and low latency are crucial requirements for designing wearable AI-empowered human activity recognition systems, due to the hard constraints of battery operations and closed-loop feedback. While neural network models have been extensively compressed to match the stringent edge requirements, spiking neural networks and event-based sensing are recently emerging as promising solutions to further improve performance due to their inherent energy efficiency and capacity to process spatiotemporal data in very low latency. This work aims to evaluate the effectiveness of spiking neural networks on neuromorphic processors in human activity recognition for wearable applications. The case of workout recognition with wrist-worn wearable motion sensors is used as a study. A multi-threshold delta modulation approach is utilized for encoding the input sensor data into spike trains to move the …
Cited by:11
Resources:[PDF] from arxiv.org
:view less
Robust and efficient depth-based obstacle avoidance for autonomous miniaturized uavs
2023
Hanna Müller, Vlad Niculescu, Tommaso Polonelli, Michele Magno, Luca Benini
IEEE Transactions on Robotics 39 (6), 4935-4951
:read more
Authors:Hanna Müller, Vlad Niculescu, Tommaso Polonelli, Michele Magno, Luca Benini
Publication date:10/05/2023
Journal:IEEE Transactions on Robotics
Volume:39
Issue:6
Pages:4935-4951
Publisher:IEEE
Description:Nanosize drones hold enormous potential to explore unknown and complex environments. Their small size makes them agile and safe for operation close to humans and allows them to navigate through narrow spaces. However, their tiny size and payload restrict the possibilities for onboard computation and sensing, making fully autonomous flight extremely challenging. The first step toward full autonomy is reliable obstacle avoidance, which has proven to be challenging by itself in a generic indoor environment. Current approaches utilize vision-based or 1-D sensors to support nanodrone perception algorithms. This article presents a lightweight obstacle avoidance system based on a novel millimeter form factor 64 pixels multizone time-of-flight (ToF) sensor and a generalized model-free control policy. In-field tests are based on the Crazyflie 2.1, extended by a custom multizone ToF deck, featuring a total flight mass of …
Cited by:47
Resources:[PDF] from arxiv.org
:view less
LocalViT: Analyzing locality in vision transformers
2023
Yawei Li, Kai Zhang, Jiezhang Cao, Radu Timofte, Michele Magno, Luca Benini, Luc Van Goo
2023 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 9598-9605
:read more
Authors:Yawei Li, Kai Zhang, Jiezhang Cao, Radu Timofte, Michele Magno, Luca Benini, Luc Van Goo
Publication date:10/01/2023
Journal:2023 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)
Pages:9598-9605
Publisher:IEEE
Description:The aim of this paper is to study the influence of locality mechanisms in vision transformers. Transformers originated from machine translation and are particularly good at modelling long-range dependencies within a long sequence. Although the global interaction between the token embeddings could be well modelled by the self-attention mechanism of transformers, what is lacking is a locality mechanism for infor-mation exchange within a local region. In this paper, locality mechanism is systematically investigated by carefully designed controlled experiments. We add locality to vision transformers into the feed-forward network. This seemingly simple solution is inspired by the comparison between feed-forward networks and inverted residual blocks. The importance of locality mechanisms is validated in two ways: 1) A wide range of design choices (activation function, layer placement, expansion ratio) are available …
Cited by:29
:view less
A relative infrastructure-less localization algorithm for decentralized and autonomous swarm formation
2023
Dominik Schindler, Vlad Niculescu, Tommaso Polonelli, Daniele Palossi, Luca Benini, Mic…
2023 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 5288-5295
:read more
Authors:Dominik Schindler, Vlad Niculescu, Tommaso Polonelli, Daniele Palossi, Luca Benini, Michele Magno
Publication date:10/01/2023
Journal:2023 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)
Pages:5288-5295
Publisher:IEEE
Description:Decentralized and autonomous control of Unmanned Aerial Vehicle (UAV) swarms is a key enabler for cooperative systems and infrastructure-less formation flights. However, UAVs often lack reliable heading angle measurements, especially in indoor scenarios, space, and GNSS-denied environments, posing an additional observability challenge on range-based relative localization. We tackle this problem by proposing a novel solution enhancing the classical tag-and-anchor trilateration. The proposed solution relies on Ultra-wideband range measurements and addresses the relative pose estimation between pairs of UAVs under relative motion. Furthermore, it does not require any explicit motion pattern or initialization procedure and leverages an approximate maximum-likelihood algorithm to recursively solve the relative localization problem with constant computational complexity. The method has been …
Cited by:3
Resources:[PDF] from pulp-platform.org
:view less
A unified sensor platform for investigating corona effects on overhead lines
2023
Pascal Bleuler, Tommaso Polonelli, Yu Xiao, Benjamin Stadler, Lorenz Gallina, Hannah Ki…
IEEE Transactions on Instrumentation and Measurement 72, 1-11
:read more
Authors:Pascal Bleuler, Tommaso Polonelli, Yu Xiao, Benjamin Stadler, Lorenz Gallina, Hannah Kirchner, Michele Magno, Christian M Franck
Publication date:09/07/2023
Journal:IEEE Transactions on Instrumentation and Measurement
Volume:72
Pages:1-11
Publisher:IEEE
Description:Outdoor long-term continuous measurements of overhead conductor corona are needed to better plan high-voltage power grids. Most of the time, only single aspects of corona are being measured over short periods of time in controlled environments using complex and expensive sensors. This article presents a single unified wireless sensor platform to reliably measure three distinct corona-related quantities on high-voltage lines, namely, the corona current through the line, the ground-level electric field, and the ground-level ion current density. The platform is a distributed, cost-effective, low-power Internet of Things (IoT) system that enables outdoor measurements of lines exposed to real weather overextended periods of time allowing to highlight correlations across seasons. With example measurements, the importance of having heterogeneous sensors measuring different corona effects in a unified way is …
Cited by:5
Resources:[PDF] from ethz.ch
:view less
Towards robust velocity and position estimation of opponents for autonomous racing using low-power radar
2023
Andrea Ronco, Nicolas Baumann, Marco Giordano, Michele Magno
arXiv preprint arXiv:2309.01647
:read more
Authors:Andrea Ronco, Nicolas Baumann, Marco Giordano, Michele Magno
Publication date:09/04/2023
Journal:arXiv preprint arXiv:2309.01647
Description:This paper presents the design and development of an intelligent subsystem that includes a novel low-power radar sensor integrated into an autonomous racing perception pipeline to robustly estimate the position and velocity of dynamic obstacles. The proposed system, based on the Infineon BGT60TR13D radar, is evaluated in a real-world scenario with scaled race cars. The paper explores the benefits and limitations of using such a sensor subsystem and draws conclusions based on field-collected data. The results demonstrate a tracking error up to 0.21 +- 0.29 m in distance estimation and 0.39 +- 0.19 m/s in velocity estimation, despite the power consumption in the range of 10s of milliwatts. The presented system provides complementary information to other sensors such as LiDAR and camera, and can be used in a wide range of applications beyond autonomous racing.
Cited by:1
Resources:[PDF] from arxiv.org
:view less
Grayscale and event-based sensor fusion for robust steering prediction for self-driving cars
2023
Luca Pascarella, Michele Magno
2023 IEEE Sensors Applications Symposium (SAS), 01-06
:read more
Authors:Luca Pascarella, Michele Magno
Publication date:07/18/2023
Journal:2023 IEEE Sensors Applications Symposium (SAS)
Pages:01-06
Publisher:IEEE
Description:Event-based vision, led by a dynamic vision sensor (DVS), is a bio-inspired vision model that leverages timestamped pixel-level brightness changes of non-static scenes. Thus, DVS's architecture captures the dynamics of a scene and filters static information out. Although machine learning algorithms based on DVS inputs overcome active pixel sensors (APS), they still struggle in challenging conditions. For example, DVS-based models outperform APS-based ones in high-dynamic scenes but suffer in static landscapes. In this paper, we present GEFU (Grayscale and Event-based FUsor), an approach that opens to sensor fusion by combining grayscale and event-based inputs. In particular, we evaluate GEFU's performance on a practical task: predicting a vehicle's steering angle in a realistic driving condition. GEFU is built on top of a consolidated convolutional neural network and trained with realistic driving …
Cited by:4
:view less
A robust and real-time hyper-spectral sensor-fusion model for concrete crack segmentation
2023
Matthias Steiner, Nicolas Baumann, Luzian Lebovitz, Michele Magno
2023 IEEE Sensors Applications Symposium (SAS), 1-6
:read more
Authors:Matthias Steiner, Nicolas Baumann, Luzian Lebovitz, Michele Magno
Publication date:07/18/2023
Journal:2023 IEEE Sensors Applications Symposium (SAS)
Pages:1-6
Publisher:IEEE
Description:Structural defects in civil infrastructure, such as highways, roads, bridges, and dams, can severely impact their reliability and safety. Manual inspection of such infrastructure is labor-intensive and costly, creating the demand for automated damage-tracking systems. Data-driven techniques, such as machine learning, and statistical methods have been utilized in a remarkable number of Structural Health Monitoring (SHM) applications. However, real-time and high-accuracy concrete crack detection poses severe challenges for deployment on embedded systems and mobile robotic platforms, due to their computational constraints, low-latency requirements, and the robustness of model predictions in field deployments. This work proposes a robust and low-latency transformer-based deep-crack segmentation model that leverages both Red Green Blue (RGB) and Hyper Spectral (HYP) data for crack detection. The model …
Cited by:2
:view less
Improving data-scarce image classification through multimodal synthetic data pretraining
2023
Carl Brander, Cristian Cioflan, Vlad Niculescu, Hanna Müller, Tommaso Polonelli, Michel…
2023 IEEE Sensors Applications Symposium (SAS), 1-6
:read more
Authors:Carl Brander, Cristian Cioflan, Vlad Niculescu, Hanna Müller, Tommaso Polonelli, Michele Magno, Luca Benini
Publication date:07/18/2023
Journal:2023 IEEE Sensors Applications Symposium (SAS)
Pages:1-6
Publisher:IEEE
Description:Deep Learning algorithms and models greatly benefit from the release of large-scale datasets, also including synthetically generated data, when real-life data is scarce. Multimodal datasets feature more descriptive environmental information than single-sensor ones, but they are generally small and not widely accessible. In this paper, we construct a synthetically-generated image classification dataset consisting of grayscale camera images and depth information acquired from an 8×8-pixel Time-of-Flight sensor. We propose and evaluate six Convolutional Neural Network-based feature-level fusion models to integrate the multimodal data, outperforming the accuracy of the camera-only model by up to 17% in real-world settings. By pretraining the model on synthetically-generated sample pairs, followed by fine-tuning it with only 16 real-domain samples, we outperform a non-pretrained counterpart by 35% while …
Cited by:3
:view less
Learning continuous piecewise non-linear activation functions for deep neural networks
2023
Xinchen Gao, Yawei Li, Wen Li, Lixin Duan, Luc Van Gool, Luca Benini, Michele Magno
2023 IEEE International Conference on Multimedia and Expo (ICME), 1835-1840
:read more
Authors:Xinchen Gao, Yawei Li, Wen Li, Lixin Duan, Luc Van Gool, Luca Benini, Michele Magno
Publication date:07/10/2023
Journal:2023 IEEE International Conference on Multimedia and Expo (ICME)
Pages:1835-1840
Publisher:IEEE
Description:Activation functions provide the non-linearity to deep neural networks, which are crucial for the optimization and performance improvement. In this paper, we propose a learnable continuous piece-wise nonlinear activation function (or CPN in short), which improves the widely used ReLU from three directions, i.e., finer pieces, non-linear terms and learnable parameterization. CPN is a continuous activation function with multiple pieces and incorporates non-linear terms in every interval. We give a general formulation of CPN and provide different implementations according to three key factors: whether the activation space is divided uniformly or not, whether the non-linear terms exist or not, and whether the activation function is continuous or not. We demonstrate the effectiveness of our method on image classification and single image super-resolution tasks by simply changing the activation function. For example, CPN …
Cited by:4
:view less
Automated Assessment and Guidance of Project Work
2023
Victoria Abou-Khalil, Andrew Vargo, Rwitajit Manjoumdar, Michele Magno, Manu Kapur
International Conference on Artificial Intelligence in Education, 69-73
:read more
Authors:Victoria Abou-Khalil, Andrew Vargo, Rwitajit Manjoumdar, Michele Magno, Manu Kapur
Publication date:06/30/2023
Journal:International Conference on Artificial Intelligence in Education
Pages:69-73
Publisher:Springer Nature Switzerland
Description:Project-Based Learning improves student achievement and prepares students for a sustainable society, but the multimodality and unstructured nature of project work makes it difficult to comprehensively assess and support it. The recent availability of high-frequency sensors and the accessibility of machine learning techniques provide opportunities to create technologies that capture and analyze data in real time during projects. The workshop aims to bring together experts from the fields of AI, learning analytics, sensing technologies, and learning sciences to discuss technologies for detecting, understanding, and predicting learning during projects, as well as to discuss what is pedagogically desirable, technically feasible, and ethically sound. This workshop is important to the AIED community, particularly those working on developing technologies to capture project work or more generally, complex multimodal …
Cited by:2
:view less
Self-sustaining ultrawideband positioning system for event-driven indoor localization
2023
Philipp Mayer, Michele Magno, Luca Benini
IEEE Internet of Things Journal 11 (1), 1272-1284
:read more
Authors:Philipp Mayer, Michele Magno, Luca Benini
Publication date:06/26/2023
Journal:IEEE Internet of Things Journal
Volume:11
Issue:1
Pages:1272-1284
Publisher:IEEE
Description:Smart and unobtrusive mobile sensor nodes that accurately track their own position have the potential to augment data collection with location-based functions. To attain this vision of unobtrusiveness, the sensor nodes must have a compact form factor and operate over long periods without battery recharging or replacement. This article presents a self-sustaining and accurate ultrawideband (UWB)-based indoor location system with conservative infrastructure overhead. An event-driven sensing approach allows for balancing the limited energy harvested in indoor conditions with the power consumption of UWB transceivers. The presented tag-centralized concept, which combines heterogeneous system design with embedded processing, minimizes idle consumption without sacrificing functionality. Despite modest infrastructure requirements, high-localization accuracy is achieved with error-correcting double-sided two …
Cited by:27
Resources:[PDF] from arxiv.org
:view less
Latency and Power Consumption in 2.4 GHz IoT Wireless Mesh Nodes: An Experimental Evaluation of Bluetooth Mesh and Wirepas Mesh
2023
Silvano Cortesi, Christian Vogt, Elio Reinschmidt, Michele Magno
2023 19th International Conference on Wireless and Mobile Computing, Networking and Com…
:read more
Authors:Silvano Cortesi, Christian Vogt, Elio Reinschmidt, Michele Magno
Publication date:06/21/2023
Journal:2023 19th International Conference on Wireless and Mobile Computing, Networking and Communications (WiMob)
Pages:200-205
Publisher:IEEE
Description:The rapid growth of the Internet of Things paradigm is pushing the need to connect billions of battery-operated devices to the internet and among them. To address this need, the introduction of energy-efficient wireless mesh networks based on Bluetooth provides an effective solution. This paper proposes a testbed setup to accurately evaluate and compare the standard Bluetooth Mesh 5.0 and the emerging energy-efficient Wirepas protocol that promises better performance. The paper presents the evaluation in terms of power consumption, energy efficiency, and transmission latency which are the most crucial features, in a controlled and reproducible test setup consisting of 10 nodes. Experimental results demonstrated that Wirepas has a median latency of 2.83ms in Low-Latency mode respectively around 2s in the Low-Energy mode. The corresponding power consumption is 6.2mA in Low-Latency mode and 38 …
Cited by:3
Resources:[PDF] from arxiv.org
:view less
Simultaneous neuromorphic selection of multiple salient objects for event vision
2023
Amélie Gruel, Jean Martinet, Michele Magno
2023 international joint conference on neural networks (IJCNN), 1-8
:read more
Authors:Amélie Gruel, Jean Martinet, Michele Magno
Publication date:06/18/2023
Journal:2023 international joint conference on neural networks (IJCNN)
Pages:1-8
Publisher:IEEE
Description:The combined use of spiking neural networks and event cameras is gaining momentum in the field of embedded computer vision as they promise to reduce latency and computational resource requests. However, state-of-the-art embedded neuromorphic models show little interest in modifying input data to optimise model performance, memory usage, latency, and power consumption. This work addresses this optimisation trade-off by implementing a neuromorphic model of salient selection, which simultaneously outputs multiple segregated objects of interest detected in an event-based scene. This work extends previous ones and identifies regions of interest as those corresponding to a high spatiotemporal density of events. Without any training and with a limited number of neurons, the proposed model is able to simultaneously detect different objects with a delay of only 14ms at most, and filtered objects maintain …
Cited by:5
Resources:[PDF] from hal.science
:view less
Investigation of mmWave radar technology for non-contact vital sign monitoring
2023
Steven Marty, Federico Pantanella, Andrea Ronco, Kanika Dheman, Michele Magno
2023 IEEE International Symposium on Medical Measurements and Applications (MeMeA), 1-6
:read more
Authors:Steven Marty, Federico Pantanella, Andrea Ronco, Kanika Dheman, Michele Magno
Publication date:06/14/2023
Journal:2023 IEEE International Symposium on Medical Measurements and Applications (MeMeA)
Pages:1-6
Publisher:IEEE
Description:Non-contact vital sign monitoring has many advantages over conventional methods in being comfortable, unobtrusive and without any risk of spreading infection. The use of millimeter-wave (mmWave) radars is one of the most promising approaches that enable contact-less monitoring of vital signs. Novel low-power implementations of this technology promise to enable vital sign sensing in embedded, battery-operated devices. The nature of these new low-power sensors exacerbates the challenges of accurate and robust vital sign monitoring and especially the problem of heart-rate tracking. This work focuses on the investigation and characterization of three Frequency Modulated Continuous Wave (FMCW) low-power radars with different carrier frequencies of 24 GHz, 60 GHz and 120 GHz. The evaluation platforms were first tested on phantom models that emulated human bodies to accurately evaluate the …
Cited by:7
Resources:[PDF] from arxiv.org
:view less
Kp2dtiny: Quantized neural keypoint detection and description on the edge
2023
Thomas Rüegg, Marco Giordano, Michele Magno
2023 IEEE 5th International Conference on Artificial Intelligence Circuits and Systems …
:read more
Authors:Thomas Rüegg, Marco Giordano, Michele Magno
Publication date:06/11/2023
Journal:2023 IEEE 5th International Conference on Artificial Intelligence Circuits and Systems (AICAS)
Pages:1-5
Publisher:IEEE
Description:Detection and description of keypoints in images is a fundamental component of a wide range of tasks such as Simultaneous Localization And Mapping (SLAM), image alignment and structure from motion (SfM). Efficient computation of these features is crucial for real-time applications and has been addressed by multiple handcrafted algorithms and, recently, by deep neural network-based detectors. Learned detectors achieve high detection performance, but pose high computational requirements, making them slow and impractical for low-power resource constraint platforms. This paper presents a quantized neural keypoint detector and descriptor optimized for edge devices exploiting two recent AI platforms such as MAX78000 by Analog Devices and the Coral AI USB accelerator from Google. To accommodate the diverse constraints and requirements of various applications, we propose and evaluate two model …
Cited by:4
:view less
Embedded neuromorphic attention model leveraging a novel low-power heterogeneous platform
2023
Amélie Gruel, Alfio Di Mauro, Robin Hunziker, Luca Benini, Jean Martinet, Michele Magno
International Conference on Artificial Intelligence Circuits and Systems (AICAS) 2023, 1-5
:read more
Authors:Amélie Gruel, Alfio Di Mauro, Robin Hunziker, Luca Benini, Jean Martinet, Michele Magno
Publication date:06/11/2023
Journal:International Conference on Artificial Intelligence Circuits and Systems (AICAS)
Volume:2023
Pages:1-5
Publisher:IEEE
Description:Neuromorphic computing has been identified as an ideal candidate to exploit the potential of event-based cameras, a promising sensor for embedded computer vision. However, state-of-the-art neuromorphic models try to maximize the model performance on large platforms rather than a trade-off between memory requirements and performance. We present the first deployment of an embedded neuromorphic algorithm on Kraken, a low-power RISC-V-based SoC prototype including a neuromorphic spiking neural network (SNN) accelerator. In addition, the model employed in this paper was designed to achieve visual attention detection on event data while minimizing the neuronal populations’ size and the inference latency. Experimental results show that it is possible to achieve saliency detection in event data with a delay of 32ms, maintains classification accuracy of 84.51% and consumes only 3.85mJ per second of processed input data, achieving all of this while processing input data 10 times faster than real-time. This trade-off between decision latency, power consumption, accuracy, and run time significantly outperforms those achieved by previous implementations on CPU and neuromorphic hardware.
Resources:[PDF] from hal.science
:view less
Towards Wearable Sweat Sensing for Glucose and Lactate: Sensors Characterisation
2023
Kanika Dheman, Alkinoos Sariglou, Michele Magno
2023 9th International Workshop on Advances in Sensors and Interfaces (IWASI), 121-126
:read more
Authors:Kanika Dheman, Alkinoos Sariglou, Michele Magno
Publication date:06/08/2023
Journal:2023 9th International Workshop on Advances in Sensors and Interfaces (IWASI)
Pages:121-126
Publisher:IEEE
Description:Non-invasive sweat glucose and lactate monitoring has many advantages over conventional blood sampling methods in being comfortable, unobtrusive, and offering continuous tracking. The use of wearable electrochemical sensors is one of the most promising approaches to enable sweat analytes’ sensing without being influenced by ambient light artifacts. Novel low-power implementations of a sweat sensing device promise to offer health and well-being tracking in wearable, battery-operated systems. Multiple challenges remain until this vision can be realized, such as identifying the variation with temperature and sources of drifts and sample evaporation. This work focuses on the investigation and characterization of glucose and lactate electrochemical sensors with the aim of unveiling their implicit materials’ properties, their dependence on temperature and their durability. The sensors were characterized with …
Cited by:1
:view less
Blade position and motion estimation on the surface of a rotating wind turbine through a single MEMS IMU
2023
Phillip Trummer, Tommaso Polonelli, Julien Deparday, Imad Abdallah, Michele Magno
2023 9th international workshop on advances in sensors and interfaces (IWASI), 40-45
:read more
Authors:Phillip Trummer, Tommaso Polonelli, Julien Deparday, Imad Abdallah, Michele Magno
Publication date:06/08/2023
Journal:2023 9th international workshop on advances in sensors and interfaces (IWASI)
Pages:40-45
Publisher:IEEE
Description:Wind turbines have played a significant role in the transition toward renewable energy sources. Accurately determining the position and motion of the rotor blades has emerged as a crucial feature for advancing their adoption and widespread use. The problem addressed in this paper is the use of a single low-power and cost-effective Inertial Measurement Unit (IMU) mounted on a wind turbine blade for position and motion estimation. Standard attitude algorithms can be used to estimate the position of a sensor relative to the earth’s frame. However, they cannot extract information about additional blade features, such as the pitch angle or the occurrence of flap-wise deflections. This paper establishes a novel framework that facilitates the identification and estimation of dynamic wind turbine angles by defining appropriate reference frames. Experimentally acquired IMU data is used to extract rotation matrices that establish the relationship between reference frames. Experimental results show the possibility of estimating the blade orientation, deflection, and twist with a≈ 1◦ precision, in addition to the relative blade altitude with an error of 5 mm.
Cited by:3
Resources:[PDF] from google.com
:view less
Towards Model Development for Sensor-Based Activity Recognition at the Construction Site
2023
Carla Tettamanti, Marco Giordano, Julia Altheimer, Lukas Linhart, Michele Magno
2023 9th International Workshop on Advances in Sensors and Interfaces (IWASI), 305-310
:read more
Authors:Carla Tettamanti, Marco Giordano, Julia Altheimer, Lukas Linhart, Michele Magno
Publication date:06/08/2023
Journal:2023 9th International Workshop on Advances in Sensors and Interfaces (IWASI)
Pages:305-310
Publisher:IEEE
Description:Digital solutions for the construction industry are promising to improve energy consumption, tool life cycle, tool design, productivity, safety, health, and risk management. In this study we assess the feasibility of using accelerometer data obtained from a low-power Micro-Electro-Mechanical Systems (MEMS) sensor directly placed on the tool, to identify screwdriver tool usage types. We focus on the performance evaluation of several distinct features and machine learning (ML) techniques regarding their accuracy and model size. To establish a comprehensive data set, we first collect data, identify fit-for-purpose usage classes and, subsequently, apply a variety of feature engineering and ML techniques to the established problem. As two distinct usage class groups, we identify, runtime classes (Drilling”, “Screwing” and “Unscrewing”) and the non-runtime classes (“Preparing the Tool “Carrying the Tool “Transportation of …
Cited by:1
:view less
Towards robust and efficient on-board mapping for autonomous miniaturized UAVs
2023
Tommaso Polonelli, Casimir Feldmann, Vlad Niculescu, Hanna Müller, Michele Magno, Luca …
2023 9th International Workshop on Advances in Sensors and Interfaces (IWASI), 9-14
:read more
Authors:Tommaso Polonelli, Casimir Feldmann, Vlad Niculescu, Hanna Müller, Michele Magno, Luca Benini
Publication date:06/08/2023
Journal:2023 9th International Workshop on Advances in Sensors and Interfaces (IWASI)
Pages:9-14
Publisher:IEEE
Description:The demand for autonomous nano-sized Unmanned Aerial Vehicles (UAVs) has risen due to their small size and agility, allowing for flight in cluttered indoor environments. However, their small size also significantly limits the payload as well as the battery size and computational resources. Especially the scarcity of memory poses a significant obstacle to generating high-resolution occupancy maps. This work presents an on-board 2-dimensional occupancy mapping system for centimeter-scale UAVs using a miniature 64-zone Time of Flight sensor. Experimental evaluations on the Crazyflie 2.1 nano-UAV have demonstrated that produced maps feature a resolution of 10 cm at mapping velocities up to 1.5 m/s, while covering an area of maximum 400 m2.
Cited by:3
:view less
Design and evaluation of a lora controlled rugged multisensor unit for induced rockfall experiments
2023
Philipp Mayer, Rabea Rogge, Andrin Caviezel, Jessica Munch, Adrian Ringenbach, Michele …
2023 9th International Workshop on Advances in Sensors and Interfaces (IWASI), 52-57
:read more
Authors:Philipp Mayer, Rabea Rogge, Andrin Caviezel, Jessica Munch, Adrian Ringenbach, Michele Magno, Luca Benini
Publication date:06/08/2023
Journal:2023 9th International Workshop on Advances in Sensors and Interfaces (IWASI)
Pages:52-57
Publisher:IEEE
Description:Climate change accelerates the thaw of permafrost and amplifies precipitation and temperature variations. As a result, rockfalls and landslides might become increasingly severe and frequent hazards in mountainous regions. Simulation tools allow the assessment of the increased risks and the planning of adequate mitigation strategies, but they need to be trained and calibrated on real-world data. This paper presents the design of a tailor-made data logger addressing the sensing requirements in induced rockfall experiments. The robust design aims at data collection at up to 1 kHz and allows the trajectory reconstruction based on the output data of various micromechanical systems sensors (accelerometer, gyroscope, magnetometer, barometer). Its integrated LoRaWAN-based wireless interface ensures userfriendly configuration and provides real-time sensor telemetry at up to 980 bit/s.
Cited by:6
Resources:[PDF] from researchgate.net
:view less
Instrumentation and measurement systems: Aerosense: A wireless, non-intrusive, flexible, and mems-based aerodynamic and acoustic measurement system for operating wind turbines
2023
Tommaso Polonelli, Julien Deparday, Imad Abdallah, Sarah Barber, Eleni Chatzi, Michele …
IEEE Instrumentation & Measurement Magazine 26 (4), 12-18
:read more
Authors:Tommaso Polonelli, Julien Deparday, Imad Abdallah, Sarah Barber, Eleni Chatzi, Michele Magno
Publication date:06/08/2023
Journal:IEEE Instrumentation & Measurement Magazine
Volume:26
Issue:4
Pages:12-18
Publisher:IEEE
Description:Wind energy as a renewable energy source has gained in popularity in recent years as a viable means to replacing fossil fuels [1]. Wind turbines form extremely sophisticated systems, operating under extreme and time-varying loads of polymorphic nature (e.g., wind, waves) and under adverse environments (highly varying temperatures and icing conditions). This implies that beyond the operation of mechanical components such as the gearbox, the robustness and resilience of structural components are of the essence but certainly overlooked so far in terms of monitoring. The operation of wind turbines relies on the use of supervisory control and data acquisition (SCADA) systems for their monitoring and control [2]. These systems typically measure operational quantities in and around the nacelle [3], such as wind speed and direction, generator temperature, as well as the generated power [4], and are provided as …
Cited by:7
Resources:[PDF] from google.com
:view less
Fully automatic gym exercises recording: An IoT solution
2023
Sizhen Bian, Alexander Rupp, Michele Magno
2023 IEEE International Workshop on Metrology for Industry 4.0 & IoT (MetroInd4. 0&IoT)…
:read more
Authors:Sizhen Bian, Alexander Rupp, Michele Magno
Publication date:06/06/2023
Journal:2023 IEEE International Workshop on Metrology for Industry 4.0 & IoT (MetroInd4. 0&IoT)
Pages:310-314
Publisher:IEEE
Description:In recent years, working out in the gym has gotten increasingly more data-focused and many gym enthusiasts are recording their exercises to have a better overview of their historical gym activities and to make a better exercise plan for the future. As a side effect, this recording process has led to a lot of time spent painstakingly operating these apps by plugging in used types of equipment and repetitions. This project aims to automate this process using an Internet of Things (IoT) approach. Specifically, beacons with embedded ultra-low-power inertial measurement units (IMUs) are attached to the types of equipment to recognize the usage and transmit the information to gym-goers and managers. We have created a small ecosystem composed of beacons, a gateway, smartwatches, android/iPhone applications, a firebase cloud server, and a dashboard, all communicating over a mixture of Bluetooth and Wifi to …
Cited by:6
Resources:[PDF] from arxiv.org
:view less
Angle of arrival and centimeter distance estimation on a smart UWB sensor node
2023
Tobias Margiani, Silvano Cortesi, Milena Keller, Christian Vogt, Tommaso Polonelli, Mic…
IEEE Transactions on Instrumentation and Measurement 72, 1-10
:read more
Authors:Tobias Margiani, Silvano Cortesi, Milena Keller, Christian Vogt, Tommaso Polonelli, Michele Magno
Publication date:06/02/2023
Journal:IEEE Transactions on Instrumentation and Measurement
Volume:72
Pages:1-10
Publisher:IEEE
Description:Accurate and low-power indoor localization is becoming more and more of a necessity to empower novel consumer and industrial applications. In this field, the most promising technology is based on UWB modulation; however, current UWB positioning systems do not reach centimeter accuracy in general deployments due to multipath and nonisotropic antennas, still necessitating several fixed anchors to estimate an object’s position in space. This article presents an in-depth study and assessment of angle of arrival (AoA) UWB measurements using a compact, low-power solution integrating a novel commercial module with phase difference of arrival (PDoA) estimation as integrated feature. Results demonstrate the possibility of reaching centimeter distance precision and ang 2.4 average angular accuracy in many operative conditions, e.g., in a ang 90 range around the center. Moreover, integrating the channel …
Cited by:55
Resources:[PDF] from arxiv.org
:view less
Aerosense: A wireless, non-intrusive, flexible, and MEMS-based aerodynamic and acoustic measurement system for operating wind turbines
2023
Tommaso Polonelli, Julien Deparday, Imad Abdallah, Sarah Barber, Eleni Chatzi, Michele …
IEEE Instrum. Meas. Mag. 26 (4), 12-18
:read more
Authors:Tommaso Polonelli, Julien Deparday, Imad Abdallah, Sarah Barber, Eleni Chatzi, Michele Magno
Publication date:06/01/2023
Journal:IEEE Instrum. Meas. Mag.
Volume:26
Issue:4
Pages:12-18
Description:The digital twin exploits this data to infer critical performance quantities in operation, such as the local angle of attack, local airflow condition over airfoil sections, blade surface damage and structural deformation. Critical phenomena, such as wear and performance under extreme loads, can be monitored and deciphered for improving future design and operation. Aerosense enables continuous automatic diagnostics, providing early detection and classification of local blade surface damage or structural deterioration, reducing operating costs and increasing revenue by supporting decisions on operation and maintenance. Finally, acoustic measurements can help improve design and operation to reduce acoustic disturbances. Aerosense advocates the adoption of advanced sensors and electronics for blade monitoring, coupled with a digital twin platform, in support of sustainable and reliable wind energy solutions.
Cited by:1
Resources:[PDF] from juliendeparday.com
:view less
Coverage guaranteed cooperative MIMO formation for underwater MI-assisted acoustic WSNs
2023
Qingyan Ren, Yanjing Sun, Michele Magno
ICC 2023-IEEE International Conference on Communications, 3920-3925
:read more
Authors:Qingyan Ren, Yanjing Sun, Michele Magno
Publication date:05/28/2023
Journal:ICC 2023-IEEE International Conference on Communications
Pages:3920-3925
Publisher:IEEE
Description:Underwater magnetic induction (MI)-assisted acoustic cooperative multiple-input-multiple-output (MIMO) technology enables reliable communication with high throughput over long transmission distances. The combination of such as technology and underwater wireless sensor networks (UWSNs) is initiating a novel underwater Internet of Things (IoT paradigm): underwater MI-assisted acoustic cooperative MIMO WSNs. The MIMO UWSNs meets the requirements of reliable communication networks connecting underwater sensor nodes and remote surface base station (BS) for the next generation of smart ocean applications. The objective of the paper is to obtain the cooperative MIMO formation scheme in these networks for minimizing the nodes' energy consumption, simultaneously ensuring the connectivity of nodes and surface BS, and improving the coverage of networks. This paper proposes a scaly cooperative …
Cited by:2
:view less
Colibriuav: An ultra-fast, energy-efficient neuromorphic edge processing uav-platform with event-based and frame-based cameras
2023
Sizhen Bian, Lukas Schulthess, Georg Rutishauser, Alfio Di Mauro, Luca Benini, Michele …
arXiv preprint arXiv:2305.18371
:read more
Authors:Sizhen Bian, Lukas Schulthess, Georg Rutishauser, Alfio Di Mauro, Luca Benini, Michele Magno
Publication date:05/27/2023
Journal:arXiv preprint arXiv:2305.18371
Description:The interest in dynamic vision sensor (DVS)-powered unmanned aerial vehicles (UAV) is raising, especially due to the microsecond-level reaction time of the bio-inspired event sensor, which increases robustness and reduces latency of the perception tasks compared to a RGB camera. This work presents ColibriUAV, a UAV platform with both frame-based and event-based cameras interfaces for efficient perception and near-sensor processing. The proposed platform is designed around Kraken, a novel low-power RISC-V System on Chip with two hardware accelerators targeting spiking neural networks and deep ternary neural networks.Kraken is capable of efficiently processing both event data from a DVS camera and frame data from an RGB camera. A key feature of Kraken is its integrated, dedicated interface with a DVS camera. This paper benchmarks the end-to-end latency and power efficiency of the neuromorphic and event-based UAV subsystem, demonstrating state-of-the-art event data with a throughput of 7200 frames of events per second and a power consumption of 10.7 si{milliwatt}, which is over 6.6 times faster and a hundred times less power-consuming than the widely-used data reading approach through the USB interface. The overall sensing and processing power consumption is below 50 mW, achieving latency in the milliseconds range, making the platform suitable for low-latency autonomous nano-drones as well.
Cited by:17
Resources:[PDF] from arxiv.org
:view less
Sélection neuromorphique d’objets saillants pour la vision événementielle
2023
Amélie Gruel, Jean Martinet, Michele Magno
ORASIS 2023
:read more
Authors:Amélie Gruel, Jean Martinet, Michele Magno
Publication date:05/22/2023
Journal:ORASIS 2023
Description:L’utilisation combinée de réseaux de neurones à impulsions et de caméras événementielles gagne du terrain dans le domaine de la vision par ordinateur embarquée. Ce travail cherche à optimiser les performances d’un modèle embarqué, l’utilisation de la mémoire, la latence et la consommation d’énergie, en implémentant un modèle neuromorphique de sélection d’objets saillants. Sans aucun entraînement et avec un nombre limité de neurones, l’architecture proposée est capable de détecter différents objets avec un délai de seulement 14ms et les objets filtrés conservent 73% de la performance de classification des données originales. A notre connaissance, il s’ agit du premier modèle neuromorphique capable de sélectionner plusieurs objets d’intérêt simultanément.
Resources:[PDF] from hal.science
:view less
Low-cost smart raven deterrent system with tiny machine learning for smart agriculture
2023
Seonyeong Heo, Nicolas Baumann, Carla Margelisch, Marco Giordano, Michele Magno
2023 IEEE International Instrumentation and Measurement Technology Conference (I2MTC), 1-6
:read more
Authors:Seonyeong Heo, Nicolas Baumann, Carla Margelisch, Marco Giordano, Michele Magno
Publication date:05/22/2023
Journal:2023 IEEE International Instrumentation and Measurement Technology Conference (I2MTC)
Pages:1-6
Publisher:IEEE
Description:Smart farming is a promising application domain for the Internet of Things, which helps farmers to reduce operating costs and increase their profit with automation. Bird or raven deterrence is one example of the potential use of the Internet of Things paradigm leading to smart farming applications. Recently, drone-based approaches have demonstrated efficacy to detect and expel birds that reduce crop yield, but on the other side, those solutions are relatively high-cost options for farmers because they require expensive devices such as desktop-level computers and autonomous drones. This paper proposes a maintenance-free, energy-efficient, and low-cost smart raven deterrent system with edge computing, which runs completely standalone and self-sustainable. In particular, a tiny convolutional neural network has been proposed and optimized for multi-core microcontrollers. To demonstrate the effectiveness of the …
Cited by:6
Resources:[PDF] from github.io
:view less
Tinyissimoyolo: A quantized, low-memory footprint, tinyml object detection network for low power microcontrollers
2023
Julian Moosmann, Marco Giordano, Christian Vogt, Michele Magno
arXiv preprint arXiv:2306.00001
:read more
Authors:Julian Moosmann, Marco Giordano, Christian Vogt, Michele Magno
Publication date:05/22/2023
Journal:arXiv preprint arXiv:2306.00001
Description:This paper introduces a highly flexible, quantized, memory-efficient, and ultra-lightweight object detection network, called TinyissimoYOLO. It aims to enable object detection on microcontrollers in the power domain of milliwatts, with less than 0.5MB memory available for storing convolutional neural network (CNN) weights. The proposed quantized network architecture with 422k parameters, enables real-time object detection on embedded microcontrollers, and it has been evaluated to exploit CNN accelerators. In particular, the proposed network has been deployed on the MAX78000 microcontroller achieving high frame-rate of up to 180fps and an ultra-low energy consumption of only 196{mu}J per inference with an inference efficiency of more than 106 MAC/Cycle. TinyissimoYOLO can be trained for any multi-object detection. However, considering the small network size, adding object detection classes will increase the size and memory consumption of the network, thus object detection with up to 3 classes is demonstrated. Furthermore, the network is trained using quantization-aware training and deployed with 8-bit quantization on different microcontrollers, such as STM32H7A3, STM32L4R9, Apollo4b and on the MAX78000's CNN accelerator. Performance evaluations are presented in this paper.
Cited by:39
Resources:[PDF] from arxiv.org
:view less
A fast and accurate optical flow camera for resource-constrained edge applications
2023
Jonas Kühne, Michele Magno, Luca Benini
arXiv preprint arXiv:2305.13087
:read more
Authors:Jonas Kühne, Michele Magno, Luca Benini
Publication date:05/22/2023
Journal:arXiv preprint arXiv:2305.13087
Description:Optical Flow (OF) is the movement pattern of pixels or edges that is caused in a visual scene by the relative motion between an agent and a scene. OF is used in a wide range of computer vision algorithms and robotics applications. While the calculation of OF is a resource-demanding task in terms of computational load and memory footprint, it needs to be executed at low latency, especially in robotics applications. Therefore, OF estimation is today performed on powerful CPUs or GPUs to satisfy the stringent requirements in terms of execution speed for control and actuation. On-sensor hardware acceleration is a promising approach to enable low latency OF calculations and fast execution even on resource-constrained devices such as nano drones and AR/VR glasses and headsets. This paper analyzes the achievable accuracy, frame rate, and power consumption when using a novel optical flow sensor consisting of a global shutter camera with an Application Specific Integrated Circuit (ASIC) for optical flow computation. The paper characterizes the optical flow sensor in high frame-rate, low-latency settings, with a frame rate of up to 88 fps at the full resolution of 1124 by 1364 pixels and up to 240 fps at a reduced camera resolution of 280 by 336, for both classical camera images and optical flow data.
Cited by:4
Resources:[PDF] from arxiv.org
:view less
Tinybird-ml: An ultra-low power smart sensor node for bird vocalization analysis and syllable classification
2023
Lukas Schulthess, Steven Marty, Matilde Dirodi, Mariana D Rocha, Linus Rüttimann, Richa…
2023 IEEE International Symposium on Circuits and Systems (ISCAS), 1-5
:read more
Authors:Lukas Schulthess, Steven Marty, Matilde Dirodi, Mariana D Rocha, Linus Rüttimann, Richard HR Hahnloser, Michele Magno
Publication date:05/21/2023
Journal:2023 IEEE International Symposium on Circuits and Systems (ISCAS)
Pages:1-5
Publisher:IEEE
Description:Animal vocalisations serve a wide range of vital functions. Although it is possible to record animal vocalisations with external microphones, more insights are gained from miniature sensors mounted directly on animals' backs. We present TinyBird-ML; a wearable sensor node weighing only 1.4 g for acquiring, processing, and wirelessly transmitting acoustic signals to a host system using Bluetooth Low Energy. TinyBird-ML embeds low-latency tiny machine learning algorithms for song syllable classification. To optimize battery lifetime of TinyBird-ML during fault-tolerant continuous recordings, we present an efficient firmware and hardware design. We make use of standard lossy compression schemes to reduce the amount of data sent over the Bluetooth antenna, which increases battery lifetime by 70% without negative impact on offline sound analysis. Furthermore, by not transmitting signals during silent periods, we …
Cited by:12
Resources:[PDF] from arxiv.org
:view less
Colibries: A milliwatts risc-v based embedded system leveraging neuromorphic and neural networks hardware accelerators for low-latency closed-loop control applications
2023
Georg Rutishauser, Robin Hunziker, Alfio Di Mauro, Sizhen Bian, Luca Benini, Michele Magno
2023 IEEE International Symposium on Circuits and Systems (ISCAS), 1-5
:read more
Authors:Georg Rutishauser, Robin Hunziker, Alfio Di Mauro, Sizhen Bian, Luca Benini, Michele Magno
Publication date:05/21/2023
Journal:2023 IEEE International Symposium on Circuits and Systems (ISCAS)
Pages:1-5
Publisher:IEEE
Description:End-to-end event-based computation has the poten-tial to push the envelope in latency and energy efficiency for edge AI applications. Unfortunately, event-based sensors (e.g., DVS cameras) and neuromorphic spike-based processors (e.g., Loihi) have been designed in a decoupled fashion, thereby missing major streamlining opportunities. This paper presents ColibriES, the first-ever neuromorphic hardware embedded system plat-form with dedicated event-sensor interfaces and full processing pipelines. ColibriES includes event and frame interfaces and data processing, aiming at efficient and long-life embedded systems in edge scenarios. ColibriES is based on the Kraken system-on-chip and contains a heterogeneous parallel ultra-low power (PULP) processor, frame-based and event-based camera interfaces, and two hardware accelerators for the computation of both event-based spiking neural networks and …
Cited by:11
Resources:[PDF] from arxiv.org
:view less
Nonlinear and machine learning analyses on high-density EEG data of math experts and novices
2023
Hanna Poikonen, Tomasz Zaluska, Xiaying Wang, Michele Magno, Manu Kapur
Scientific Reports 13 (1), 8012
:read more
Authors:Hanna Poikonen, Tomasz Zaluska, Xiaying Wang, Michele Magno, Manu Kapur
Publication date:05/17/2023
Journal:Scientific Reports
Volume:13
Issue:1
Pages:8012
Publisher:Nature Publishing Group UK
Description:Current trend in neurosciences is to use naturalistic stimuli, such as cinema, class-room biology or video gaming, aiming to understand the brain functions during ecologically valid conditions. Naturalistic stimuli recruit complex and overlapping cognitive, emotional and sensory brain processes. Brain oscillations form underlying mechanisms for such processes, and further, these processes can be modified by expertise. Human cortical functions are often analyzed with linear methods despite brain as a biological system is highly nonlinear. This study applies a relatively robust nonlinear method, Higuchi fractal dimension (HFD), to classify cortical functions of math experts and novices when they solve long and complex math demonstrations in an EEG laboratory. Brain imaging data, which is collected over a long time span during naturalistic stimuli, enables the application of data-driven analyses. Therefore, we also …
Cited by:9
Resources:[HTML] from nature.com
:view less
A Human Body Power Transfer System to Enable Battery-Less Sensor Nodes
2023
Rabea Rogge, Lukas Schulthess, Christian Vogt, Michele Magno
Proceedings of the 8th ACM/IEEE Conference on Internet of Things Design and Implementat…
:read more
Authors:Rabea Rogge, Lukas Schulthess, Christian Vogt, Michele Magno
Publication date:05/09/2023
Journal:Proceedings of the 8th ACM/IEEE Conference on Internet of Things Design and Implementation
Pages:456-457
Description: New wearable technologies come with high requirements for miniaturization and flexibility, which are usually restricted by rigid batteries. Capacitive power transfer and communication, employing the human body as a conductive medium enables energy-efficient communication and even the possibility to achieve battery-less wearable sensors distributed on the body. This work presents as a proof-of-concept a complete system consisting of a custom-designed on-body transmitter and battery-less receiver and evaluates the power transmitted and the range achieved. We demonstrate the applicability of our prototype to a real-life scenario as a glucose level tracker even in realistic non-perfect grounding conditions. The realized design offers a power transmission of up to 2.5 mW at distances of 15 cm and at 125 cm, showing the possibility of battery-less on-body edge computing applications.
:view less
A lora-based energy-efficient sensing system for urban computing
2023
Lukas Schulthess, Tiago Salzmann, Christian Vogt, Michele Magno
Proceedings of the 8th ACM/IEEE Conference on Internet of Things Design and Implementat…
:read more
Authors:Lukas Schulthess, Tiago Salzmann, Christian Vogt, Michele Magno
Publication date:05/09/2023
Journal:Proceedings of the 8th ACM/IEEE Conference on Internet of Things Design and Implementation
Pages:481-482
Description: Public space architecture requires reliable data to optimize city resources and enhance their attractiveness. The feedback on acceptance of these changes by the population currently relies on subjective questionnaires or objective but cost-intensive observations, mobile data usage, or video surveillance, which does not preserve privacy. To collect data on public square utilization and usage anonymously for urban computing, this work presents a low-cost, low-power, and privacy-preserving sensing system based on low-power sensor nodes. It is capable of tracking the usage of public chairs in squares and parks by monitoring environmental noise, chair utilization, chair position, temperature, and humidity while keeping maintenance costs low. The final sensing system’s robust operation is proven by field tests at two public squares in a city, providing real-time measurements over a city-wide LoRaWAN network. The …
Cited by:1
:view less
Battery-free and passive wake-up receiver for underwater communication
2023
Lukas Schulthess, Philipp Mayer, Michele Magno
Proceedings of the 8th ACM/IEEE Conference on Internet of Things Design and Implementat…
:read more
Authors:Lukas Schulthess, Philipp Mayer, Michele Magno
Publication date:05/09/2023
Journal:Proceedings of the 8th ACM/IEEE Conference on Internet of Things Design and Implementation
Pages:479-480
Description: Underwater Wireless Networks (UWNs), together with Underwater Wireless Sensor Nodes (UWSNs), are key enablers for various underwater activities in the fields of research, surveillance, rescue, and even military usage. In order to fulfill their mission in remote areas and harsh environments, UWSNs must meet high standards. Since the deployment of such a device is very costly and labor extensive, a long lifetime, high reliability, as well as no maintenance, are highly desirable. However, to achieve this goal, the overall power consumption of a UWSN needs to be reduced. By combining energy harvesting capabilities with a power-efficient wake-up circuit, the constant power drain in idle state can be heavily reduced, and even prevented. This paper presents a maintenance free and energy-neutral wake-up receiver for underwater communication that targets the challenge of the energy limitations of underwater …
Cited by:3
Resources:[PDF] from researchgate.net
:view less
Contactless Vital Sign Monitoring using Low-Power FMCW Radar
2023
Steven Marty, Kanika Dheman, Michele Magno
Proceedings of the 8th ACM/IEEE Conference on Internet of Things Design and Implementat…
:read more
Authors:Steven Marty, Kanika Dheman, Michele Magno
Publication date:05/09/2023
Journal:Proceedings of the 8th ACM/IEEE Conference on Internet of Things Design and Implementation
Pages:461-463
Description: Non-contact vital sign monitoring has several advantages over conventional methods, such as comfort, unobtrusiveness, and a reduced risk of infection transmission. Low-power millimeter-wave (mmWave) radars offer a promising solution for contactless vital sign measurement in embedded, battery-operated devices. Reduced power of these sensor systems leads to challenges associated with precise and reliable vital sign monitoring, particularly with regard to heart rate (HR) measurement. This work investigates adaptations of standard signal processing steps to extract HR and respiration rate (RR) from the raw data of a Frequency Modulated Continuous Wave (FMCW) radar signal suitable for low-power operation. By using less than 100 kB of RAM it could fit into a typical Bluetooth low-energy module. Additionally, we evaluate the performance of our algorithms on 10 people including different body types …
:view less
In-ear-voice: Towards milli-watt audio enhancement with bone-conduction microphones for in-ear sensing platforms
2023
Philipp Schilk, Niccolò Polvani, Andrea Ronco, Milos Cernak, Michele Magno
Proceedings of the 8th ACM/IEEE Conference on Internet of Things Design and Implementat…
:read more
Authors:Philipp Schilk, Niccolò Polvani, Andrea Ronco, Milos Cernak, Michele Magno
Publication date:05/09/2023
Journal:Proceedings of the 8th ACM/IEEE Conference on Internet of Things Design and Implementation
Pages:1-12
Description: The recent ubiquitous adoption of remote conferencing has been accompanied by omnipresent frustration with distorted or otherwise unclear voice communication. Audio enhancement can compensate for low-quality input signals from, for example, small true wireless earbuds, by applying noise suppression techniques. Such processing relies on voice activity detection (VAD) with low latency and the added capability of discriminating the wearer’s voice from others - a task of significant computational complexity. The tight energy budget of devices as small as modern earphones, however, requires any system attempting to tackle this problem to do so with minimal power and processing overhead, while not relying on speaker-specific voice samples and training due to usability concerns. This paper presents the design and implementation of a custom research platform for low-power wireless earbuds based on novel …
Cited by:16
Resources:[PDF] from arxiv.org
:view less
Toward the future generation of railway localization exploiting RTK and GNSS
2023
Denis Mikhaylov, Carla Amatetti, Tommaso Polonelli, Enea Masina, Riccardo Campana, Kai …
IEEE Transactions on Instrumentation and Measurement 72, 1-10
:read more
Authors:Denis Mikhaylov, Carla Amatetti, Tommaso Polonelli, Enea Masina, Riccardo Campana, Kai Berszin, Charles Moatti, Davide Amato, Alessandro Vanelli-Coralli, Michele Magno, Luca Benini
Publication date:05/02/2023
Journal:IEEE Transactions on Instrumentation and Measurement
Volume:72
Pages:1-10
Publisher:IEEE
Description:Smart sensors have become pervasive in railway transportation applications, particularly in Europe where digital technologies are increasingly being applied to the railway signaling field. In the future, safety-critical track-side train detection equipment, such as track circuits and axle counters, will be eliminated in favor of an accurate position estimate supplied by the train. However, the best approach to calculate an accurate position estimate remains an open research question, especially due to the high availability and reliability required. This article describes two static experiments performed with a global navigation satellite system (GNSS) module, which demonstrate that the real-world accuracy achievable with GNSS and real time kinematic (RTK) alone is not sufficient for safety-critical applications, meaning further complementary sensors are required. Furthermore, a custom sensor node containing a GNSS …
Cited by:18
Resources:[PDF] from unibo.it
:view less
Efficient inference with model cascades
2023
Luzian Lebovitz, Lukas Cavigelli, Michele Magno, Lorenz K Muller
Transactions on Machine Learning Research
:read more
Authors:Luzian Lebovitz, Lukas Cavigelli, Michele Magno, Lorenz K Muller
Publication date:05/01/2023
Journal:Transactions on Machine Learning Research
Description:State-of-the-art deep learning models are becoming ever larger. However, many practical applications are constrained by the cost of inference. Cascades of pretrained models with conditional execution address these requirements based on the intuition that some inputs are easy enough that they can be processed correctly by a smaller model allowing for an early exit. If the smaller model is not sufficiently confident in its prediction, the input is passed on to a larger model. The selection of the confidence threshold allows to trade off computational cost against accuracy. In this work we explore the effective design of model cascades, thoroughly evaluate the impact on the accuracy-efficiency trade-off, and provide a reproducible state-of-the-art baseline that is currently missing for related research. We demonstrate that model cascades dominate the ImageNet Pareto front already with 2-model cascades, achieving an average reduction in compute effort at equal accuracy of almost 3.1x above 86% and more than 1.9x between 80% and 86% top-1 accuracy, while 3-model cascades achieve 4.4x above 87% accuracy. We confirm wider applicability and effectiveness of the method on the GLUE benchmark. We release the code to reproduce our experiments in the supplementary material and use only publicly available pretrained models and datasets.
Cited by:11
Resources:[PDF] from openreview.net
:view less
Fully on-board low-power localization with multizone time-of-flight sensors on nano-uavs
2023
Hanna Müller, Nicky Zimmerman, Tommaso Polonelli, Michele Magno, Jens Behley, Cyrill St…
2023 Design, Automation & Test in Europe Conference & Exhibition (DATE), 1-6
:read more
Authors:Hanna Müller, Nicky Zimmerman, Tommaso Polonelli, Michele Magno, Jens Behley, Cyrill Stachniss, Luca Benini
Publication date:04/17/2023
Journal:2023 Design, Automation & Test in Europe Conference & Exhibition (DATE)
Pages:1-6
Publisher:IEEE
Description:Nano-size unmanned aerial vehicles (UAVs) hold enormous potential to perform autonomous operations in complex environments, such as inspection, monitoring or data collection. Moreover, their small size allows safe operation close to humans and agile flight. An important part of autonomous flight is localization, a computationally intensive task, especially on a nano-UAV that usually has strong constraints in sensing, processing and memory. This work presents a real-time localization approach with low-element-count multizone range sensors for resource-constrained nano-UAVs. The proposed approach is based on a novel miniature 64-zone time-of-flight sensor from STMicroelectronics and a RISC-V-based parallel ultra-low-power processor to enable accurate and low latency Monte Carlo Localization on-board. Experimental evaluation using a nano-UAV open platform demonstrated that the proposed …
Cited by:7
Resources:[PDF] from arxiv.org
:view less
3D Hand Tracking with Induced Magnetic Field
2023
Sizhen Bian, Bo Zhou, Paul Lukowicz, Mengxi Liu, Michele Magno, Kexuan Guo
2023 IEEE International Conference on Pervasive Computing and Communications Workshops …
:read more
Authors:Sizhen Bian, Bo Zhou, Paul Lukowicz, Mengxi Liu, Michele Magno, Kexuan Guo
Publication date:03/13/2023
Journal:2023 IEEE International Conference on Pervasive Computing and Communications Workshops and other Affiliated Events (PerCom Workshops)
Pages:589-594
Publisher:IEEE
Description:Sensor-based 3D hand tracking is still challenging despite the massive exploration of different sensing modalities in the past decades. This work describes the design, implementation, and evaluation of a novel induced magnetic field-based 3D hand tracking system, aiming to address the shortcomings of existing approaches and supply an alternative solution. The system is composed of transmitters for magnetic field generation, a wrist-worn receiver for field strength sensing, and Zigbee units for synchronization. In more detail, the transmitters generate the oscillating magnetic fields with a registered sequence, the receiver coil senses the strength of the induced magnetic field by a customized three axes orthogonal coil, which is configured as the LC oscillator with the same oscillating frequency so that an induced current shows up when the receiver is located in the field of the generated magnetic field. Five scenarios …
Cited by:2
:view less
Comparison between an rssi-and an mcpd-based ble indoor localization system
2023
Silvano Cortesi, Christian Vogt, Michele Magno
Computers 12 (3), 59
:read more
Authors:Silvano Cortesi, Christian Vogt, Michele Magno
Publication date:03/10/2023
Journal:Computers
Volume:12
Issue:3
Pages:59
Publisher:MDPI
Description:IPS is a crucial technology that enables medical staff and hospital management to accurately locate and track persons or assets inside medical buildings. Among other technologies, readily available BLE can be exploited to achieve an energy-efficient and low-cost solution. This work presents the design, implementation and comparison of a RSSI-based and a MCPD-based indoor localization system. The implementation is based on a lightweight wkNN algorithm that processes RSSI and MCPD distance data from connection-less BLE Beacons. The designed hardware and firmware are implemented around the state-of-the-art SoC for BLE, the nRF5340 from Nordic Semiconductor. Experimental evaluation with real-time data processing has been evaluated and presented in a 7.3 m × 8.9 m room with furniture and six beacon nodes. The experimental results on randomly chosen validation points within the room show an average error of only 0.50 m for the MCPD approach, whereas the RSSI approach achieved an error of 1.39 m.
Cited by:12
Resources:[HTML] from mdpi.com
:view less
ColibriUAV: Towards an Ultra-Fast, Energy-Efficient Neuromorphic edge-processing platform UAV with Event-Based and Frame-Based Cameras
2023
Sizhen Bian, Lukas Schulthess, Georg Rutishauser, Alfio Di Mauro, Luca Benini, Michele …
:read more
Authors:Sizhen Bian, Lukas Schulthess, Georg Rutishauser, Alfio Di Mauro, Luca Benini, Michele Magno
Publication date:01/01/2023
Description:The interest in dynamic vision sensor (DVS)-powered unmanned aerial vehicles (UAV) is raising, especially due to the microsecond-level reaction time of the bio-inspired event sensor, which increases robustness and reduces latency of the perception tasks compared with a RGB camera. This work presents ColibriUAV, a UAV platform with both frame-based and event-based cameras interfaces for efficient vision data perception and near-sensor processing. The proposed platform is designed around Kraken, a novel low-power RISC-V System on Chip with two hardware accelerators targeting spiking neural networks and deep ternary neural networks. Kraken is capable of efficient processing of both event data from a DVS camera and frame data from a RGB camera. A key feature of Kraken is the integrated dedicated interface with DVS camera. This paper benchmarks the latency and power efficiency of an end-to-end neuromorphic and event-based UAV subsystem demonstrating a state-of-art event data reading performance with 7200 frames of events per second throughput and 10.7 mW power consumption, which is over 6.6 times faster and a hundred times less power than the widely used data reading approach through the USB interface. The overall sensing and processing power consumption is below 50mW achieving latency in the milliseconds range, making the platform suitable also for low latency autonomous nano-drones.
Resources:[PDF] from researchgate.net
:view less
Energy-Efficient Embedded Systems: Pioneering Intelligence at the Edge for Sustainable Wearable Devices
2023
Michele Magno
:read more
Authors:Michele Magno
Publication date:01/01/2023
Publisher:ETH Zurich
Description:Energy-Efficient Embedded Systems: Pioneering Intelligence at the Edge for Sustainable Wearable Devices - Research Collection Header Upper Right Menu Log in de jump to https://www.ethz.ch Research Collection Toggle navigation Upper Right Menu Login Help Help Language Deutsch Toggle navigation Search View Item Home Theses Habilitation Thesis View Item Home Theses Habilitation Thesis View Item Research Collection Navigational link Search Energy-Efficient Embedded Systems: Pioneering Intelligence at the Edge for Sustainable Wearable Devices Mendeley CSV RIS BibTeX Download Full text (PDF, 37.14Mb) Thumbnail Closed access Author Magno, Michele cc Date 2023-11 Type Habilitation Thesis ETH Bibliography yes Altmetrics Download Full text (PDF, 37.14Mb) Publication status published Publisher ETH Zurich Organisational unit 01225 - D-ITET Zentr. f. projektbasiertes Lernen / D-ITET …
:view less
Considerations when Automating the Assessment and Guidance of Project Work
2023
Victoria Abou-Khalil, Andrew Vargo, Rwitajit Majumdar, Michele Magno, Manu Kapur
learning 6, 7
:read more
Authors:Victoria Abou-Khalil, Andrew Vargo, Rwitajit Majumdar, Michele Magno, Manu Kapur
Publication date:01/01/2023
Journal:learning
Volume:6
Pages:7
Description:In this report, we summarize the discussions that took place during the workshop on Automated Assessment and Guidance of Project Work at AIED 2023 in Tokyo, Japan. The workshop organizers and participants discussed the critical considerations and challenges in automating assessment and guidance for Project-Based Learning (PBL).
Resources:[PDF] from ceur-ws.org
:view less
Aerosense: a self-sustainable and long-range bluetooth wireless sensor node for aerodynamic and aeroacoustic monitoring on wind turbines
2022
Tommaso Polonelli, Hanna Müller, Weikang Kong, Raphael Fischer, Luca Benini, Michele Ma…
IEEE Sensors Journal 23 (1), 715-723
:read more
Authors:Tommaso Polonelli, Hanna Müller, Weikang Kong, Raphael Fischer, Luca Benini, Michele Magno
Publication date:12/01/2022
Journal:IEEE Sensors Journal
Volume:23
Issue:1
Pages:715-723
Publisher:IEEE
Description:This article presents a low-power, self-sustainable, and modular wireless sensor node for aerod- ynamic and acoustic measurements on wind turbines and other industrial structures. It includes 40 high-accuracy barometers, ten microphones, and five differential pressure sensors and implements a lossy and a lossless on-board data compression algorithm to decrease the transmission energy cost. The wireless transmitter is based on Bluetooth Low Energy 5.1 (BLE) tuned for long range and high throu- ghput while maintaining adequate per-bit energy efficiency (80 nJ). Moreover, we field-assessed the node capability to collect precise and accurate aerodynamic data. Outdoor experimental tests revealed that the system can acquire and sustain a data rate of 850 kb over 438 m. The power consumption while collecting and streaming all the measured data is 120 mW, enabling self-sustainability and long-term in …
Cited by:31
Resources:[PDF] from arxiv.org
:view less
Model-based design for self-sustainable sensor nodes
2022
Philipp Mayer, Michele Magno, Luca Benini
Energy Conversion and Management 272, 116335
:read more
Authors:Philipp Mayer, Michele Magno, Luca Benini
Publication date:11/15/2022
Journal:Energy Conversion and Management
Volume:272
Pages:116335
Publisher:Pergamon
Description:Long-term and maintenance-free operation is a critical feature for large-scale deployed battery-operated sensor nodes. Energy harvesting (EH) is the most promising technology to overcome the energy bottleneck of today’s sensors and to enable the vision of perpetual operation. However, relying on fluctuating environmental energy requires an application-specific analysis of the energy statistics combined with an in-depth characterization of circuits and algorithms, making design and verification complex. This article presents a model-based design (MBD) approach for EH-enabled devices accounting for the dynamic behavior of components in the power generation, conversion, storage, and discharge paths. The extension of existing compact models combined with data-driven statistical modeling of harvesting circuits allows accurate offline analysis, verification, and validation. The presented approach facilitates …
Cited by:9
Resources:[HTML] from sciencedirect.com
:view less
Realtime hand-gesture recognition based on novel charge variation sensor and IMU
2022
Elio Reinschmidt, Christian Vogt, Michele Magno
2022 IEEE Sensors, 1-4
:read more
Authors:Elio Reinschmidt, Christian Vogt, Michele Magno
Publication date:10/30/2022
Journal:2022 IEEE Sensors
Pages:1-4
Publisher:IEEE
Description:Wearable hand gesture devices are of growing interest to enhance human-machine interfaces as well as digital communication between humans. Although many solutions have been proposed using various sensing technologies, the development of a truly wearable, low power, reliable and unobtrusive device is still a challenge. This work proposes a new device based on a combination of a novel electrostatic sensing circuit fused with a six degree of freedom Inertial Measurement Unit (IMU), to achieve a wearable bracelet capable of active gesture detection for over 11 hours on one battery charge. Due to the proposed tiny machine learning model, gestures are detected in real time by an onboard ARM Cortex M33 microcontroller with an accuracy of up to 87%. The IMU gesture recognition is enhanced by the electrostatic sensing bracelet, increasing accuracy by more than 10% with respect to IMU only estimations.
Cited by:11
:view less
A Low Power Infrared Sensor for Direction, Speed, Distance Finding for Contextual Intelligence
2022
Tiago Salzmann, Michele Magno
2022 IEEE Sensors, 1-4
:read more
Authors:Tiago Salzmann, Michele Magno
Publication date:10/30/2022
Journal:2022 IEEE Sensors
Pages:1-4
Publisher:IEEE
Description:This paper presents a device capable of context awareness exploiting novel ultra-low power thermal infrared sensors (TMOS) from STMicroelectronics. We propose a new method using a single infrared sensor to estimate distance, speed and direction of movement with an accuracy of up to 98.36%. We also propose a lightweight algorithm optimized for working on hardware constrained systems such as a microcontroller, reaching high accuracy detection at very low power values. The TMOS sensor averages at 58.9µW at a 8Hz sampling frequency, showing superior performance compared to more popular pyroelectric sensors when considering the number of sensors used and the corresponding estimation scores. The paper shows a full set of characterization and experimental results to show the benefits of the proposed method.
Cited by:6
:view less
Machine learning in-sensors: Computation-enabled intelligent sensors for next generation of iot
2022
Andrea Ronco, Lukas Schulthess, David Zehnder, Michele Magno
2022 IEEE sensors, 01-04
:read more
Authors:Andrea Ronco, Lukas Schulthess, David Zehnder, Michele Magno
Publication date:10/30/2022
Journal:2022 IEEE sensors
Pages:01-04
Publisher:IEEE
Description:Smart sensors are an emerging technology that allows combining the data acquisition with the elaboration directly on the Edge device, very close to the sensors. To push this concept to the extreme, technology companies are proposing a new generation of sensors allowing to move the intelligence from the edge host device, typically a microcontroller, directly to the ultra-low-power sensor itself, in order to further reduce the miniaturization, cost and energy efficiency. This paper evaluates the capabilities of a novel and promising solution from STMicroelectronics. The presence of a floating point unit and an accelerator for binary neural networks provide capabilities for in-sensor feature extraction and machine learning. We propose a comparison of full-precision and binary neural networks for activity recognition with accelerometer data generated by the sensor itself. Experimental results have demonstrated that the …
Cited by:14
Resources:[PDF] from arxiv.org
:view less
RF power transmission for self-sustaining miniaturized IoT devices
2022
Lukas Schulthess, Federico Villani, Philipp Mayer, Michele Magno
2022 29th IEEE International Conference on Electronics, Circuits and Systems (ICECS), 1-4
:read more
Authors:Lukas Schulthess, Federico Villani, Philipp Mayer, Michele Magno
Publication date:10/24/2022
Journal:2022 29th IEEE International Conference on Electronics, Circuits and Systems (ICECS)
Pages:1-4
Publisher:IEEE
Description:Radio Frequency (RF) wireless power transfer is a promising technology that has the potential to constantly power small Internet of Things (IoT) devices, enabling even battery-less systems and reducing their maintenance requirements. However, to achieve this ambitious goal, carefully designed RF energy harvesting (EH) systems are needed to minimize the conversion losses and the conversion efficiency of the limited power. For intelligent internet of things sensors and devices, which often have non-constant power requirements, an additional power management stage with energy storage is needed to temporarily provide a higher power output than the power being harvested. This paper proposes an RF wireless power energy conversion system for miniaturized IoT composed of an impedance matching network, a rectifier, and power management with energy storage. The proposed sub-system has been …
Cited by:9
Resources:[PDF] from arxiv.org
:view less
Predictive energy-aware adaptive sampling with deep reinforcement learning
2022
Seonyeong Heo, Philipp Mayer, Michele Magno
2022 29th IEEE International Conference on Electronics, Circuits and Systems (ICECS), 1-4
:read more
Authors:Seonyeong Heo, Philipp Mayer, Michele Magno
Publication date:10/24/2022
Journal:2022 29th IEEE International Conference on Electronics, Circuits and Systems (ICECS)
Pages:1-4
Publisher:IEEE
Description:Energy harvesting can enable wireless smart sensors to be self-sustainable by allowing them to gather energy from the environment. However, since the energy availability changes dynamically depending on the environment, it is difficult to find an optimal energy management strategy at design time. One existing approach to reflecting dynamic energy availability is energy-aware adaptive sampling, which changes the sampling rate of a sensor according to the energy state. This work proposes deep reinforcement learning-based predictive adaptive sampling for a wireless sensor node. The proposed approach applies deep reinforcement learning to find an effective adaptive sampling strategy based on the harvesting power and energy level. In addition, the proposed approach enables predictive adaptive sampling by designing adaptive sampling models that consider the trend of energy state. The evaluation results …
Cited by:4
Resources:[PDF] from ethz.ch
:view less
Exploring automatic gym workouts recognition locally on wearable resource-constrained devices
2022
Sizhen Bian, Xiaying Wang, Tommaso Polonelli, Michele Magno
2022 IEEE 13th International Green and Sustainable Computing Conference (IGSC), 1-6
:read more
Authors:Sizhen Bian, Xiaying Wang, Tommaso Polonelli, Michele Magno
Publication date:10/24/2022
Journal:2022 IEEE 13th International Green and Sustainable Computing Conference (IGSC)
Pages:1-6
Publisher:IEEE
Description:Automatic gym activity recognition on energy-and resource-constrained wearable devices removes the human-interaction requirement during intense gym sessions - like soft-touch tapping and swiping. This work presents a tiny and highly accurate residual convolutional neural network that runs in milliwatt microcontrollers for automatic workouts classification. We evaluated the inference performance of the deep model with quantization on three resource-constrained devices: two microcontrollers with ARM-Cortex M4 and M7 core from ST Microelectronics, and a GAP8 system on chip, which is an open-sourced, multi-core RISC-V computing platform from Green-Waves Technologies. Experimental results show an accuracy of up to 90.4% for eleven workouts recognition with full precision inference. The paper also presents the trade-off performance of the resource-constrained system. While keeping the recognition …
Cited by:19
Resources:[PDF] from arxiv.org
:view less
Cardiac monitoring with novel low power sensors measuring upper thoracic electrostatic charge variation for long lasting wearable devices
2022
Kanika Dheman, David Werder, Michele Magno
2022 18th International Conference on Wireless and Mobile Computing, Networking and Com…
:read more
Authors:Kanika Dheman, David Werder, Michele Magno
Publication date:10/10/2022
Journal:2022 18th International Conference on Wireless and Mobile Computing, Networking and Communications (WiMob)
Pages:154-159
Publisher:IEEE
Description:Cardiovascular disease is a major cause of premature mortality, high healthcare costs, and disability-adjusted life years. Digital interventions such as continuous cardiac monitoring solutions can help to monitor the patient status and provide valuable feedback to clinicians to detect early warning signs and provide effective interventions. This paper presents the evaluation of a novel low-power sensor exploited to measure the electrostatic charge variation in the upper thorax to provide an energy-efficient and accurate detection of the electric activity of the heart. The sensor is investigated for measuring the heart activity in terms of the QRS complex. The paper presents the design of a wearable sensor device, optimization of electrode positions and incorporation into a wearable chest strap that can be integrated seamlessly under clothes. Due to the low power consumption of the sensor, the sensor node consumes only …
Cited by:7
:view less
Widevision: A low-power, multi-protocol wireless vision platform for distributed surveillance
2022
Moritz Scherer, Fabian Sidler, Michael Rogenmoser, Michele Magno, Luca Benini
2022 18th International Conference on Wireless and Mobile Computing, Networking and Com…
:read more
Authors:Moritz Scherer, Fabian Sidler, Michael Rogenmoser, Michele Magno, Luca Benini
Publication date:10/10/2022
Journal:2022 18th International Conference on Wireless and Mobile Computing, Networking and Communications (WiMob)
Pages:394-399
Publisher:IEEE
Description:The trend in Internet of Things research points toward performing increasingly compute-intensive data analysis tasks on embedded sensor nodes, rather than server centers. Ex-ploiting the technological advances in both energy efficiency, and Tiny Machine Learning algorithms and methods, an increasing number of recognition and classification tasks can be performed by small, low-power, wireless sensor nodes. This paper presents Wide Vision, a wireless, wide-area sensing platform capable of performing on-board person detection with power requirements in the mW range. The WideVision platform integrates seamlessly into the Internet of Things, by coupling a dedicated multi-radio platform, including a LoRa interface, enabling medium-and long-range communication, with a novel parallel RISC- V microcontroller. We evaluate the proposed platform with the GAP8 microcontroller, which includes an 8-core RISC …
Cited by:5
Resources:[PDF] from ethz.ch
:view less
VitalPod: A low power in-ear vital parameter monitoring system
2022
Philipp Schilk, Kanika Dheman, Michele Magno
2022 18th International Conference on Wireless and Mobile Computing, Networking and Com…
:read more
Authors:Philipp Schilk, Kanika Dheman, Michele Magno
Publication date:10/10/2022
Journal:2022 18th International Conference on Wireless and Mobile Computing, Networking and Communications (WiMob)
Pages:94-99
Publisher:IEEE
Description:Monitoring of physiological parameters support early detection, prevention, and management of adverse health-care related events. In-ear wearable sensor nodes that track changing bio-physiological signals can be advantageous over traditional monitoring methods in being compact, unobtrusive, and inconspicuous, increasing their appeal. However, in-ear ergonomics place rigid constraints on a device's physical design and size, limiting battery lifetime and restricting the incorporation of multiple sensor modules. This work presents the design and implementation of the wireless hearable VitalPod, an in-ear multi-vital sign monitor that measures heart rate (HR), respiratory rate (RR), blood oxygenation (SpO2), skin temperature and activity. The VitalPod is designed with low power and energy efficiency in mind, using novel sensing integrated circuits and processing modules that achieve operational longevity of up …
Cited by:10
:view less
Enabling Predictive Maintenance on Electric Motors Through a Self-sustainable Wireless Sensor Node
2022
Andrea Bentivogli, Tommaso Polonelli, Michele Magno, Guido Comai
International Conference on Applications in Electronics Pervading Industry, Environment…
:read more
Authors:Andrea Bentivogli, Tommaso Polonelli, Michele Magno, Guido Comai
Publication date:09/26/2022
Journal:International Conference on Applications in Electronics Pervading Industry, Environment and Society
Pages:3-8
Publisher:Springer Nature Switzerland
Description:Periodic maintenance and unpredictable equipment failure of industrial machinery are expensive elements in a company’s balance and potentially hazardous for human operators. Periodic inspections at predefined intervals are commonly applied to limit unplanned production downtime and safety concerns. The latest advancements in smart sensor technology enables online equipment monitoring that can directly anticipate the deterioration and incoming breakages on operating machines, reducing maintenance costs. This paper presents a deploy and forget sensor node for predictive maintenance on industrial electric motors, which targets three-phase asynchronous motors, supporting the data collection from multiple sensors, such as vibrations, environmental noise, temperature, and the external magnetic field. The sensor node features ultra-low-power design, achieving self-sustainability by exploiting a 44 cm …
Cited by:2
:view less
Model-and acceleration-based pursuit controller for high-performance autonomous racing
2022
Jonathan Becker, Nadine Imholz, Luca Schwarzenbach, Edoardo Ghignone, Nicolas Baumann, …
arXiv preprint arXiv:2209.04346
:read more
Authors:Jonathan Becker, Nadine Imholz, Luca Schwarzenbach, Edoardo Ghignone, Nicolas Baumann, Michele Magno
Publication date:09/09/2022
Journal:arXiv preprint arXiv:2209.04346
Description:Autonomous racing is a research field gaining large popularity, as it pushes autonomous driving algorithms to their limits and serves as a catalyst for general autonomous driving. For scaled autonomous racing platforms, the computational constraint and complexity often limit the use of Model Predictive Control (MPC). As a consequence, geometric controllers are the most frequently deployed controllers. They prove to be performant while yielding implementation and operational simplicity. Yet, they inherently lack the incorporation of model dynamics, thus limiting the race car to a velocity domain where tire slip can be neglected. This paper presents Model- and Acceleration-based Pursuit (MAP) a high-performance model-based trajectory tracking algorithm that preserves the simplicity of geometric approaches while leveraging tire dynamics. The proposed algorithm allows accurate tracking of a trajectory at unprecedented velocities compared to State-of-the-Art (SotA) geometric controllers. The MAP controller is experimentally validated and outperforms the reference geometric controller four-fold in terms of lateral tracking error, yielding a tracking error of 0.055m at tested speeds up to 11m/s.
Cited by:44
Resources:[PDF] from arxiv.org
:view less
An open platform for efficient drone-to-sensor wireless ranging and data harvesting
2022
Tommaso Polonelli, Michele Magno, Vlad Niculescu, Luca Benini, David Boyle
Sustainable Computing: Informatics and Systems 35, 100734
:read more
Authors:Tommaso Polonelli, Michele Magno, Vlad Niculescu, Luca Benini, David Boyle
Publication date:09/01/2022
Journal:Sustainable Computing: Informatics and Systems
Volume:35
Pages:100734
Publisher:Elsevier
Description:Drones deployed in combination with wireless sensors can unlock a host of prospective applications in environments that lack infrastructure communications networks and where access may be impossible for human operators. Community building efforts to engage with this opportunity are hampered by a lack of platform support and an evolving understanding of the performance of known wireless communications systems in dynamic outdoor environments, particularly under mobility. This paper proposes and evaluates a new combination of ultra-wide band and wake-up radio technologies. These enable high precision landing and support energy efficient operation. We describe in detail the design and implementation of an open platform making use of the combination of these radios to improve upon ranging, bandwidth and energy efficiency problems that affect drone-wireless sensor systems. Our evaluation …
Cited by:10
Resources:[HTML] from sciencedirect.com
:view less
Neuromorphic edge computing for biomedical applications: Gesture classification using emg signals
2022
Antonio Vitale, Elisa Donati, Roger Germann, Michele Magno
IEEE Sensors Journal 22 (20), 19490-19499
:read more
Authors:Antonio Vitale, Elisa Donati, Roger Germann, Michele Magno
Publication date:08/03/2022
Journal:IEEE Sensors Journal
Volume:22
Issue:20
Pages:19490-19499
Publisher:IEEE
Description:With the emergence of edge-computing platforms, the applications of smart wearable devices are immense. This technology can be incorporated in consumer products such as smartwatches and activity trackers, for continuous health monitoring, as well as for medical applications such as myoelectric prosthetics, to interpret the electric activity in the residual limb and achieve fast and precise control. However, wearable technologies require a lightweight, energy-efficient, and low-latency processing system in order to extend the devices’ autonomy while maintaining a realistic user-feedback interaction. Neuromorphic processing, thanks to its event-based and asynchronous nature, presents ideal characteristics for compact brain-inspired low-power and ultra-fast computing systems that can enable a new generation of wearable devices. This article presents two spiking neural networks (SNNs) for event-based …
Cited by:63
Resources:[PDF] from google.com
:view less
Towards lightweight deep neural network for smart agriculture on embedded systems
2022
Pengwei Du, Tommaso Polonelli, Michele Magno, Zhiyuan Cheng
2022 IEEE Sensors Applications Symposium (SAS), 1-6
:read more
Authors:Pengwei Du, Tommaso Polonelli, Michele Magno, Zhiyuan Cheng
Publication date:08/01/2022
Journal:2022 IEEE Sensors Applications Symposium (SAS)
Pages:1-6
Publisher:IEEE
Description:Agriculture is the pillar industry for human survival. However, various diseases threaten the health of crops and lead to a decrease in yield. Industry 4.0 is making strides in plant illness prevention and detection, other than supporting farmers to improve plantations’ income. To prevent crop diseases in time, this paper proposes, implements, and evaluates a low-power smart camera. It features a lightweight neural network to verify and monitor the growth status of crops. The proposed tiny model features optimized complexity, to be deployed in milliwatt power microcontrollers, and high accuracy. Experimental results show that our work reaches 99% accuracy on a 4-classes dataset and more than 96% for a 10 classes dataset. The compact model size (139 kB) and low complexity enable ultra-low power consumption (2.63 mW per hour) on the battery-powered Sony Spresense platform, which features a six-core ARM …
Cited by:5
:view less
Self-sustainable IoT wireless sensor node for predictive maintenance on electric motors
2022
Tommaso Polonelli, Andrea Bentivogli, Guido Comai, Michele Magno
2022 IEEE Sensors Applications Symposium (SAS), 1-6
:read more
Authors:Tommaso Polonelli, Andrea Bentivogli, Guido Comai, Michele Magno
Publication date:08/01/2022
Journal:2022 IEEE Sensors Applications Symposium (SAS)
Pages:1-6
Publisher:IEEE
Description:Unexpected equipment failure is expensive and potentially hazardous for workers and users. Periodic inspections and maintenance at predefined intervals aim to limit unplanned production downtime, costly replacement of parts and safety concerns. On the other side, predictive maintenance techniques can monitor equipment as it operates, anticipating deterioration and incoming breakages, enabling just-in-time services at reduced operational costs. This paper presents a deploy and forget predictive maintenance sensor node designed explicitly for industrial electric motors. It is targeted for AC mono and three-phase asynchronous motors and generators, measuring vibrations, environmental noise, temperature, and the external magnetic field. The proposed sensor achieves self-sustainability by exploiting a 4x4 cm thermal source for 72 s with a ∆T of 20 °C, and it features short-long wireless data transfer …
Cited by:10
:view less
Towards the future generation of railway localization and signaling exploiting sub-meter RTK GNSS
2022
Carla Amatetti, Tommaso Polonelli, Enea Masina, Charles Moatti, Denis Mikhaylov, Davide…
2022 IEEE Sensors Applications Symposium (SAS), 1-6
:read more
Authors:Carla Amatetti, Tommaso Polonelli, Enea Masina, Charles Moatti, Denis Mikhaylov, Davide Amato, Alessandro Vanelli-Coralli, Michele Magno, Luca Benini
Publication date:08/01/2022
Journal:2022 IEEE Sensors Applications Symposium (SAS)
Pages:1-6
Publisher:IEEE
Description:Internet of Things devices and smart sensors have become increasingly more pervasive in railway transportation applications, where they have the potential to significantly improve reliability, capacity, safety, and to reduce costs. In the ‘smart rail’ concept a key enabler is the ability to accurately localize trains with centimeter precision. This can be achieved using a combination of a high-precision GNSS-based module capable of achieving sub-meter accuracy and emerging radio and sensor technologies. This paper proposes a train tracking sensor node for in-field assessments fusing the absolute localization data from the GNSS and from local reference systems, such as Real Time Kinematics (RTK) with Inertial Measurement Unit (IMU) and Dead Reckoning (DRK). A complete wireless sensor node has been designed and evaluated in the field for functionality and power consumption. Within the sensor node, two …
Cited by:7
:view less
Automatic extraction of muscle fascicle pennation angle from raw ultrasound data
2022
Soley Hafthorsdottir, Sergei Vostrikov, Andrea Cossettini, Michael Rieder, Christoph Le…
2022 IEEE Sensors Applications Symposium (SAS), 1-5
:read more
Authors:Soley Hafthorsdottir, Sergei Vostrikov, Andrea Cossettini, Michael Rieder, Christoph Leitner, Michele Magno, Luca Benini
Publication date:08/01/2022
Journal:2022 IEEE Sensors Applications Symposium (SAS)
Pages:1-5
Publisher:IEEE
Description:Compact, wearable, wireless ultrasound (US) sensing systems are promising devices for the observation of human muscle dynamics, offering low power, non-invasive continuous monitoring of contracting muscles. Plane wave imaging is an ideal imaging modality to meet the high frame rate requirements of fast contracting muscles. However, the low power requirements of wearable wireless US constrain the data transfer rates from the probe to the host computer, and limit the maximum number of transducer channels, at the same time discouraging beamforming on the probe. Therefore, it is crucial to extract physiological parameters directly from raw US data for applications demanding fast imaging speeds (like monitoring muscles and tendons in motion). Machine Learning (ML) methods can be employed to effectively extract such features. Although a few recent works demonstrated A-mode US for motion and force …
Cited by:4
:view less
Performance Comparison between Decawave DW1000 and DW3000 in low-power double side ranging applications
2022
Tommaso Polonelli, Simon Schläpfer, Michele Magno
2022 IEEE Sensors Applications Symposium (SAS), 1-6
:read more
Authors:Tommaso Polonelli, Simon Schläpfer, Michele Magno
Publication date:08/01/2022
Journal:2022 IEEE Sensors Applications Symposium (SAS)
Pages:1-6
Publisher:IEEE
Description:Indoor localization and context-awareness are becoming two of the key technologies for a large variety of applications. Real-time locating systems with centimeter accuracy and low power consumption have recently been made available by employing the Ultra WideBand (UWB) technology. Since 2015, Decawave has produced commercial UWB integrated circuits, exploiting time-of-flight measurement techniques to estimate the distance between two agents. This work presents a performance study between two Decawave transceivers, the DW1000 and the new DW3000 released in 2020. The testing space includes areas under line-of-sight and diverse non-line-of-sight conditions caused by the reflection of the UWB radio signals across various obstacles. Finally, we analyze the power consumption in distinct configurations, comparing the two devices. Results show that the two have similar precision in …
Cited by:24
Resources:[PDF] from ethz.ch
:view less
Survey, analysis and comparison of radar technologies for embedded vital sign monitoring
2022
Marco Giordano, Gamze Islamoglu, Viviane Potocnik, Christian Vogt, Michele Magno
2022 44th Annual International Conference of the IEEE Engineering in Medicine & Biology…
:read more
Authors:Marco Giordano, Gamze Islamoglu, Viviane Potocnik, Christian Vogt, Michele Magno
Publication date:07/11/2022
Journal:2022 44th Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC)
Pages:854-860
Publisher:IEEE
Description:Contactless vital sign monitoring systems are becoming increasing in demand for a wide range of biomedical applications. Millimetre-wave radars and embedded signal processing are the most promising technologies to enable non-contact vital signs monitoring. In this work, the challenging task of heart rate estimation from radar data has been addressed. Three different radar systems from Infineon, Texas Instruments and Acconeer, and four algorithms, FFT, Median-FFT, STFT and Median-STFT, have been analysed and compared against a reference sensor. Accuracy, as well as power figures, have been reported for all the radar systems. A dataset of 16 volunteers has been acquired, yielding a total of 400 minutes of radar-recorded vital sign data. The accuracy of the four investigated algorithms has been reported on average and per subject for every radar. The algorithm exploiting the Short Time Fourier …
Cited by:16
:view less
Tiny tcn model for gesture recognition with multi-point low power tof-sensors
2022
Stephan Boner, Christian Vogt, Michele Magno
2022 IEEE 4th International Conference on Artificial Intelligence Circuits and Systems …
:read more
Authors:Stephan Boner, Christian Vogt, Michele Magno
Publication date:06/13/2022
Journal:2022 IEEE 4th International Conference on Artificial Intelligence Circuits and Systems (AICAS)
Pages:356-359
Publisher:IEEE
Description:Gesture recognition is currently an important field of research, as it provides the basis for the next generation of Human Machine Interface. Especially recognizing gestures with touch-less technology has several advantages including, for example, the possibility of working with gloves either outside or in sterile environments. In this work, we present a tiny machine learning neural network model exploiting a novel, miniaturized and low power Time of flight (ToF)-sensor from STMicroelectronics. The algorithm is based on a combination of temporal convolutional networks and is optimized to work on an embedded small and low power ARM cortex-M4 processor with a few kilo Byte of RAM, as employed in every recent Bluetooth Low Energy module. A dataset has been collected with the ToF sensor for training and evaluation of the proposed algorithm. The model has been evaluated for accuracy and a trade-off between …
Cited by:10
:view less
Real-time low power audio distortion circuit modeling: a tinyml deep learning approach
2022
Davide Plozza, Marco Giordano, Michele Magno
2022 IEEE 4th International Conference on Artificial Intelligence Circuits and Systems …
:read more
Authors:Davide Plozza, Marco Giordano, Michele Magno
Publication date:06/13/2022
Journal:2022 IEEE 4th International Conference on Artificial Intelligence Circuits and Systems (AICAS)
Pages:415-418
Publisher:IEEE
Description:This work proposes a combined approach using deep learning and standard signal conditioning to model analog audio distortion circuits in real-time. The proposed model targets low latency and low power resource-constrained processors, and it is based on a quantized neural network. Pre- and post-processing consisting in filtering and dithering has been applied to improve the performance of the proposed optimized model. The model has been compared with a real-time state-of-art model WaveNet3 running on a modern desktop computer, which we used as performance reference. Our proposed model achieves a parameter size reduction of 8.4x and a neural network multiply-accumulation operations reduction of 5.1x with respect to the WaveNet3, while maintaining comparable performance. The model has been optimized and deployed on the novel MAX78000 microcontroller which features an on-board …
Cited by:2
:view less
Survey and comparison of milliwatts micro controllers for tiny machine learning at the edge
2022
Marco Giordano, Luigi Piccinelli, Michele Magno
2022 IEEE 4th International Conference on Artificial Intelligence Circuits and Systems …
:read more
Authors:Marco Giordano, Luigi Piccinelli, Michele Magno
Publication date:06/13/2022
Journal:2022 IEEE 4th International Conference on Artificial Intelligence Circuits and Systems (AICAS)
Pages:94-97
Publisher:IEEE
Description:Low power Internet of Things devices are growing in number and computational capabilities, pushing to ubiquitous deployment of smart sensors that embed on board both the sensing and the processing. Thus, one of the most emerging requirements of such devices is to provide intelligence in resource-constrained processors that consume few milliwatts of power. This work focuses on surveying, comparing and evaluating seven different recent and popular microcontrollers with a power envelope from a few up to hundreds of milliwatts against a Convolutional Neural Networks workload for a non trivial task such as face recognition. The evaluation reports key points of tiny machine learning performance of the target microcontrollers in terms of inference time, power consumption, energy per inference and computational efficiency. Experimental results highlight best-in-class power consumption for Ambiq Apollo3 and …
Cited by:40
:view less
Neuromorphic event-based spatio-temporal attention using adaptive mechanisms
2022
Amélie Gruel, Antonio Vitale, Jean Martinet, Michele Magno
2022 IEEE 4th international conference on artificial intelligence circuits and systems …
:read more
Authors:Amélie Gruel, Antonio Vitale, Jean Martinet, Michele Magno
Publication date:06/13/2022
Journal:2022 IEEE 4th international conference on artificial intelligence circuits and systems (AICAS)
Pages:379-382
Publisher:IEEE
Description:Contrary to RGB cameras, Dynamic Vision Sensor (DVS) output visual data in the form of an asynchronous events stream by recording pixel-wise luminance changes at microsecond resolution. While conventional computer vision approaches utilise frame-based input data, thus failing to take full advantage of the high temporal resolution, novel approaches use spiking neural networks Spiking Neural Networks (SNNs) which are more compatible to handle event-based data since these bio-inspired neural models intrinsically encode information in a sparse manner using activation spikes trains. This paper presents an attentional mechanism which detects regions with higher event density by using inherent SNN dynamics combined with online weight and threshold adaptation. We implemented the network directly on Intel's research neuromorphic chip Loihi and evaluate our proposed method on the open DVS128 …
Cited by:15
Resources:[PDF] from hal.science
:view less
Parallelizing optical flow estimation on an ultra-low power RISC-V cluster for Nano-UAV navigation
2022
Jonas Kühne, Michele Magno, Luca Benini
2022 IEEE International Symposium on Circuits and Systems (ISCAS), 301-305
:read more
Authors:Jonas Kühne, Michele Magno, Luca Benini
Publication date:05/27/2022
Journal:2022 IEEE International Symposium on Circuits and Systems (ISCAS)
Pages:301-305
Publisher:IEEE
Description:Optical flow estimation is crucial for autonomous navigation and localization of unmanned aerial vehicles (UAV). On micro and nano UAVs, real-time calculation of the optical flow is run on low power and resource-constrained microcontroller units (MCUs). Thus, lightweight algorithms for optical flow have been proposed targeting real-time execution on traditional single-core MCUs. This paper introduces an efficient parallelization strategy for optical flow computation targeting new-generation multicore low power RISC-V based microcontroller units. Our approach enables higher frame rates at lower clock speeds. It has been implemented and evaluated on the eight-core cluster of a commercial octa-core MCU (GAP8) reaching a parallelization speedup factor of 7.21 allowing for a frame rate of 500 frames per second when running on a 50MHz clock frequency. The proposed parallel algorithm significantly boosts the …
Cited by:5
Resources:[PDF] from arxiv.org
:view less
TC-Driver: Trajectory Conditioned Driving for Robust Autonomous Racing–A Reinforcement Learning Approach
2022
Edoardo Ghignone, Nicolas Baumann, Mike Boss, Michele Magno
arXiv preprint arXiv:2205.09370
:read more
Authors:Edoardo Ghignone, Nicolas Baumann, Mike Boss, Michele Magno
Publication date:05/19/2022
Journal:arXiv preprint arXiv:2205.09370
Description:Autonomous racing is becoming popular for academic and industry researchers as a test for general autonomous driving by pushing perception, planning, and control algorithms to their limits. While traditional control methods such as MPC are capable of generating an optimal control sequence at the edge of the vehicles physical controllability, these methods are sensitive to the accuracy of the modeling parameters. This paper presents TC-Driver, a RL approach for robust control in autonomous racing. In particular, the TC-Driver agent is conditioned by a trajectory generated by any arbitrary traditional high-level planner. The proposed TC-Driver addresses the tire parameter modeling inaccuracies by exploiting the heuristic nature of RL while leveraging the reliability of traditional planning methods in a hierarchical control structure. We train the agent under varying tire conditions, allowing it to generalize to different model parameters, aiming to increase the racing capabilities of the system in practice. The proposed RL method outperforms a non-learning-based MPC with a 2.7 lower crash ratio in a model mismatch setting, underlining robustness to parameter discrepancies. In addition, the average RL inference duration is 0.25 ms compared to the average MPC solving time of 11.5 ms, yielding a nearly 40-fold speedup, allowing for complex control deployment in computationally constrained devices. Lastly, we show that the frequently utilized end-to-end RL architecture, as a control policy directly learned from sensory input, is not well suited to model mismatch robustness nor track generalization. Our realistic simulations show that TC-Driver …
Cited by:8
Resources:[PDF] from arxiv.org
:view less
Towards a multi-pixel time-of-flight indoor navigation system for nano-drone applications
2022
Vlad Niculescu, Hanna Müller, Iman Ostovar, Tommaso Polonelli, Michele Magno, Luca Benini
2022 IEEE International Instrumentation and Measurement Technology Conference (I2MTC), 1-6
:read more
Authors:Vlad Niculescu, Hanna Müller, Iman Ostovar, Tommaso Polonelli, Michele Magno, Luca Benini
Publication date:05/16/2022
Journal:2022 IEEE International Instrumentation and Measurement Technology Conference (I2MTC)
Pages:1-6
Publisher:IEEE
Description:Unmanned aerial vehicles (UAVs) have recently attracted the industry’s attention due to their numerous civilian and potential commercial applications. A promising UAV subclass includes nano and micro UAVs, characterized by centimeter size, few grams of payload and extremely limited on-board computational resources. Those features pose major challenges to enable autonomous navigation or even more basic relevant subtasks, such as reliable obstacle avoidance. This paper explores and characterizes a multi-zone Time of Flight (ToF) sensor to enhance autonomous navigation with a significantly lower computational load than most common visual-based solutions. In particular, the state-of-the-art integrated ToF sensor is characterized for the first time in literature in-field using an ad hoc lightweight PCB and the Crazyflie nano-UAV. The paper focuses, on the 8x8 pixel configuration, to detect obstacles up to …
Cited by:24
:view less
Demo abstract: Towards reliable obstacle avoidance for nano-UAVs
2022
Iman Ostovar, Vlad Niculescu, Hanna Müller, Tommaso Polonelli, Michele Magno, Luca Benini
2022 21st ACM/IEEE International Conference on Information Processing in Sensor Network…
:read more
Authors:Iman Ostovar, Vlad Niculescu, Hanna Müller, Tommaso Polonelli, Michele Magno, Luca Benini
Publication date:05/04/2022
Journal:2022 21st ACM/IEEE International Conference on Information Processing in Sensor Networks (IPSN)
Pages:501-502
Publisher:IEEE
Description:Unmanned aerial vehicles (UAVs) are a very active research topic, and especially the nano and micro subclass, characterized by cen-timeter size and minimal on-board computational capabilities, have gained popularity in recent years. These lightweight platforms provide good agility and movement freedom in indoor environments, but it is still a significant challenge to enable autonomous navigation or basic obstacle avoidance capabilities using standard image sensors, due to the limited computational capabilities that can be hosted on-board. This work demonstrates the possibility of using a new multi-zone Time of Flight (ToF) sensor to enhance autonomous navigation with a significantly lower computational load than most common visual-based solutions. Our system proved reliable (>95%) in-field obstacle avoidance capabilities when flying in indoor environments with dynamic obstacles.
Cited by:1
:view less
Aerosense: Long-range bluetooth wireless sensor node for aerodynamic monitoring on wind turbine blades
2022
Tommaso Polonelli, Julien Deparday, Hanna Müller, Raphael Fischer, Luca Benini, Sarah B…
Journal of Physics: Conference Series 2265 (2), 022074
:read more
Authors:Tommaso Polonelli, Julien Deparday, Hanna Müller, Raphael Fischer, Luca Benini, Sarah Barber, Michele Magno
Publication date:05/01/2022
Journal:Journal of Physics: Conference Series
Volume:2265
Issue:2
Pages:022074
Publisher:IOP Publishing
Description:Predictive maintenance and structural health monitoring are challenging and promising research fields today. In particular, cost-effective and long-term monitoring of wind turbines has been proven to be one of the key elements to successfully increase their efficiency. Accurate numerical modeling and real-time control-in-the-loop play an increasingly prominent role in understanding and optimizing blade aerodynamic and acoustic performances. A non-intrusive and modular measurement system is a prerequisite for long-term measurement campaigns in existing and future wind turbines. Current methods of performing aerodynamic and acoustic field measurements are cumbersome and expensive, leading to a shortage of aerodynamic and acoustic datasets on operating wind turbines. This paper demonstrates the ability of the new Aerosense system to operate successfully in the field. Aerosense is a long-lasting …
Cited by:6
Resources:[PDF] from iop.org
:view less
Design and performance evaluation of an ultralow-power smart IoT device with embedded TinyML for asset activity monitoring
2022
Marco Giordano, Nicolas Baumann, Michele Crabolu, Raphael Fischer, Giovanni Bellusci, M…
IEEE Transactions on Instrumentation and Measurement 71, 1-11
:read more
Authors:Marco Giordano, Nicolas Baumann, Michele Crabolu, Raphael Fischer, Giovanni Bellusci, Michele Magno
Publication date:04/15/2022
Journal:IEEE Transactions on Instrumentation and Measurement
Volume:71
Pages:1-11
Publisher:IEEE
Description:This article proposes a proof-of-concept device to continuously assess the usage of handheld power tools and detect construction working tasks (e.g., different drilling works) along with potential misusages, e.g., drops, with an energy-efficient architecture design. The designed device is based on Bluetooth low energy (BLE) and NFC connectivity. BLE is used to exchange data with a gateway, whereas NFC has been chosen as an energy-efficient wake-up mechanism. A temperature and humidity sensor is embedded to monitor storage conditions and an accelerometer for tool usage monitoring. The ARM Cortex-M4 core embedded in the BLE module is exploited to process the information at the edge. A Tiny Machine Learning (TinyML) algorithm is proposed to process the data directly on board and achieve low latency and high energy efficiency. The TinyML algorithm has been developed embedded in the proposed …
Cited by:62
Resources:[PDF] from ieee.org
:view less
Energy-efficient, precise uwb-based 3-d localization of sensor nodes with a nano-uav
2022
Vlad Niculescu, Daniele Palossi, Michele Magno, Luca Benini
IEEE Internet of Things Journal 10 (7), 5760-5777
:read more
Authors:Vlad Niculescu, Daniele Palossi, Michele Magno, Luca Benini
Publication date:04/13/2022
Journal:IEEE Internet of Things Journal
Volume:10
Issue:7
Pages:5760-5777
Publisher:IEEE
Description:Smart interaction between autonomous centimeter-scale unmanned aerial vehicles (i.e., nano-UAVs) and Internet of Things (IoT) sensor nodes is an upcoming high-impact scenario. This work tackles precise 3-D localization of indoor edge nodes with an autonomous nano-UAV without prior knowledge of their position. We employ ultrawideband (UWB) and wake-up radio (WUR) technologies: we perform UWB-based ranging and data exchange between the nano-UAV and the nodes, while the WUR minimizes the sensors’ power consumption. UWB-based precise localization requires addressing multiple sources of error, such as UWB-ranging noise and UWB antennas’ uneven radiation pattern. The limited computational resources aboard a nano-UAV further complicate this scenario, requiring real-time execution of the localization algorithm within a microcontroller unit (MCU). We propose a novel UWB-based localization …
Cited by:39
:view less
Leveraging tactile sensors for low latency embedded smart hands for prosthetic and robotic applications
2022
Xiaying Wang, Fabian Geiger, Vlad Niculescu, Michele Magno, Luca Benini
IEEE Transactions on Instrumentation and Measurement 71, 1-14
:read more
Authors:Xiaying Wang, Fabian Geiger, Vlad Niculescu, Michele Magno, Luca Benini
Publication date:04/08/2022
Journal:IEEE Transactions on Instrumentation and Measurement
Volume:71
Pages:1-14
Publisher:IEEE
Description:Tactile sensing is a crucial perception mode for robots and human amputees in need of controlling a prosthetic device. Today, robotic and prosthetic systems are still missing the important feature of accurate tactile sensing. This lack is mainly due to the fact that the existing tactile technologies have limited spatial and temporal resolution and are either expensive or not scalable. In this article, we present the design and implementation of a hardware–software embedded system called SmartHand. It is specifically designed to enable the acquisition and real-time processing of high-resolution tactile information from a hand-shaped multisensor array for prosthetic and robotic applications. During data collection, our system can deliver a high throughput of 100 frames per second, which is higher than previous related work. This has allowed the collection of a new tactile dataset consisting of 340 000 frames while …
Cited by:20
Resources:[PDF] from arxiv.org
:view less
Fly, wake-up, find: UAV-based energy-efficient localization for distributed sensor nodes
2022
Vlad Niculescu, Daniele Palossi, Michele Magno, Luca Benini
Sustainable Computing: Informatics and Systems 34, 100666
:read more
Authors:Vlad Niculescu, Daniele Palossi, Michele Magno, Luca Benini
Publication date:04/01/2022
Journal:Sustainable Computing: Informatics and Systems
Volume:34
Pages:100666
Publisher:Elsevier
Description:A challenging application scenario in the field of industrial Unmanned Aerial Vehicles (UAVs) is the capability of a robot to find and query smart sensor nodes deployed at arbitrary locations in the mission area. This work explores the combination of different communication technologies, namely, Ultra-Wideband (UWB) and Wake-Up Radio (WUR), with a UAV that acts as a “ubiquitous local-host” of a Wireless Sensor Network (WSN). First, the UAV performs the localization of the sensor node via multiple UWB range measurements, and then it flies in its proximity to perform energy-efficient data acquisition. We propose an energy-efficient and accurate localization algorithm – based on multi-lateration – that is computationally inexpensive and robust to in-field noise. Aiming at minimizing the sensor node energy consumption, we also present a communication protocol that leverages WUR technology to minimize ON …
Cited by:16
Resources:[HTML] from sciencedirect.com
:view less
A RDMA interface for ultra-fast ultrasound data-streaming over an optical link
2022
Andrea Cossettini, Konstantin Taranov, Christian Vogt, Michele Magno, Torsten Hoefler, …
2022 Design, Automation & Test in Europe Conference & Exhibition (DATE), 80-83
:read more
Authors:Andrea Cossettini, Konstantin Taranov, Christian Vogt, Michele Magno, Torsten Hoefler, Luca Benini
Publication date:03/14/2022
Journal:2022 Design, Automation & Test in Europe Conference & Exhibition (DATE)
Pages:80-83
Publisher:IEEE
Description:Digital ultrasound (US) probes integrate the analog-to-digital conversion directly on the probe and can be conveniently connected to commodity devices. Existing digital probes are however limited to a relatively small number of channels, do not guarantee access to the raw US data, or cannot operate at very high frame rates (e.g., due to exhaustion of computing and storage units on the receiving device). In this work, we present an open, compact, power-efficient, 192-channels digital US data acquisition system capable of streaming US data at transfer rates greater than 80 Gbps towards a host PC for ultra-high frame rate imaging (in the multi-kHz range). Our US probe is equipped with two power-efficient Field Programmable Gate Arrays (FPGAs) and is interfaced to the host PC with two optical-link 100G Ethernet connections. The high-speed performance is enabled by implementing a Remote Direct Memory Access …
Cited by:4
Resources:[PDF] from ethz.ch
:view less
Sub-mW keyword spotting on an MCU: Analog binary feature extraction and binary neural networks
2022
Gianmarco Cerutti, Lukas Cavigelli, Renzo Andri, Michele Magno, Elisabetta Farella, Luc…
IEEE Transactions on Circuits and Systems I: Regular Papers 69 (5), 2002-2012
:read more
Authors:Gianmarco Cerutti, Lukas Cavigelli, Renzo Andri, Michele Magno, Elisabetta Farella, Luca Benini
Publication date:02/08/2022
Journal:IEEE Transactions on Circuits and Systems I: Regular Papers
Volume:69
Issue:5
Pages:2002-2012
Publisher:IEEE
Description:Keyword spotting (KWS) is a crucial function enabling the interaction with the many ubiquitous smart devices in our surroundings, either activating them through wake-word or directly as a human-computer interface. For many applications, KWS is the entry point for our interactions with the device and, thus, an always-on workload. Many smart devices are mobile and their battery lifetime is heavily impacted by continuously running services. KWS and similar always-on services are thus the focus when optimizing the overall power consumption. This work addresses KWS energy-efficiency on low-cost microcontroller units (MCUs). We combine analog binary feature extraction with binary neural networks. By replacing the digital preprocessing with the proposed analog front-end, we show that the energy required for data acquisition and preprocessing can be reduced by , cutting its share from a dominating 85% to a mere 16 …
Cited by:28
Resources:[PDF] from arxiv.org
:view less
Development of a wireless, non-intrusive, MEMS-based pressure and acoustic measurement system for large-scale operating wind turbine blades
2022
Sarah Barber, Julien Deparday, Yuriy Marykovskiy, Eleni Chatzi, Imad Abdallah, Gregory …
Wind Energy Science Discussions 2022, 1-25
:read more
Authors:Sarah Barber, Julien Deparday, Yuriy Marykovskiy, Eleni Chatzi, Imad Abdallah, Gregory Duthé, Michele Magno, Tommaso Polonelli, Raphael Fischer, Hanna Müller
Publication date:01/20/2022
Journal:Wind Energy Science Discussions
Volume:2022
Pages:1-25
Description:As the wind energy industry is maturing and wind turbines are growing, there is an increasing need for cost-effective monitoring and data analysis solutions to understand the complex aerodynamic and acoustic behaviour of the flexible blades. Published measurements on operating rotor blades in real conditions are very scarce, due to the complexity of the installation and use of measurement systems. However, recent developments in electronics, wireless communication and MEMS sensors are making it possible to acquire data in a cost-effective and energy-efficient way. In this work, therefore, a cost-effective MEMS-based aerodynamic and acoustic wireless measurement system that is thin, non-intrusive, easy to install, low power, and self-sustaining is designed and tested. The results show that the system is capable of delivering relevant results continuously, although work needs to be done on calibrating and correcting the pressure signals, as well as on refining the concept for the attachment sleeve for weather protection in the field. Finally, two methods for using the measurements to provide added value to the wind energy industry are developed and demonstrated: (1) inferring local angle of attack via stagnation point detection using differential pressure sensors near the leading edge, and (2) detecting and classifying leading edge erosion using instantaneous snapshots of the measured pressure fields. On-going work involves field tests on an operating 6 kW wind turbine in Switzerland.
Cited by:31
Resources:[HTML] from copernicus.org
:view less
Receiver device for touch communication
2021

:read more
Publication date:11/23/2021
Description:According to the present invention there is provided a receiver device comprising, a first electrode (3) which can capacitive couple to an electrode of a transmitter device; a second electrode (5) which can capacitive couple to said electrode of said transmitter device; an energy harvesting circuit (7), which comprises a first capacitor (9), wherein said first electrode (3) is electrically connected to the energy harvesting circuit (7) so that energy from a signal which was transmitted from the electrode of the transmitter device and received at the first electrode (3), can be used to increase voltage across the first capacitor (9); and a comparator (15), wherein the first capacitor (9) is electrically connected to a positive supply input terminal (15c) of the comparator (15) so that voltage across the first capacitor (9) can be used to power the comparator (15); a demodulator circuit (11) wherein said second electrode (5) is electrically …
Cited by:1
Resources:[PDF] from googleapis.com
:view less
Towards artefact-free bio-impedance measurements: Evaluation, identification and suppression of artefacts at multiple frequencies
2021
Kanika Dheman, Philipp Mayer, Manuel Eggimann, Michele Magno, Simone Schuerle
IEEE Sensors Journal 22 (1), 589-600
:read more
Authors:Kanika Dheman, Philipp Mayer, Manuel Eggimann, Michele Magno, Simone Schuerle
Publication date:11/16/2021
Journal:IEEE Sensors Journal
Volume:22
Issue:1
Pages:589-600
Publisher:IEEE
Description:ObjectiveMethods
Cited by:10
:view less
A battery-free long-range wireless smart camera for face recognition
2021
Marco Giordano, Michele Magno
Proceedings of the 19th ACM Conference on Embedded Networked Sensor Systems, 594-595
:read more
Authors:Marco Giordano, Michele Magno
Publication date:11/15/2021
Journal:Proceedings of the 19th ACM Conference on Embedded Networked Sensor Systems
Pages:594-595
Description:In this demo we present a battery-free smart camera that exploits aggressive power management and energy harvesting to achieve face recognition in an energy-neutral fashion. A novel hardware accelerator for Convolution Neural Networks is employed to speed up the inference of the Tiny Machine Learning algorithm. The recognized face, and not the entire image, is sent via LoRa in a sensor network-like scenario. Experimental results demonstrated the capability of the developed sensor node to start and work perpetually with only a small photovoltaic panel array.
Cited by:14
:view less
Rf power transmission: Energy harvesting for self-sustaining miniaturized sensor nodes
2021
Federico Villani, Philipp Mayer, Michele Magno
Proceedings of the 19th ACM Conference on Embedded Networked Sensor Systems, 592-593
:read more
Authors:Federico Villani, Philipp Mayer, Michele Magno
Publication date:11/15/2021
Journal:Proceedings of the 19th ACM Conference on Embedded Networked Sensor Systems
Pages:592-593
Description:Radio Frequency (RF) energy transfer is an emerging technology to supply perpetually the new generation of internet of things devices. The proposed work shows the design and implementation of RF power transmission circuits the possible usages as a power source for batteryless devices. The realized circuits can receive power in the order of 1-10 mW depending on the distance from the transmitter, size, and antenna efficiency, allowing the deployment of these rectification circuits in any low power sensing network that requires a reliable and controllable power source. This paper will introduce and illustrate the preliminary results achieve for the work done for in a life-demo.
Cited by:1
:view less
High-accuracy ranging and localization with ultrawideband communications for energy-constrained devices
2021
Laura Flueratoru, Silvan Wehrli, Michele Magno, Elena Simona Lohan, Dragoş Niculescu
IEEE Internet of Things Journal 9 (10), 7463-7480
:read more
Authors:Laura Flueratoru, Silvan Wehrli, Michele Magno, Elena Simona Lohan, Dragoş Niculescu
Publication date:11/03/2021
Journal:IEEE Internet of Things Journal
Volume:9
Issue:10
Pages:7463-7480
Publisher:IEEE
Description:Ultrawideband (UWB) communications have gained popularity in recent years for being able to provide distance measurements and localization with high accuracy, which can enhance the capabilities of devices in the Internet of Things (IoT). Since energy efficiency is of utmost concern in such applications, in this work, we evaluate the power and energy consumption, distance measurements, and localization performance of two types of UWB physical interfaces (PHYs), which use either a low- or high-rate pulse repetition (LRP and HRP, respectively). The evaluation is done through measurements acquired in identical conditions, which is crucial in order to have a fair comparison between the devices. We performed measurements in typical line-of-sight (LOS) and nonline-of-sight (NLOS) scenarios. Our results suggest that the LRP interface allows a lower power and energy consumption than the HRP one. Both …
Cited by:59
Resources:[PDF] from arxiv.org
:view less
Comprehensive modelling framework for a low temperature gradient thermoelectric generator
2021
Sergei Vostrikov, Andrey Somov, Pavel Gotovtsev, Michele Magno
Energy Conversion and Management 247, 114721
:read more
Authors:Sergei Vostrikov, Andrey Somov, Pavel Gotovtsev, Michele Magno
Publication date:11/01/2021
Journal:Energy Conversion and Management
Volume:247
Pages:114721
Publisher:Pergamon
Description:Thermoelectric energy harvesting (TEH) is a promising technology enabling the self-sustainable operation of ultra low-power sensing devices performing monitoring tasks. Conventional TEH research mainly focuses on the improvements of the material properties (i.e thermoelectric figure of merit ZT) and thermoelectric module (TEM) geometry. However, enhanced performance of the thermoelectric generator (TEG) can not be practically achieved without optimal integration of the novel TEM with the DC-DC converter. The power converter, having its own input impedance requirements and conversion efficiency curve, may keep the operation point of TEG far from the maximum power point of TEM, leading to power loss. Furthermore, since the physical processes in the thermoelectric transducer are coupled with the electrical processes in the DCDC converter, both components should be analyzed together to achieve …
Cited by:16
:view less
Ultra-low power wake-up receiver for location aware objects operating with UWB
2021
Tommaso Polonelli, Federico Villani, Michele Magno
2021 17th International Conference on Wireless and Mobile Computing, Networking and Com…
:read more
Authors:Tommaso Polonelli, Federico Villani, Michele Magno
Publication date:10/11/2021
Journal:2021 17th International Conference on Wireless and Mobile Computing, Networking and Communications (WiMob)
Pages:369-376
Publisher:IEEE
Description:Ultra-wide band is one of the most promising localization technologies already and increasingly used in industrial environments. It is also starting to be included in many Internet of Things and mobile devices. The most attractive feature of ultra-wide band for localization and positioning is the achievable centimeter-accuracy that can enable a highly secure spoofing-protected application. On the other hand, the main drawback that still limits its use in battery-operated devices is the high power consumption, especially in idle listening. Today most common approaches use duty cycling, which reduces the overall power consumption at the cost of increased latency. The paper presents a hardware wake-up radio with addressing capability for ultra-wide band communication and ranging. Moreover, the paper introduces a novel protocol that enables the generation of wake-up signals directly with any existing ultra-wide band …
Cited by:8
:view less
Design and implementation of an RSSI-based bluetooth low energy indoor localization system
2021
Silvano Cortesi, Marc Dreher, Michele Magno
2021 17th International Conference on Wireless and Mobile Computing, Networking and Com…
:read more
Authors:Silvano Cortesi, Marc Dreher, Michele Magno
Publication date:10/11/2021
Journal:2021 17th International Conference on Wireless and Mobile Computing, Networking and Communications (WiMob)
Pages:163-168
Publisher:IEEE
Description:Indoor Positioning System (IPS) is a crucial technology that enables medical staff and hospital managements to accurately locate and track persons or assets inside the medical buildings. Among other technologies, Bluetooth Low Energy (BLE) can be exploited for achieving an energy-efficient and low-cost solution. This work presents the design and implementation of an received signal strength indicator (RSSI)-based indoor localization system. The paper shows the implementation of a low complex weighted k-Nearest Neighbors algorithm that processes raw RSSI data from connection-less iBeacon’s. The designed hardware and firmware are implemented around the low-power and low-cost nRF52832 from Nordic Semiconductor. Experimental evaluation with the real-time data processing has been evaluated and presented in a 7.2 m by 7.2 m room with furniture and 5 beacon nodes. The experimental results …
Cited by:9
Resources:[PDF] from arxiv.org
:view less
Energy-positive activity recognition-from kinetic energy harvesting to smart self-sustainable wearable devices
2021
Philipp Mayer, Michele Magno, Luca Benini
IEEE Transactions on Biomedical Circuits and Systems 15 (5), 926-937
:read more
Authors:Philipp Mayer, Michele Magno, Luca Benini
Publication date:09/24/2021
Journal:IEEE Transactions on Biomedical Circuits and Systems
Volume:15
Issue:5
Pages:926-937
Publisher:IEEE
Description:Wearable, intelligent, and unobtrusive sensor nodes that monitor the human body and the surrounding environment have the potential to create valuable data for preventive human-centric ubiquitous healthcare. To attain this vision of unobtrusiveness, the smart devices have to gather and analyze data over long periods of time without the need for battery recharging or replacement. This article presents a software-configurable kinetic energy harvesting and power management circuit that enables self-sustainable wearable devices. By exploiting the kinetic transducer as an energy source and an activity sensor simultaneously, the proposed circuit provides highly efficient context-aware control features. Its mixed-signal nano-power context awareness allows reaching energy neutrality even in energy-drought periods, thus significantly relaxing the energy storage requirements. Furthermore, the asynchronous sensing …
Cited by:38
Resources:[PDF] from ethz.ch
:view less
System implementation trade-offs for low-speed rotational variable reluctance energy harvesters
2021
Ye Xu, Sebastian Bader, Michele Magno, Philipp Mayer, Bengt Oelmann
Sensors 21 (18), 6317
:read more
Authors:Ye Xu, Sebastian Bader, Michele Magno, Philipp Mayer, Bengt Oelmann
Publication date:09/21/2021
Journal:Sensors
Volume:21
Issue:18
Pages:6317
Publisher:MDPI
Description:Low-power energy harvesting has been demonstrated as a feasible alternative for the power supply of next-generation smart sensors and IoT end devices. In many cases, the output of kinetic energy harvesters is an alternating current (AC) requiring rectification in order to supply the electronic load. The rectifier design and selection can have a considerable influence on the energy harvesting system performance in terms of extracted output power and conversion losses. This paper presents a quantitative comparison of three passive rectifiers in a low-power, low-voltage electromagnetic energy harvesting sub-system, namely the full-wave bridge rectifier (FWR), the voltage doubler (VD), and the negative voltage converter rectifier (NVC). Based on a variable reluctance energy harvesting system, we investigate each of the rectifiers with respect to their performance and their effect on the overall energy extraction. We conduct experiments under the conditions of a low-speed rotational energy harvesting application with rotational speeds of 5 rpm to 20 rpm, and verify the experiments in an end-to-end energy harvesting evaluation. Two performance metrics—power conversion efficiency (PCE) and power extraction efficiency (PEE)—are obtained from the measurements to evaluate the performance of the system implementation adopting each of the rectifiers. The results show that the FWR with PEEs of 20% at 5 rpm to 40% at 20 rpm has a low performance in comparison to the VD (40–60%) and NVC (20–70%) rectifiers. The VD-based interface circuit demonstrates the best performance under low rotational speeds, whereas the NVC outperforms the VD …
Cited by:11
Resources:[HTML] from mdpi.com
:view less
The relevance of rock shape over mass—implications for rockfall hazard assessments
2021
Andrin Caviezel, Adrian Ringenbach, Sophia E Demmel, Claire E Dinneen, Nora Krebs, Yves…
Nature communications 12 (1), 5546
:read more
Authors:Andrin Caviezel, Adrian Ringenbach, Sophia E Demmel, Claire E Dinneen, Nora Krebs, Yves Bühler, Marc Christen, Guillaume Meyrat, Andreas Stoffel, Elisabeth Hafner, Lucie A Eberhard, Daniel von Rickenbach, Kevin Simmler, Philipp Mayer, Pascal S Niklaus, Thomas Birchler, Tim Aebi, Lukas Cavigelli, Michael Schaffner, Stefan Rickli, Christoph Schnetzler, Michele Magno, Luca Benini, Perry Bartelt
Publication date:09/20/2021
Journal:Nature communications
Volume:12
Issue:1
Pages:5546
Publisher:Nature Publishing Group UK
Description:The mitigation of rapid mass movements involves a subtle interplay between field surveys, numerical modelling, and experience. Hazard engineers rely on a combination of best practices and, if available, historical facts as a vital prerequisite in establishing reproducible and accurate hazard zoning. Full-scale field tests have been performed to reinforce the physical understanding of debris flows and snow avalanches. Rockfall dynamics are - especially the quantification of energy dissipation during the complex rock-ground interaction - largely unknown. The awareness of rock shape dependence is growing, but presently, there exists little experimental basis on how rockfall hazard scales with rock mass, size, and shape. Here, we present a unique data set of induced single-block rockfall events comprising data from equant and wheel-shaped blocks with masses up to 2670 kg, quantifying the influence of rock shape …
Cited by:60
Resources:[HTML] from nature.com
Full View
:view less
General purpose and neural network approach for benchmarking microcontrollers under radiation
2021
Marco Giordano, Rudy Ferraro, Michele Magno, Salvatore Danzeca
2021 21th European Conference on Radiation and Its Effects on Components and Systems (R…
:read more
Authors:Marco Giordano, Rudy Ferraro, Michele Magno, Salvatore Danzeca
Publication date:09/13/2021
Journal:2021 21th European Conference on Radiation and Its Effects on Components and Systems (RADECS)
Pages:1-8
Publisher:IEEE
Description:In this work a testing methodology for micro-controllers exposed to radiation is proposed. General purpose benchmarks are reviewed to provide a mean of testing all the macro-areas of a microcontroller, and a neural network benchmark is introduced as a representative class of novel computing algorithms for IoT devices. Metrics from literature are reviewed and a new metric, the Mean Energy per Unit Workload Between Failure, is introduced. It combines computing performance and energy consumption in a single unit, making it specifically useful to benchmark battery-operated edge nodes. A method to analyse reset causes is also introduced, giving important insights into failure mechanisms and potential patterns. The testing strategy has been validated on a representative class of four Cortex M0+ and Cortex M4 microcontrollers irradiated under a 200MeV proton beam with different fluences. Results from the …
Cited by:2
:view less
Towards an open, flexible, wearable ultrasound probe for musculoskeletal monitoring
2021
Sergei Vostrikov, Andrea Cossettini, Christian Vogt, Christoph Leitner, Michele Magno, …
2021 IEEE International Ultrasonics Symposium (IUS), 1-4
:read more
Authors:Sergei Vostrikov, Andrea Cossettini, Christian Vogt, Christoph Leitner, Michele Magno, Luca Benini
Publication date:09/11/2021
Journal:2021 IEEE International Ultrasonics Symposium (IUS)
Pages:1-4
Publisher:IEEE
Description:Ultrasound (US) is a widely used tool to observe musculoskeletal features during movement. US signals provide information about the instantaneous length and activation of muscles, and these signals are used for new prosthetic control strategies, to increase the performance of Human-Machine interfaces, or to improve muscle force predictions. However, existing commercial systems and research platforms are bulky, non-wearable, not supporting high frame rates, or lack configurability. Our work presents an US prototype meeting all key requirements to measure muscle activity during motion: our platform is open (providing access to raw data), flexible (operating in different modalities and channel count), it features wireless connectivity (supporting high frame rates> 100 Hz) and supports low power consumption (<1W) for a longer battery lifetime.
Cited by:15
:view less
Smarttag: An ultra low power asset tracking and usage analysis iot device with embedded ml capabilities
2021
Marco Giordano, Raphael Fischer, Michele Crabolu, Giovanni Bellusci, Michele Magno
2021 IEEE Sensors Applications Symposium (SAS), 1-6
:read more
Authors:Marco Giordano, Raphael Fischer, Michele Crabolu, Giovanni Bellusci, Michele Magno
Publication date:08/23/2021
Journal:2021 IEEE Sensors Applications Symposium (SAS)
Pages:1-6
Publisher:IEEE
Description:Assessing power tools usage helps to prolong their life cycle, as well as indicate targeted maintenance interventions after a particular series of events, e.g. drops. In this work, we propose a low power multi-sensors hardware-software co-design for extremely long shelf life, and a long operating lifecycle. The designed device is based on a Bluetooth Low Energy (BLE) system on chip (SoC) to exchange data with a gateway. NFC has been chosen to wake up the device without adding any additional power consumption. The system on a chip includes an ARM Cortex-M4F core to further process the information achieving low latency and high energy efficiency. The device hosts a temperature and humidity sensor used to monitor the storage conditions, and an accelerometer is used for condition and activity monitoring. This paper provides a proof-of-concept approach to continuously assess the usage of a power tool and …
Cited by:13
:view less
Smarthand: towards embedded smart hands for prosthetic and robotic applications
2021
Xiaying Wang, Fabian Geiger, Vlad Niculescu, Michele Magno, Luca Benini
2021 IEEE Sensors Applications Symposium (SAS), 1-6
:read more
Authors:Xiaying Wang, Fabian Geiger, Vlad Niculescu, Michele Magno, Luca Benini
Publication date:08/23/2021
Journal:2021 IEEE Sensors Applications Symposium (SAS)
Pages:1-6
Publisher:IEEE
Description:The sophisticated sense of touch of the human hand significantly contributes to our ability to safely, efficiently, and dexterously manipulate arbitrary objects in our environment. Robotic and prosthetic devices lack refined tactile feedback from their end-effectors, leading to counterintuitive and complex control strategies. To address this lack, tactile sensors have been designed and developed, but they are either expensive and not scalable or offer an insufficient spatial and temporal resolution. This paper focuses on overcoming these issues by designing a smart embedded system, called SmartHand, enabling the acquisition and real-time processing of high-resolution tactile information from a hand-shaped multi-sensor array for prosthetic and robotic applications. We acquire a new tactile dataset consisting of 340,000 frames while interacting with 16 objects from everyday life and the empty hand, i.e., a total of 17 …
Cited by:13
Resources:[PDF] from arxiv.org
:view less
ImpediSense: A long lasting wireless wearable bio-impedance sensor node
2021
Kanika Dheman, Philipp Mayer, Manuel Eggimann, Simone Schuerle, Michele Magno
Sustainable Computing: Informatics and Systems 30, 100556
:read more
Authors:Kanika Dheman, Philipp Mayer, Manuel Eggimann, Simone Schuerle, Michele Magno
Publication date:06/01/2021
Journal:Sustainable Computing: Informatics and Systems
Volume:30
Pages:100556
Publisher:Elsevier
Description:Bio-impedance is a method to assess the body composition safely, non-invasively and inexpensively. This method finds application for assessing body fluid and body composition for multiple disease scenarios in clinical environments and for at-home monitoring of chronic ailments. Bio-impedance sensors require higher power than most other bio-signal acquisition systems due to need of high frequency current and voltage management. Currently used bio-impedance devices are bulky due to incorporation of large batteries and cannot be used for long term monitoring, especially for wearable applications. This limits the widespread implementation of bio-impedance measurement devices. We present the design and implementation of a wireless wearable bio-impedance sensor node, ImpediSense, which has a low power system design that achieves long duration operability without compromising on sensor …
Cited by:25
:view less
H-Watch: an open, connected platform for AI-enhanced CoViD19 infection symptoms monitoring and contact tracing
2021
Tommaso Polonelli, Lukas Schulthess, Philipp Mayer, Michele Magno, Luca Benini
2021 IEEE International Symposium on Circuits and Systems (ISCAS), 1-5
:read more
Authors:Tommaso Polonelli, Lukas Schulthess, Philipp Mayer, Michele Magno, Luca Benini
Publication date:05/22/2021
Journal:2021 IEEE International Symposium on Circuits and Systems (ISCAS)
Pages:1-5
Publisher:IEEE
Description:The novel COVID-19 disease has been declared a pandemic event. Early detection of infection symptoms and contact tracing are playing a vital role in containing COVID-19 spread. As demonstrated by recent literature, multi-sensor and connected wearable devices might enable symptom detection and help tracing contacts, while also acquiring useful epidemiological information. This paper presents the design and implementation of a fully open-source wearable platform called H-Watch. It has been designed to include several sensors for COVID-19 early detection, multi-radio for wireless transmission and tracking, a microcontroller for processing data on-board, and finally, an energy harvester to extend the battery lifetime. Experimental results demonstrated only 5.9 mW of average power consumption, leading to a lifetime of 9 days on a small watch battery. Finally, all the hardware and the software, including a …
Cited by:17
Resources:[PDF] from arxiv.org
:view less
Towards always-on event-based cameras for long-lasting battery-operated smart sensor nodes
2021
Moritz Scherer, Philipp Mayer, Alfio Di Mauro, Michele Magno, Luca Benini
2021 IEEE International Instrumentation and Measurement Technology Conference (I2MTC), 1-6
:read more
Authors:Moritz Scherer, Philipp Mayer, Alfio Di Mauro, Michele Magno, Luca Benini
Publication date:05/17/2021
Journal:2021 IEEE International Instrumentation and Measurement Technology Conference (I2MTC)
Pages:1-6
Publisher:IEEE
Description:A recent and promising approach to minimize the power consumption of always-on battery-operated sensors is to perform “smart” detection of events to trigger processing. This approach effectively reduces the data bandwidth and power consumption at the system-level and increases the lifetime of sensor nodes. This paper presents an always-on, event-driven ultra-low-power camera platform for motion detection applications. The platform exploits an event-driven VGA imager that features a motion detection mode based on a tunable scene background subtraction algorithm and a grayscale imaging mode. To reduce the power consumption in the motion detection mode, the platform implements a configurable refresh rate which allows for adaption to sensing requirements by trading off between power consumption and detection sensitivity. With accurate experimental evaluation the paper demonstrates that the …
Cited by:3
Resources:[PDF] from researchgate.net
:view less
Windnode: A long-lasting and long-range bluetooth wireless sensor node for pressure and acoustic monitoring on wind turbines
2021
Raphael Fischer, Hanna Mueller, Tommaso Polonelli, Luca Benini, Michele Magno
2021 4th IEEE international conference on industrial cyber-physical systems (ICPS), 393…
:read more
Authors:Raphael Fischer, Hanna Mueller, Tommaso Polonelli, Luca Benini, Michele Magno
Publication date:05/10/2021
Journal:2021 4th IEEE international conference on industrial cyber-physical systems (ICPS)
Pages:393-399
Publisher:IEEE
Description:This paper presents a low power, flexible and energy-efficient wireless sensor node for aerodynamic and acoustic measurements on wind turbine blades and other industrial structures. It comprises 40 high-accuracy absolute MEMS pressure sensors, ten MEMS microphones, a data processing system, a wireless transmitter based on Bluetooth Low Energy 5 tuned for long-range and high throughput while maintaining energy efficiency. The sensor node has been designed and implemented to test the range of communication, the impact on energy efficiency, the functionality, and the estimated lifetime. Experimental tests outdoor in realistic conditions revealed that the system can sustain a data rate of 850kbps over 438m. The node power consumption while streaming all measured data from a multi-MW wind turbine is only 46mW, enabling lifetimes of a full month even in the worst-case scenario of streaming all …
Cited by:15
:view less
Tinyradarnn: Combining spatial and temporal convolutional neural networks for embedded gesture recognition with short range radars
2021
Moritz Scherer, Michele Magno, Jonas Erb, Philipp Mayer, Manuel Eggimann, Luca Benini
IEEE Internet of Things Journal 8 (13), 10336-10346
:read more
Authors:Moritz Scherer, Michele Magno, Jonas Erb, Philipp Mayer, Manuel Eggimann, Luca Benini
Publication date:03/19/2021
Journal:IEEE Internet of Things Journal
Volume:8
Issue:13
Pages:10336-10346
Publisher:IEEE
Description:This work proposes a low-power high-accuracy embedded hand-gesture recognition algorithm targeting battery-operated wearable devices using low-power short-range RADAR sensors. A 2-D convolutional neural network (CNN) using range-frequency Doppler features is combined with a temporal convolutional neural network (TCN) for time sequence prediction. The final algorithm has a model size of only 46 thousand parameters, yielding a memory footprint of only 92 KB. Two data sets containing 11 challenging hand gestures performed by 26 different people have been recorded containing a total of 20'210 gesture instances. On the 11 hand gesture data set, accuracies of 86.6% (26 users) and 92.4% (single user) have been achieved, which are comparable to the state of the art, which achieves 87% (10 users) and 94% (single user), while using a TCN-based network that is 7500× smaller than the state of the …
Cited by:99
Resources:[PDF] from arxiv.org
:view less
Flydvs: An event-driven wireless ultra-low power visual sensor node
2021
Alfio Di Mauro, Moritz Scherer, Jordi Fornt Mas, Basile Bougenot, Michele Magno, Luca B…
2021 Design, Automation & Test in Europe Conference & Exhibition (DATE), 1851-1854
:read more
Authors:Alfio Di Mauro, Moritz Scherer, Jordi Fornt Mas, Basile Bougenot, Michele Magno, Luca Benini
Publication date:02/01/2021
Journal:2021 Design, Automation & Test in Europe Conference & Exhibition (DATE)
Pages:1851-1854
Publisher:IEEE
Description:Event-based cameras, also called dynamic vision sensors (DVS), inspired by the human vision system, are gaining popularity due to their potential energy-saving since they generate asynchronous events only from the pixels changes in the field of view. Unfortunately, in most current uses, data acquisition, processing, and streaming of data from event-based cameras are performed by power-hungry hardware, mainly high-power FPGAs. For this reason, the overall power consumption of an event-based system that includes digital capture and streaming of events, is in the order of hundreds of milliwatts or even watts, reducing significantly usability in real-life low-power applications such as wearable devices. This work presents FlyDVS, the first event-driven wireless ultra-low-power visual sensor node that includes a low-power Lattice FPGA and, a Bluetooth wireless system-on-chip, and hosts a commercial ultra-low …
Cited by:12
Resources:[PDF] from date-conference.com
:view less
How can wake-up radio reduce lora downlink latency for energy harvesting sensor nodes?
2021
Nour El Hoda Djidi, Matthieu Gautier, Antoine Courtay, Olivier Berder, Michele Magno
Sensors 21 (3), 733
:read more
Authors:Nour El Hoda Djidi, Matthieu Gautier, Antoine Courtay, Olivier Berder, Michele Magno
Publication date:01/22/2021
Journal:Sensors
Volume:21
Issue:3
Pages:733
Publisher:MDPI
Description:LoRa is popular for internet of things applications as this communication technology offers both a long range and a low power consumption. However, LoRaWAN, the standard MAC protocol that uses LoRa as physical layer, has the bottleneck of a high downlink latency to achieve energy efficiency. To overcome this drawback we explore the use of wake-up radio combined with LoRa, and propose an adequate MAC protocol that takes profit of both these heterogeneous and complementary technologies. This protocol allows an opportunistic selection of a cluster head that forwards commands from the gateway to the nodes in the same cluster. Furthermore, to achieve self-sustainability, sensor nodes might include an energy harvesting sub-system, for instance to scavenge energy from the light, and their quality of service can be tuned, according to their available energy. To have an effective self-sustaining LoRa system, we propose a new energy manager that allows less fluctuations of the quality of service between days and nights. Latency and energy are modeled in a hybrid manner, i.e., leveraging microbenchmarks on real hardware platforms, to explore the influence of the energy harvesting conditions on the quality of service of this heterogeneous network. It is clearly demonstrated that the cooperation of nodes within a cluster drastically reduces the latency of LoRa base station commands, e.g., by almost 90% compared to traditional LoRa scheme for a 10 nodes cluster.
Cited by:21
Resources:[HTML] from mdpi.com
:view less
IEEE: General Purpose and Neural Network Approach for Benchmarking Microcontrollers Under Radiation
2021
Marco Giordano, Michele Magno, Rudy Ferraro, Salvatore Danzeca
, 1-8
:read more
Authors:Marco Giordano, Michele Magno, Rudy Ferraro, Salvatore Danzeca
Publication date:01/01/2021
Pages:1-8
Description:In this work a testing methodology for micro-controllers exposed to radiation is proposed. General purpose benchmarks are reviewed to provide a mean of testing all the macro-areas of a microcontroller, and a neural network benchmark is introduced as a representative class of novel computing algorithms for IoT devices. Metrics from literature are reviewed and a new metric, the Mean Energy per Unit Workload Between Failure, is introduced. It combines computing performance and energy consumption in a single unit, making it specifically useful to benchmark battery-operated edge nodes. A method to analyse reset causes is also introduced, giving important insights into failure mechanisms and potential patterns. The testing strategy has been validated on a representative class of four Cortex M0+ and Cortex M4 microcontrollers irradiated under a 200MeV proton beam with different fluences. Results from the irradiation campaign are presented and commented on to validate the benchmarks and metrics discussed.
:view less
In-situ kinematic tracking via rugged multi-sensor MEMS units
2021
Andrin Caviezel, Adrian Ringenbach, Miguel Sanchez, Marc Christen, Philipp Mayer, Miche…
25th International Congress of Theoretical and Applied Mechanics–Book of Abstracts
:read more
Authors:Andrin Caviezel, Adrian Ringenbach, Miguel Sanchez, Marc Christen, Philipp Mayer, Michele Magno, Luca Benini, Perry Bartelt
Publication date:01/01/2021
Journal:25th International Congress of Theoretical and Applied Mechanics–Book of Abstracts
Publisher:International Union of Theoretical and Applied Mechanics
Description:The development in miniaturised microelectronic mechanical systems (MEMS) sensors during the last decade driven by growing needs for autonomous driving and unmanned aerial vehicle navigation lead to a giant performance increase. Here, we present data acquired via rugged low-power multi-sensor nodes, that have been designed to acquire and log accurate inertial sensor measurements during induced in-field experiments with falling rocks and moving avalanches. Field experiments have been carried out with several differently shaped rocks on typical terrain in the Swiss alpine region. The sensor streams are integral part of an excessive experimental campaign, studying influence of rock shape and mass. Using equally shaped rocks with masses up to 2670 kg offers for the first time systematic insights on rock kinematics and its dependence on the rock mass.
Cited by:2
:view less
On the energy consumption and ranging accuracy of ultra-wideband physical interfaces
2020
Laura Flueratoru, Silvan Wehrli, Michele Magno, Dragos Niculescu
GLOBECOM 2020-2020 IEEE Global Communications Conference, 1-7
:read more
Authors:Laura Flueratoru, Silvan Wehrli, Michele Magno, Dragos Niculescu
Publication date:12/07/2020
Journal:GLOBECOM 2020-2020 IEEE Global Communications Conference
Pages:1-7
Publisher:IEEE
Description:Ultra-wideband (UWB) communication is attracting increased interest for its high-accuracy distance measurements. However, the typical current consumption of tens to hundreds of mA during transmission and reception might make the technology prohibitive to battery-powered devices in the Internet of Things. The IEEE 802.15.4 standard specifies two UWB physical layer interfaces (PHYs), with low- and high-rate pulse repetition (LRP and HRP, respectively). While the LRP PHY allows a more energy-efficient implementation of the UWB transceiver than its HRP counterpart, the question is whether some ranging quality is lost in exchange. We evaluate the trade-off between power and energy consumption, on the one hand, and distance measurement accuracy and precision, on the other hand, using UWB devices developed by Decawave (HRP) and 3db Access (LRP). We find that the distance measurement errors …
Cited by:28
Resources:[PDF] from google.com
:view less
RTK-LoRa: high-precision, long-range, and energy-efficient localization for mobile IoT devices
2020
Philipp Mayer, Michele Magno, Armin Berger, Luca Benini
IEEE Transactions on Instrumentation and Measurement 70, 1-11
:read more
Authors:Philipp Mayer, Michele Magno, Armin Berger, Luca Benini
Publication date:12/04/2020
Journal:IEEE Transactions on Instrumentation and Measurement
Volume:70
Pages:1-11
Publisher:IEEE
Description:High-precision global navigation satellite system (GNSS) is a crucial geolocalization feature enabling a wide range of applications, from mobile Internet-of-Things devices to autonomous drones and self-driving vehicles. Real-time kinematic (RTK) is a GNSS technology that attracting increased interest due to the centimeter precision achievable when wireless communication is present on the devices. On the other hand, sending continuously wireless data increases the energy consumption and the cost of the solution, especially when communication is carried over the 4G network. Due to those drawbacks, RTK is not much exploited in the localization of battery-operated devices. This work combines RTK with low-power long-range communication to achieve submeter precision in an energy-efficient RTK-based system. The proposed system exploits a state-of-the-art RTK-GNSS module combined with a long range …
Cited by:37
Resources:[PDF] from ethz.ch
:view less
A low power and smart power unit for kinetic self-sustainable wearable devices
2020
Philipp Mayer, Michele Magno, Luca Benini
2020 27th IEEE International Conference on Electronics, Circuits and Systems (ICECS), 1-4
:read more
Authors:Philipp Mayer, Michele Magno, Luca Benini
Publication date:11/23/2020
Journal:2020 27th IEEE International Conference on Electronics, Circuits and Systems (ICECS)
Pages:1-4
Publisher:IEEE
Description:A novel trend to achieve long-lifetime or even self-sustainable wearable devices is to exploit energy harvesting from environmental or body energy. Their power management circuits need to be carefully designed to enable a small-size energy-efficient wearable system, supporting multiple power domains ranging from mW in an active mode to nW in sleep modes. This work presents a fully configurable smart power unit suitable for kinetic energy harvesting transducers, Kinetron MGS, enabling self-sustainability for wearable devices. The proposed power management circuit hosts a low power microcontroller to manage the energy harvesting, voltage conversion from batteries, and wake-up circuits to exit low power states automatically. The source and the load power points are decoupled with multiple DC-DC converters aiming to supply loads with adaptive voltage scaling and high reliability. Experimental results …
Cited by:7
Resources:[PDF] from researchgate.net
:view less
A battery-free long-range wireless smart camera for face detection
2020
Marco Giordano, Philipp Mayer, Michele Magno
Proceedings of the 8th International Workshop on Energy Harvesting and Energy-Neutral S…
:read more
Authors:Marco Giordano, Philipp Mayer, Michele Magno
Publication date:11/16/2020
Journal:Proceedings of the 8th International Workshop on Energy Harvesting and Energy-Neutral Sensing Systems
Pages:29-35
Description:This paper presents a battery-free smart camera that combines tiny machine learning, long-range communication, power management, and energy harvesting. The smart sensor node has been implemented and evaluated in the field, showing both battery-less capabilities with a small-size photovoltaic panel and the energy efficiency of the proposed solution. We evaluated two different ARM Cortex-M4F microcontrollers, the Ambiq Apollo 3 that is an energy-efficient microcontroller, and a Microchip SAMD51 able to work in high radiation environments but with a higher power in active mode. Finally, a low power LoRa module provides the long-range wireless transmission capability. The tiny machine learning algorithm for face recognition has been optimized in terms of accuracy versus energy, achieving up to 97% accuracy recognizing five different faces. Experimental results demonstrated the capability of the …
Cited by:44
:view less
Adversarial Machine Learning against Real-World Attacks on CNN Object Detectors
2020
Alessandro Ottaviano
:read more
Authors:Alessandro Ottaviano
Publication date:10/23/2020
Description:The past few years have witnessed a growing interest in the analysis of Machine Learning models robustness against adversarial examples, i.e. externally injected modifications to the input of a Neural Network able to pollute the predicted output correctness. It often happens that the adversarial nature of the examples is imperceptible and/or incognito with respect to the clean input yet causing a non-negligible drop in the accuracy. Therefore, several issues and open questions about the actual and effective security of modern Machine Learning models employed for different tasks, from Speech Recognition to Computer Vision, are introduced. As a matter of facts, there exists an expanding field of interest which is getting devoted to craft countermeasures for lowering the attack's strength: Adversarial Defense techniques follow different fashions according to the attack threat-model they aim to defend against. The research community has started a process of hierarchical and methodological organization to flatten the ground of reference, thus letting them to acquire solid coherent results as well as a robust application toolset. This document aims first at analyzing the effectiveness of adversarial patch attacks targeting misdetection against benchmark Convolutional Neural Networks (CNN) objects and face detectors - You Only Look Once (YOLO), Single Shot Detector (SSD) and Multitask Cascaded CNN (MTCNN) - while keeping as steady as possible the setup flow, and assessing the obtained results in terms of model's accuracy drop. Simulations are performed in the framework of white box digital attacks, where the attacker owns full knowledge …
Resources:[PDF] from polito.it
:view less
Smart power unit—mW-to-nW power management and control for self-sustainable IoT devices
2020
Philipp Mayer, Michele Magno, Luca Benini
IEEE Transactions on Power Electronics 36 (5), 5700-5710
:read more
Authors:Philipp Mayer, Michele Magno, Luca Benini
Publication date:10/16/2020
Journal:IEEE Transactions on Power Electronics
Volume:36
Issue:5
Pages:5700-5710
Publisher:IEEE
Description:Self-sustainability and intelligence will be critical features of the next generation of Internet of Things devices. Power management circuits need to be energy-efficient in multiple power modes, from nW sleep to mW active, and to support energy harvesting (EH) from multiple environmental sources. This article presents an adaptive and firmware-configurable power supply unit that enables intelligent devices to operate in the sub μW range while achieving self-sustainability through EH. The microcontroller-based design allows efficient conversion from batteries, dc, ac environmental sources, and nA quiescent currents. Source and load power points are decoupled with multiple dc-dc converters aiming to supply loads with adaptive voltage scaling and achieving high reliability. Experimental results show the flexibility and efficiency of this approach: the proposed power supply unit achieves a quiescent current of 54 nA …
Cited by:61
Resources:[PDF] from ethz.ch
:view less
Wireless, artefact aware impedance sensor node for continuous bio-impedance monitoring
2020
Kanika Dheman, Philipp Mayer, Michele Magno, Simone Schuerle
IEEE Transactions on Biomedical Circuits and Systems 14 (5), 1122-1134
:read more
Authors:Kanika Dheman, Philipp Mayer, Michele Magno, Simone Schuerle
Publication date:09/02/2020
Journal:IEEE Transactions on Biomedical Circuits and Systems
Volume:14
Issue:5
Pages:1122-1134
Publisher:IEEE
Description:Body bio-impedance is a unique parameter to monitor changes in body composition non-invasively. Continuous measurement of bio-impedance can track changes in body fluid content and cell mass and has widespread applications for physiological monitoring. State-of-the-art implementation of bio-impedance sensor devices is still limited for continuous use, in part, due to artefacts arising at the skin-electrode (SE) interface. Artefacts at the SE interface may arise due to various factors such as motion, applied pressure on the electrode surface, changes in ambient conditions or gradual drying of electrodes. This paper presents a novel bio-impedance sensor node that includes an artefact aware method for bio-impedance measurement. The sensor node enables autonomous and continuous measurement of bio-impedance and SE contact impedance at ten frequencies between 10 kHz to 100 kHz to detect artefacts at …
Cited by:14
:view less
Sound event detection with binary neural networks on tightly power-constrained IoT devices
2020
Gianmarco Cerutti, Renzo Andri, Lukas Cavigelli, Elisabetta Farella, Michele Magno, Luc…
Proceedings of the ACM/IEEE International Symposium on Low Power Electronics and Design…
:read more
Authors:Gianmarco Cerutti, Renzo Andri, Lukas Cavigelli, Elisabetta Farella, Michele Magno, Luca Benini
Publication date:08/10/2020
Journal:Proceedings of the ACM/IEEE International Symposium on Low Power Electronics and Design
Pages:19-24
Description:Sound event detection (SED) is a hot topic in consumer and smart city applications. Existing approaches based on deep neural networks (DNNs) are very effective, but highly demanding in terms of memory, power, and throughput when targeting ultra-low power always-on devices. Latency, availability, cost, and privacy requirements are pushing recent IoT systems to process the data on the node, close to the sensor, with a very limited energy supply, and tight constraints on the memory size and processing capabilities precluding to run state-of-the-art DNNs. In this paper, we explore the combination of extreme quantization to a small-footprint binary neural network (BNN) with the highly energy-efficient, RISC-V-based (8+1)-core GAP8 microcontroller. Starting from an existing CNN for SED whose footprint (815 kB) exceeds the 512 kB of memory available on our platform, we retrain the network using binary filters and …
Cited by:57
Resources:[PDF] from arxiv.org
:view less
Radio frequency power transmission for self-sustaining miniaturized iot devices: Survey and experimental evaluation
2020
Louis Meile, Anja Ulrich, Philipp Mayer, Michele Magno
2020 International Symposium on Power Electronics, Electrical Drives, Automation and Mo…
:read more
Authors:Louis Meile, Anja Ulrich, Philipp Mayer, Michele Magno
Publication date:06/24/2020
Journal:2020 International Symposium on Power Electronics, Electrical Drives, Automation and Motion (SPEEDAM)
Pages:132-137
Publisher:IEEE
Description:The Internet of Things (IoT) is a promising vision to cover a wide range of applications. However, battery-operated devices at the edge of the Internet, have a limited lifetime or involve significant maintenance effort. Energy Harvesting (EH) is one of the most investigated technologies to extend the battery lifetime. Nevertheless, the further miniaturization of devices poses challenges, mainly due to the small form factor needed. In particular, harvesting energy from miniaturized transducers (i.e., millimeter-sized solar panels) is significantly more challenging. Among other EH technologies, transmitting power wirelessly is growing in popularity as it can be controlled, and it is less unpredictable than environmental sources. This work investigates different technologies to supply small size and low power smart devices for IoT applications with wireless power transmission. The paper illustrates with experimental measurements …
Cited by:8
:view less
An accurate eegnet-based motor-imagery brain–computer interface for low-power edge computing
2020
Xiaying Wang, Michael Hersche, Batuhan Tömekce, Burak Kaya, Michele Magno, Luca Benini
2020 IEEE international symposium on medical measurements and applications (MeMeA), 1-6
:read more
Authors:Xiaying Wang, Michael Hersche, Batuhan Tömekce, Burak Kaya, Michele Magno, Luca Benini
Publication date:06/01/2020
Journal:2020 IEEE international symposium on medical measurements and applications (MeMeA)
Pages:1-6
Publisher:IEEE
Description:This paper presents an accurate and robust embedded motor-imagery brain–computer interface (MI-BCI). The proposed novel model, based on EEGNet [1], matches the requirements of memory footprint and computational resources of low-power microcontroller units (MCUs), such as the ARM Cortex-M family. Furthermore, the paper presents a set of methods, including temporal downsampling, channel selection, and narrowing of the classification window, to further scale down the model to relax memory requirements with negligible accuracy degradation. Experimental results on the Physionet EEG Motor Movement/Imagery Dataset show that standard EEGNet achieves 82.43%, 75.07%, and 65.07% classification accuracy on 2-, 3-, and 4-class MI tasks in global validation, outperforming the state-of-the-art (SoA) convolutional neural network (CNN) by 2.05%, 5.25%, and 6.49%. Our novel method further scales …
Cited by:131
Resources:[PDF] from arxiv.org
:view less
NB-IoT versus LoRaWAN: An experimental evaluation for industrial applications
2020
Massimo Ballerini, Tommaso Polonelli, Davide Brunelli, Michele Magno, Luca Benini
IEEE Transactions on Industrial Informatics 16 (12), 7802-7811
:read more
Authors:Massimo Ballerini, Tommaso Polonelli, Davide Brunelli, Michele Magno, Luca Benini
Publication date:04/15/2020
Journal:IEEE Transactions on Industrial Informatics
Volume:16
Issue:12
Pages:7802-7811
Publisher:IEEE
Description:Low power and long-range communications are crucial features of the Internet of Things (IoT) paradigm that is becoming essential even for industrial applications. Today, the most promising long-range communication technologies are LoRaWAN and Narrow Band IoT (NB-IoT), which are driving a large IoT ecosystem. In this article, we evaluate the performance of LoRaWAN and NB-IoT with accurate in-field measurements using the same application context for a fair comparison in terms of energy efficiency, lifetime, quality of service, and coverage. The NB-IoT energy transmission is scarcely dependent on the payload length. Thus applications that can tolerate buffering and caching techniques on the node are favored. On the other hand, LoRaWAN consumes 10 × lower energy compared to NB-IoT for occasional and latency-sensitive communications, for which it enables much end-device lifetime. Finally, this …
Cited by:103
Resources:[PDF] from unibo.it
:view less
A non-invasive wearable bioimpedance system to wirelessly monitor bladder filling
2020
Markus Reichmuth, Simone Schürle, Michele Magno
2020 Design, Automation & Test in Europe Conference & Exhibition (DATE), 338-341
:read more
Authors:Markus Reichmuth, Simone Schürle, Michele Magno
Publication date:03/09/2020
Journal:2020 Design, Automation & Test in Europe Conference & Exhibition (DATE)
Pages:338-341
Publisher:IEEE
Description:Abstract² Monitoring of renal function can be crucial for patients in acute care settings. Commonly during postsurgical surveillance, urinary catheters are employed to assess the urine output accurately. However, as with any external device inserted into the body, the use of these catheters carries a significant risk of infection. In this paper, we present a non invasive method to measure the fill rate of the bladder, and thus rate of renal clearance, via an external bioimpedance sensor system to avoid the use of urinary catheters, thereby eliminating the risk of infections and improving patient comfort. We design and propose a 4 electrode front end and the whole wearable and wireless system with low power and accuracy in mind. The results demonstrate the accuracy of the sensors and low power consumption of only 80μW with a duty cycling of 1 acquisition every 5 minutes, which makes this battery operated wearable device a long term monitor system.
Cited by:32
Resources:[PDF] from date-conference.com
:view less
HR-SAR-Net: A deep neural network for urban scene segmentation from high-resolution SAR data
2020
Xiaying Wang, Lukas Cavigelli, Manuel Eggimann, Michele Magno, Luca Benini
2020 IEEE Sensors Applications Symposium (SAS), 1-6
:read more
Authors:Xiaying Wang, Lukas Cavigelli, Manuel Eggimann, Michele Magno, Luca Benini
Publication date:03/09/2020
Journal:2020 IEEE Sensors Applications Symposium (SAS)
Pages:1-6
Publisher:IEEE
Description:Synthetic aperture radar (SAR) data is becoming increasingly available to a wide range of users through commercial service providers with resolutions reaching 0.5 m/px. Segmenting SAR data still requires skilled personnel, limiting the potential for large-scale use. We show that it is possible to automatically and reliably perform urban scene segmentation from next-gen resolution SAR data (0.15 m/px) using deep neural networks (DNNs), achieving a pixel accuracy of 95.19% and a mean intersection-over-union (mIoU) of 74.67% with data collected over a region of merely 2.2km2. The presented DNN is not only effective, but is very small with only 63k parameters and computationally simple enough to achieve a throughput of around 500 Mpx/s using a single GPU. We further identify that additional SAR receive antennas and data from multiple flights massively improve the segmentation accuracy. We describe a …
Cited by:38
Resources:[PDF] from arxiv.org
:view less
A2Event: A micro-watt programmable frequency-time detector for always-on energy-neutral sensing
2020
Philipp Mayer, Michele Magno, Luca Benini
Sustainable Computing: Informatics and Systems 25, 100368
:read more
Authors:Philipp Mayer, Michele Magno, Luca Benini
Publication date:03/01/2020
Journal:Sustainable Computing: Informatics and Systems
Volume:25
Pages:100368
Publisher:Elsevier
Description:Internet of Things (IoT) sensors are becoming more and more intelligence and unobtrusive, surrounding us in everyday life. A key requirement for those devices is to be “always-on” performing “smart” detection to catch only the events of interest when they occur. A recent and trend is to design low power circuit to extract features close to the sensors without an analog-digital conversion. The goal is to achieve place-and-forget deployment with perpetual operation: this poses the challenge of achieving micro-watt power consumption of the always-on analog event detector and of harvesting energy from environmental sources, to supply the smart sensor. This paper presents A2Event (Analog to Event), a microwatt programmable pattern recognition circuit for analog sensors, with up to 128 simultaneous time-frequency features exploiting mixed-signal low power design, which is able to generate an event when a targeted …
Cited by:12
Resources:[PDF] from sciencedirect.com
:view less
InfiniWolf: Energy efficient smart bracelet for edge computing with dual source energy harvesting
2020
Michele Magno, Xiaying Wang, Manuel Eggimann, Lukas Cavigelli, Luca Benini
arXiv preprint arXiv:2003.00041
:read more
Authors:Michele Magno, Xiaying Wang, Manuel Eggimann, Lukas Cavigelli, Luca Benini
Publication date:02/28/2020
Journal:arXiv preprint arXiv:2003.00041
Description:This work presents InfiniWolf, a novel multi-sensor smartwatch that can achieve self-sustainability exploiting thermal and solar energy harvesting, performing computationally high demanding tasks. The smartwatch embeds both a System-on-Chip (SoC) with an ARM Cortex-M processor and Bluetooth Low Energy (BLE) and Mr. Wolf, an open-hardware RISC-V based parallel ultra-low-power processor that boosts the processing capabilities on board by more than one order of magnitude, while also increasing energy efficiency. We demonstrate its functionality based on a sample application scenario performing stress detection with multi-layer artificial neural networks on a wearable multi-sensor bracelet. Experimental results show the benefits in terms of energy efficiency and latency of Mr. Wolf over an ARM Cortex-M4F micro-controllers and the possibility, under specific assumptions, to be self-sustainable using thermal and solar energy harvesting while performing up to 24 stress classifications per minute in indoor conditions.
Cited by:29
Resources:[PDF] from arxiv.org
:view less
FANN-on-MCU: An open-source toolkit for energy-efficient neural network inference at the edge of the Internet of Things
2020
Xiaying Wang, Michele Magno, Lukas Cavigelli, Luca Benini
IEEE Internet of Things Journal 7 (5), 4403-4417
:read more
Authors:Xiaying Wang, Michele Magno, Lukas Cavigelli, Luca Benini
Publication date:02/27/2020
Journal:IEEE Internet of Things Journal
Volume:7
Issue:5
Pages:4403-4417
Publisher:IEEE
Description:The growing number of low-power smart devices in the Internet of Things is coupled with the concept of “edge computing” that is moving some of the intelligence, especially machine learning, toward the edge of the network. Enabling machine learning algorithms to run on resource-constrained hardware, typically on low-power smart devices, is challenging in terms of hardware (optimized and energy-efficient integrated circuits), algorithmic, and firmware implementations. This article presents a FANN-on-MCU, an open-source toolkit built upon the fast artificial neural network (FANN) library to run lightweight and energy-efficient neural networks on microcontrollers based on both the ARM Cortex-M series and the novel RISC-V-based parallel ultralow-power (PULP) platform. The toolkit takes multilayer perceptrons trained with FANN and generates code targeted to low-power microcontrollers. This article also presents …
Cited by:199
Resources:[PDF] from arxiv.org
:view less
Opportunistic Cluster Heads for Heterogeneous Networks Combining LoRa and Wake-up Radio.
2020
Nour El Hoda Djidi, Antoine Courtay, Matthieu Gautier, Olivier Berder, Michele Magno
EWSN, 200-205
:read more
Authors:Nour El Hoda Djidi, Antoine Courtay, Matthieu Gautier, Olivier Berder, Michele Magno
Publication date:02/17/2020
Journal:EWSN
Pages:200-205
Description:Connected devices using LoRaWAN standard achieve low energy consumption by leaving their sleep state only to send their data. However, this technique induces a high downlink latency that is not compatible with applications that require a low latency such as remote control or actuatortype applications. To overcome this trade-off between power consumption and latency, we propose in this paper a MAC protocol design leveraging a heterogeneous network architecture composed of both long-range and ultra low power short-range wake-up radios. The proposed protocol does not change the LoRaWAN standard but at each uplink, a node operating in LoRa class A becomes an opportunistic cluster head and thus the gateway takes the opportunity of its receive windows to send commands intended to other nodes. Thanks to this novel network architecture and appropriate MAC protocol, the latency can be reduced while maintaining or even increasing the energy efficiency. Considering clusters of ten nodes, gains of 3.33 and 2.11 can be achieved in latency and power consumption, respectively.
Cited by:5
Resources:[PDF] from ewsn.org
:view less
Nanowatt clock and data recovery for ultra-low power wake-up receivers
2020
M D’Addato, A Antolini, F Renzini, AM Elgani, L Perilli, E Franchi Scarselli, A Gnudi, …
Proceedings of the 2020 International Conference on Embedded Wireless Systems and Netwo…
:read more
Authors:M D’Addato, A Antolini, F Renzini, AM Elgani, L Perilli, E Franchi Scarselli, A Gnudi, M Magno, R Canegallo
Publication date:02/01/2020
Journal:Proceedings of the 2020 International Conference on Embedded Wireless Systems and Networks (EWSN 2020), Lyon, France
Pages:17-19
Description:This paper presents the design of a data-startable baseband logic for wake-up receivers (WuRxs) enabling nodes to receive infinite bits in addition to a codeword. The proposed integrated circuit includes a control logic with addressing capabilities and a clock and data recovery (CDR) block based on a Gated Oscillator (GO). At each data transition the phase misalignment between received data and clock is compensated in a highly energy-efficient way thus allowing to correctly receive infinite bits. The difference between the Gated Oscillator free-running frequency and the bit-rate limits only the maximum number of equal consecutive bits that can be received. A design is presented in STMicroelectronics 90-nm BCD technology 1.2-V supply. Baseband logic has been supplied with 0.6 V to reduce overall consumption. The overall power consumption is 4.78 nW during the rest state and 9 pJ/bit at 1-kbps data rate. The …
Cited by:9
Resources:[PDF] from researchgate.net
:view less
An energy-efficient localization system for imprecisely positioned sensor nodes with flying UAVs
2020
Vlad Niculescu, Michele Magno, Daniele Palossi, Luca Benini
2020 IEEE 18th International Conference on Industrial Informatics (INDIN), 188-193
:read more
Authors:Vlad Niculescu, Michele Magno, Daniele Palossi, Luca Benini
Publication date:01/01/2020
Journal:2020 IEEE 18th International Conference on Industrial Informatics (INDIN)
Pages:188-193
Publisher:IEEE
Description:This work investigates the capability of unmanned aerial vehicles (UAVs) to find and communicate with wireless sensor nodes positioned at unknown locations. In this scenario, the UAV acts as a mobile gateway that estimates the sensor node position using multiple ultra-wideband (UWB) range measurements, before flying in its vicinity to perform energy-efficient data acquisition. In addition to UWB, we use wake-up radio (WUR) to improve the sensor node’s energy efficiency, keeping it in the always-on “low-activity” state when the drone is not nearby. The paper proposes a localization algorithm that consists of an iterative, noise-robust and computationally lightweight approach based on multi-lateration. Experimental evaluations performed on synthetic data demonstrate that our approach achieves a submeter localization accuracy using only three range measurements. We confirm this with an extensive in-field evaluation. The multilateration algorithm runs in 4 ms, in low power microcontrollers such as the ARM Cortex-M4F. The WUR and our energy-efficient algorithm enable the sensor node to consume only 31 mJ during the whole localization-acquisition process. Our solution can be introduced in many other industrial applications where a mobile robot needs to estimate the location of imprecisely positioned objects.
Cited by:6
Resources:[PDF] from ethz.ch
:view less
Piepser 2.0: A self-sustaining smartwatch to maximize the paragliders flytime
2019
Nicolas Baumann, Michael Ganz, Michele Magno
IEEE Transactions on Instrumentation and Measurement 69 (4), 1445-1454
:read more
Authors:Nicolas Baumann, Michael Ganz, Michele Magno
Publication date:12/10/2019
Journal:IEEE Transactions on Instrumentation and Measurement
Volume:69
Issue:4
Pages:1445-1454
Publisher:IEEE
Description:The main motivation of paraglider pilots is to stay in the air for as long as possible. Therefore, paraglider pilots are always searching for thermal upwind that allow them to gain altitude. These thermal lifts are difficult to detect. Therefore, sensors and devices that indicate the vertical speed (so-called variometers) are widely used among paraglider pilots. This article presents the design and the implementation of an ultralow-power, self-sustaining, high-precision, wrist-worn variometer with a minimal form factor but infinite lifetime, which can visually and acoustically indicate the vertical velocity. This article demonstrates the benefits of combining multisource energy harvesting (EH) for wearable devices with low power design, exploiting a novel near-threshold ARM Cortex-M4F microcontroller, the Ambiq Apollo2, for the onboard processing. The experimental results show a power consumption of only 17.12 μW in sleep …
Cited by:2
:view less
Tinybird: An energy neutral acoustic bluetooth-low-energy sensor node with rf energy harvesting
2019
Oliver Brunecker, Michele Magno
Proceedings of the 7th International Workshop on Energy Harvesting & Energy-Neutral Sen…
:read more
Authors:Oliver Brunecker, Michele Magno
Publication date:11/10/2019
Journal:Proceedings of the 7th International Workshop on Energy Harvesting & Energy-Neutral Sensing Systems
Pages:1-7
Description:Continuous advances in sensing and wireless technology now permit acoustic data acquisition and wireless transmission. With these technological developments, new application scenarios are a focal important for research theses. In particular in-vivo animal monitoring is a quickly growing domain, in which the wireless sensor needs to be placed on the animal's body and should be unobtrusive, light-weight, small, and long-lasting, or perpetually working. This paper presents the design and development of TinyBird, an ultra-low-power, miniaturized and lightweight wireless sensor node for acoustic monitoring. The node is designed to be worn with minimal effort by small-sized birds, to collect, process, and send/receive data to/from a remote host via Bluetooth Low-Energy. The main feature of the developed node is the capability to stream compressed or uncompressed audio data continuously. One unique feature of …
Cited by:5
Resources:[PDF] from researchgate.net
:view less
Low power embedded gesture recognition using novel short-range radar sensors
2019
Manuel Eggimann, Jonas Erb, Philipp Mayer, Michele Magno, Luca Benini
2019 IEEE SENSORS, 1-4
:read more
Authors:Manuel Eggimann, Jonas Erb, Philipp Mayer, Michele Magno, Luca Benini
Publication date:10/27/2019
Journal:2019 IEEE SENSORS
Pages:1-4
Publisher:IEEE
Description:This work proposes a low-power high-accuracy embedded hand-gesture recognition using low power short-range radar sensors. The hardware and software match the requirements for battery-operated wearable devices. A 2D Convolutional Neural Network (CNN) using range frequency Doppler features is combined with a Temporal Convolutional Neural Network (TCN) for time sequence prediction. The final algorithm has a model size of only 45723 parameters, yielding a memory footprint of only 91kB. Two datasets containing 11 challenging hand gestures performed by 26 different people have been recorded containing a total of 20210 gesture instances. On the 11 hands, gestures and an accuracy of 87% (26 users) and 92% (single user) have been achieved. Furthermore, the prediction algorithm has been implemented in the GAP8 Parallel Ultra-Low-Power processor by GreenWaves Technologies, showing …
Cited by:14
Resources:[PDF] from researchgate.net
:view less
Edgeeye: A long-range energy-efficient vision node for long-term edge computing
2019
Simon Benninger, Michele Magno, Andres Gomez, Luca Benini
2019 Tenth International Green and Sustainable Computing Conference (IGSC), 1-8
:read more
Authors:Simon Benninger, Michele Magno, Andres Gomez, Luca Benini
Publication date:10/21/2019
Journal:2019 Tenth International Green and Sustainable Computing Conference (IGSC)
Pages:1-8
Publisher:IEEE
Description:Recent Internet of Things (IoT) devices start to integrate data-intensive sensors such as cameras or microphones. To reduce the amount of data that needs to be transmitted to the cloud, an IoT device needs to process the data on-board, which is commonly referred to as edge computing. This paper presents a stand-alone, edge computing device called EdgeEye, capable of data-centric processing in the mW range. It employs a GAP8 processor which belongs to the PULP processor family to perform machine learning inference on images that were acquired with an ultra-low- power (ULP) camera. The results of the inference are transmitted using long-range communication (LoRa and LoRaWAN). EdgeEye is evaluated in the application scenario of people counting, using a newly proposed convolutional neural network that runs in the 8-cores of GAP8. The system performs the people recognition task (image …
Cited by:19
Resources:[PDF] from andresgomez.ch
:view less
A bluetooth-low-energy sensor node for acoustic monitoring of small birds
2019
Michele Magno, Fabien Vultier, Bence Szebedy, Homare Yamahachi, Richard HR Hahnloser, L…
IEEE Sensors Journal 20 (1), 425-433
:read more
Authors:Michele Magno, Fabien Vultier, Bence Szebedy, Homare Yamahachi, Richard HR Hahnloser, Luca Benini
Publication date:09/11/2019
Journal:IEEE Sensors Journal
Volume:20
Issue:1
Pages:425-433
Publisher:IEEE
Description:Animals can generate sounds that serve a wide range of vital functions such as to defend themselves or their territories, to attract a partner, to maintain contact with other members of their social group, and to help themselves and their partner/group during navigation. Ethologists are interested in recording and analyzing these sounds, many of which are vocalizations. Advances in sensing and wireless technology permit today acoustic data acquisition and transmission in a wireless manner. In many applications, the wireless sensor needs to be placed on the animal's body and should be unobtrusive, light-weight, small, and longlasting. This paper presents the design and development of an ultra-low power miniaturized and lightweight wireless sensor node for monitoring captive zebra finches. The node is designed to be worn with minimal effort by small-sized birds to collect, process, and send/receive data to/from a …
Cited by:30
:view less
Flexible and lightweight devices for wireless multi-color optogenetic experiments controllable via commercial cell phones
2019
Philipp Mayer, Nandhini Sivakumar, Michael Pritz, Matjia Varga, Andreas Mehmann, Seungh…
Frontiers in neuroscience 13, 819
:read more
Authors:Philipp Mayer, Nandhini Sivakumar, Michael Pritz, Matjia Varga, Andreas Mehmann, Seunghyun Lee, Alfredo Salvatore, Michele Magno, Matt Pharr, Helge C Johannssen, Gerhard Troester, Hanns Ulrich Zeilhofer, Giovanni Antonio Salvatore
Publication date:09/06/2019
Journal:Frontiers in neuroscience
Volume:13
Pages:819
Publisher:Frontiers Media SA
Description:Optogenetics provide a potential alternative approach to the treatment of chronic pain, in which complex pathology often hampers efficacy of standard pharmacological approaches. Technological advancements in the development of thin, wireless, and mechanically flexible optoelectronic implants offer new routes to control the activity of subsets of neurons and nerve fibers in vivo. This study reports a novel and advanced design of battery-free, flexible, and lightweight devices equipped with one or two miniaturized LEDs, which can be individually controlled in real time. Two proof-of-concept experiments in mice demonstrate the feasibility of these devices. First, we show that blue-light devices implanted on top of the lumbar spinal cord can excite channelrhodopsin expressing nociceptors to induce place aversion. Second, we show that nocifensive withdrawal responses can be suppressed by green-light optogenetic (Archaerhodopsin-mediated) inhibition of action potential propagation along the sciatic nerve. One salient feature of these devices is that they can be operated via modern tablets and smartphones without bulky and complex lab instrumentation. In addition to the optical stimulation, the design enables the simultaneously wireless recording of the temperature in proximity of the stimulation area. As such, these devices are primed for translation to human patients with implications in the treatment of neurological and psychiatric conditions far beyond chronic pain syndromes.
Cited by:25
Resources:[HTML] from frontiersin.org
:view less
Experimental evaluation on NB-IoT and LoRaWAN for industrial and IoT applications
2019
Massimo Ballerini, Tommaso Polonelli, Davide Brunelli, Michele Magno, Luca Benini
2019 IEEE 17th International Conference on Industrial Informatics (INDIN) 1, 1729-1732
:read more
Authors:Massimo Ballerini, Tommaso Polonelli, Davide Brunelli, Michele Magno, Luca Benini
Publication date:07/22/2019
Journal:2019 IEEE 17th International Conference on Industrial Informatics (INDIN)
Volume:1
Pages:1729-1732
Publisher:IEEE
Description:Low power and long-range communications are essential features of the Internet of Things (IoT) paradigm that is becoming widespread across a spectrum of industrial applications. In this paper, we present performance evaluation of the most promising long-range communication technologies, namely LoRaWAN and NB-IoT. We present accurate in-field measurements using a monitoring application as a testbench for a fair comparison in terms of energy efficiency and lifetime. Experimental results highlight that NB-IoT payload length does not impact on transmission energy. Thus, applications that implement buffering and caching techniques are favored. On the other hand, LoRaWAN consumes 10× less energy to transmit a payload equivalent to that of NB-IoT, thereby allowing longer end-device lifetime.
Cited by:23
Resources:[PDF] from researchgate.net
:view less
Self-sustainable smart ring for long-term monitoring of blood oxygenation
2019
Michele Magno, Giovanni A Salvatore, Petar Jokic, Luca Benini
IEEE access 7, 115400-115408
:read more
Authors:Michele Magno, Giovanni A Salvatore, Petar Jokic, Luca Benini
Publication date:07/11/2019
Journal:IEEE access
Volume:7
Pages:115400-115408
Publisher:IEEE
Description:Medical devices measure vital parameters such as pulse, respiration rate, and blood oxygenation, over periods of days or weeks in a continuous manner. Traditional systems only support such requirements in stationary applications where a constant power supply is available. Trends toward remote healthcare and telemedicine require wearable devices, able to provide similar functionalities in wireless mode. Miniaturized and thin form factors, desirable in wearable applications, set stringent constraints on the available power, and consequently on the accuracy and lifetime. Energy harvesting combined with low-power design and energy efficient processing can significantly extend the lifetime of wearable devices. This paper presents a wearable pulse oximeter assembled in a 3D ring-like geometry that achieves self-sustainability by exploiting efficient power management, solar energy harvesting, and ultra-low …
Cited by:60
Resources:[PDF] from ieee.org
:view less
SmarTEG: An autonomous wireless sensor node for high accuracy accelerometer-based monitoring
2019
Michele Magno, Lukas Sigrist, Andres Gomez, Lukas Cavigelli, Antonio Libri, Emanuel Pop…
Sensors 19 (12), 2747
:read more
Authors:Michele Magno, Lukas Sigrist, Andres Gomez, Lukas Cavigelli, Antonio Libri, Emanuel Popovici, Luca Benini
Publication date:06/19/2019
Journal:Sensors
Volume:19
Issue:12
Pages:2747
Publisher:MDPI
Description:We report on a self-sustainable, wireless accelerometer-based system for wear detection in a band saw blade. Due to the combination of low power hardware design, thermal energy harvesting with a small thermoelectric generator (TEG), an ultra-low power wake-up radio, power management and the low complexity algorithm implemented, our solution works perpetually while also achieving high accuracy. The onboard algorithm processes sensor data, extracts features, performs the classification needed for the blade’s wear detection, and sends the report wirelessly. Experimental results in a real-world deployment scenario demonstrate that its accuracy is comparable to state-of-the-art algorithms executed on a PC and show the energy-neutrality of the solution using a small thermoelectric generator to harvest energy. The impact of various low-power techniques implemented on the node is analyzed, highlighting the benefits of onboard processing, the nano-power wake-up radio, and the combination of harvesting and low power design. Finally, accurate in-field energy intake measurements, coupled with simulations, demonstrate that the proposed approach is energy autonomous and can work perpetually.
Cited by:26
Resources:[HTML] from mdpi.com
:view less
LoRa vs. LoRa: In-field evaluation and comparison for long-lifetime sensor nodes
2019
Philipp Mayer, Michele Magno, Thomas Brunner, Luca Benini
2019 IEEE 8th International Workshop on Advances in Sensors and Interfaces (IWASI), 307…
:read more
Authors:Philipp Mayer, Michele Magno, Thomas Brunner, Luca Benini
Publication date:06/13/2019
Journal:2019 IEEE 8th International Workshop on Advances in Sensors and Interfaces (IWASI)
Pages:307-311
Publisher:IEEE
Description:Low-power and long-range communication have emerged as a promising technology for long lifetime Internet of Things devices and applications. LoRa is one of the most popular solution for low-power and long-range communication in IoT, providing mW power consumption and km range with few kB of throughput. Recently Semtech, the only LoRa transceiver producer, released the SX126X, a novel and optimized version of its popular SX1276 transceiver. Semtech promises lower power and higher range for the new transceiver. This paper analyzes and compares the power consumption of the two transceivers with experimental in-field measurements. Moreover, the paper presents a smart sensor node for the long term and long-range monitoring that use the novel transceiver to transmit data to a remote gateway. Experimental evaluation shows the improvements of the new SX126x transceiver with up to 72% of …
Cited by:25
Resources:[PDF] from researchgate.net
:view less
A RISC-V based open hardware platform for always-on wearable smart sensing
2019
Manuel Eggimann, Stefan Mach, Michele Magno, Luca Benini
2019 IEEE 8th International Workshop on Advances in Sensors and Interfaces (IWASI), 169…
:read more
Authors:Manuel Eggimann, Stefan Mach, Michele Magno, Luca Benini
Publication date:06/13/2019
Journal:2019 IEEE 8th International Workshop on Advances in Sensors and Interfaces (IWASI)
Pages:169-174
Publisher:IEEE
Description:We present a fully programmable ultra-low-power embedded platform that hosts an "electronic skin" (E-skin) arrays of tactile sensors with up to 64 channels, ECG/EMG sensors up to 8 channels, inertial sensors, and a Bluetooth Low Energy 5.0 module. The platform's compute engine is a heterogeneous multi-core parallel ultra-low power (PULP) processor based on RISC-V, capable of delivering up to 2.5 GOPS, within a 55 mW power consumption envelope, which makes the platform ideal for battery-powered always-on operation. Experimental results show a peak of 38.3x energy efficiency increase (0.7 V, 85 MHz) compared to ARM-Cortex-M microcontrollers with similar power budgets.
Cited by:33
Resources:[PDF] from researchgate.net
:view less
Netwis: A scalable and robust body sensor network for biomedical application
2019
Massimo Ballerini, Michele Magno, Davide Brunelli, Guido Cornai, Luca Benini
2019 IEEE 8th International Workshop on Advances in Sensors and Interfaces (IWASI), 118…
:read more
Authors:Massimo Ballerini, Michele Magno, Davide Brunelli, Guido Cornai, Luca Benini
Publication date:06/13/2019
Journal:2019 IEEE 8th International Workshop on Advances in Sensors and Interfaces (IWASI)
Pages:118-123
Publisher:IEEE
Description:Wireless wearable sensors have developed rapidly in recent years, primarily driven by e-health, fitness and wellness applications. The technological evolution of low power microprocessors is enabling to process data locally, saving energy and bandwidth and increasing the overall throughput of the wireless network. This paper presents a new general-purpose Inertial Measure Unit that exploits a dual-core architecture. A core offers processing capability, and the other one is a radio interface IEEE 802.15.4. We propose the whole system and a protocol to maximize the throughput, reduce the packet loss and improve the robustness of wireless sensor nodes communication. Experimental results show that our solution offers better data throughput for configurations below 10 nodes compared to widely used commercial wireless sensor nodes. The paper also presents an experimental evaluation of scalability (up to 10 …
Cited by:2
Resources:[PDF] from researchgate.net
:view less
Wireless power transmission powering miniaturized low power IoT devices: A Revie
2019
Louis Meile, Anja Ulrich, Michele Magno
2019 IEEE 8th International Workshop on Advances in Sensors and Interfaces (IWASI), 312…
:read more
Authors:Louis Meile, Anja Ulrich, Michele Magno
Publication date:06/13/2019
Journal:2019 IEEE 8th International Workshop on Advances in Sensors and Interfaces (IWASI)
Pages:312-317
Publisher:IEEE
Description:Energy Harvesting (EH) is a mature solution to extend the short lifetime of many wireless sensor nodes and IoT devices. However, miniaturizing EH devices to supply low power and small form factor IoT devices is still challenging and not always effective. In fact, EH from the miniaturized is more challenging due to strict constraints in terms of size, weight, and cost. Among other technologies, wireless power transmission is growing of popularity due to the fact that it can be controlled and it is less unpredictable than environments sources. This paper presents a review of technologies for wireless power transmission that can supply cm-scale low power IoT devices. Additionally, this paper provides in-field evaluation with mm-scale antennas of radio frequency power transmission using a commercial system: Powercast. Experimental results focus on evaluating the power flowing in the battery, which also includes the …
Cited by:29
Resources:[PDF] from researchgate.net
:view less
Energy-autonomous on-rotor RPM sensor using variable reluctance energy harvesting
2019
Ye Xu, Sebastian Bader, Michele Magno, Philipp Mayer, Bengt Oelmann
2019 IEEE 8th International Workshop on Advances in Sensors and Interfaces (IWASI), 175…
:read more
Authors:Ye Xu, Sebastian Bader, Michele Magno, Philipp Mayer, Bengt Oelmann
Publication date:06/13/2019
Journal:2019 IEEE 8th International Workshop on Advances in Sensors and Interfaces (IWASI)
Pages:175-180
Publisher:IEEE
Description:Energy-autonomous wireless sensor systems have the potential to enable condition monitoring without the need for a wired electrical infrastructure or capacity-limited batteries. In this paper, a robust and low-cost energy-autonomous wireless rotational speed sensor is presented, which harvests energy from the rotary motion of its host using the variable reluctance principle. A microelectromechanical system (MEMS) gyroscope is utilized for angular velocity measurements, and a Bluetooth Low Energy System-on-Chip (SoC) transmits the acquired samples wirelessly. An analysis on the individual subsystems is performed, investigating the output of the energy transducer, the required energy by the load, and energy losses in the whole system. The results of simulations and experimental measurements on a prototype implementation show that the system achieves energy-autonomous operation with sample rates …
Cited by:8
Resources:[PDF] from researchgate.net
:view less
An energy efficient system for touch modality classification in electronic skin applications
2019
Mario Osta, Ali Ibrahim, Michele Magno, Manuel Eggimann, Antonio Pullini, Paolo Gastald…
2019 IEEE International Symposium on Circuits and Systems (ISCAS), 1-4
:read more
Authors:Mario Osta, Ali Ibrahim, Michele Magno, Manuel Eggimann, Antonio Pullini, Paolo Gastaldo, Maurizio Valle
Publication date:05/26/2019
Journal:2019 IEEE International Symposium on Circuits and Systems (ISCAS)
Pages:1-4
Publisher:IEEE
Description:Electronic-skin aiming to mimic human skin is becoming a reality and systems able to process data close to the sensors are required to reduce latency and power consumption. This paper presents the design and implementation of an energy efficient smart system for tactile sensing based on a RISC-V parallel ultra-low power platform (PULP). The PULP processor, called Mr. Wolf, performs the on-board classification of different touch modalities. This demonstrates the promising use of on-board classification for emerging robot and prosthetic applications. Experimental results demonstrate the effectiveness of the platform on improving the energy efficiency of the online classification. In our experiments, Mr. Wolf runs 3.6 times faster than an ARM Cortex M4F (STM32F40), consuming only 28 mW. The proposed platform achieves 15× better energy efficiency, than the classification done on the STM32F40, consuming …
Cited by:23
Resources:[PDF] from researchgate.net
:view less
Fanncortexm: An open source toolkit for deployment of multi-layer neural networks on arm cortex-m family microcontrollers: Performance analysis with stress detection
2019
Michele Magno, Lukas Cavigelli, Philipp Mayer, Ferdinand Von Hagen, Luca Benini
2019 IEEE 5th World Forum on Internet of Things (WF-IoT), 793-798
:read more
Authors:Michele Magno, Lukas Cavigelli, Philipp Mayer, Ferdinand Von Hagen, Luca Benini
Publication date:04/15/2019
Journal:2019 IEEE 5th World Forum on Internet of Things (WF-IoT)
Pages:793-798
Publisher:IEEE
Description:We present FANNCortexM, an open-source toolkit built upon the Fast Artificial Neural Network (FANN) library to run lightweight neural networks on ARM Cortex-M series microcontrollers. The toolkit takes a neural network trained with FANN and generates code targeted at execution on low-power microcontrollers either with a floating-point unit (i.e., ARM Cortex-M4F and M7F) or without a floating-point unit (i.e., ARM Cortex M0-M3). The toolkit is optimized in terms of memory and computational resources. We demonstrate its functionality on the basis of a sample application scenario performing stress detection on a wearable multi-sensor bracelet. Experimental results show a high classification accuracy of 96% for the target application scenario, and low latency of only a few microseconds while keeping the memory requirements (11kB flash storage, 36kB RAM) far below the limitations of the device. Power …
Cited by:17
Resources:[PDF] from ethz.ch
:view less
EmbedUWB: Low power embedded high-precision and low latency UWB localization
2019
Philipp Mayer, Michele Magno, Christoph Schnetzler, Luca Benini
2019 IEEE 5th World Forum on Internet of Things (WF-IoT), 519-523
:read more
Authors:Philipp Mayer, Michele Magno, Christoph Schnetzler, Luca Benini
Publication date:04/15/2019
Journal:2019 IEEE 5th World Forum on Internet of Things (WF-IoT)
Pages:519-523
Publisher:IEEE
Description:Positioning based on Ultra-wideband (UWB) wireless communication promises multipath immunity, high resolution, and strong wall penetration. Hence, many academic and industrial researchers are proposing UWB positioning systems especially to track and locate objects and person in indoor environments. UWB indoor localization, based on stationary "anchors" tracking mobile "tags", is already a reality in many application scenarios. However, most of the available systems either perform tracking on servers which collect data from tags and anchors or delegate to the anchors to calculate the actual position of the tags. Both approaches imply long latency and limited throughput in terms of position fixes per unit time. In this paper, we present the design and the implementation of a highly accurate and low latency asymmetric double-sided two-way ranging algorithm that runs at very modest energy budget on low …
Cited by:29
Resources:[PDF] from researchgate.net
:view less
Energy harvesting meets iot: Fuelling adoption of transient computing in embedded systems
2019
Domenico Balsamo, Michele Magno, Kacper Kubara, Bogdan Lazarescu, Geoff V Merrett
2019 IEEE 5th World Forum on Internet of Things (WF-IoT), 413-417
:read more
Authors:Domenico Balsamo, Michele Magno, Kacper Kubara, Bogdan Lazarescu, Geoff V Merrett
Publication date:04/15/2019
Journal:2019 IEEE 5th World Forum on Internet of Things (WF-IoT)
Pages:413-417
Publisher:IEEE
Description:The emerging class of transient computing systems enables computation to be sustained despite power outages due to the variable nature of energy harvesting. However, existing approaches are largely designed for specific architectures, and hence are not broadly applicable across different IoT devices. Emerging platforms based on portable, hardware-independent software should rely on lightweight operating systems (OSs) designed specifically for embedded IoT applications, such as Arm mbed OS and Contiki OS. To enable the widespread use of transient computing, transient approaches need to be integrated into these operating systems. In this paper, we discuss the challenges of providing software primitives for transient computing to facilitate hardware-independent implementation using standard OS APIs, and present the integration of a state-of-art transient approach, Hibernus into mbed OS. This OS is …
Cited by:21
Resources:[PDF] from soton.ac.uk
:view less
ZeroPowerTouch: Zero-Power Smart Receiver for Touch Communication and Sensing in Wearable Applications
2019
Philipp Mayer, Raphael Strebel, Michele Magno
2019 Design, Automation & Test in Europe Conference & Exhibition (DATE), 944-947
:read more
Authors:Philipp Mayer, Raphael Strebel, Michele Magno
Publication date:03/25/2019
Journal:2019 Design, Automation & Test in Europe Conference & Exhibition (DATE)
Pages:944-947
Publisher:IEEE
Description:The human body can be used as a transmission medium for electric fields. By applying an electric field with a frequency of decades of megahertz to isolated electrodes on the human body, it is possible to send energy and data. Extra body and intra-body communication is an interesting alternative way to communicate wirelessly in the new era of wearable device and internet of things. This promising communication works without the need to design dedicate radio hardware and with lower power consumption. We designed and implemented a novel zero-power receiver targeting intra-body and extra-body wireless communication and touch sensing. To achieve zero-power and always-on working, we combined ultra-low power design and an energy-harvesting subsystem, which extracts energy directly from the received message. This energy is then employed to supply the whole receiver to demodulate the message …
Cited by:1
Resources:[PDF] from researchgate.net
:view less
Piepser: A smart wrist-worn variometer to maximize the paragliders flytime
2019
Tim Fischer, Michael Ganz, Nicolas Baumann, Michele Magno
2019 IEEE Sensors Applications Symposium (SAS), 1-6
:read more
Authors:Tim Fischer, Michael Ganz, Nicolas Baumann, Michele Magno
Publication date:03/11/2019
Journal:2019 IEEE Sensors Applications Symposium (SAS)
Pages:1-6
Publisher:IEEE
Description:The goal or the motivation for paraglider pilots is to stay as long in the air as possible. Therefore paraglider pilots are always searching for thermal upwinds that allow them to gain altitude. These thermal lifts are difficult to detect as we cannot see them with our eyes and we can only feel the vertical acceleration but not the vertical speed with our body. Therefore devices which indicate the vertical speed (so called Variometers) are widely used among paraglider pilots. The main goal for this paper is to design and to implement a low-power, low-cost and wearable variometer with a minimal formfactor but long lifetime, which can display and indicate the vertical velocity. Experimental results show a power consumption of 6.27mW at full load. We managed to achieve a price point of 30.2 CHF per unit and a device volume of 47x47x25 [mm] at a weight of 43 grams. The wearable variometer is designed around the novel …
Cited by:2
:view less
SmartAid: A Low-Power Smart Hearing Aid For Stutterers
2019
Moritz Scherer, Kiran Menachery, Michele Magno
2019 IEEE Sensors Applications Symposium (SAS), 1-6
:read more
Authors:Moritz Scherer, Kiran Menachery, Michele Magno
Publication date:03/11/2019
Journal:2019 IEEE Sensors Applications Symposium (SAS)
Pages:1-6
Publisher:IEEE
Description:Interdisciplinary projects combining biomedical and electrical engineering pose an interesting opportunity for today's society. In the future, more and more people will have to rely on wearable devices to monitor and understand biological variables. One of the most key challenges is the design of wearable devices that operate reliably and autonomously for long periods using small batteries. In this paper, we present the design of a novel smart hearing aid for stutterers in which an event-driven architecture is used to minimize power consumption, and onboard processing and actuators help the user to stop stuttering. The design has been implemented using a novel Ambiq Apollo 2 Blue processor, which includes a 5.0 Bluetooth interface with the lowest power consumption on the market and tested in the field. The microcontroller performs the data analyses directly onboard actuating a speaker to help the user when …
Cited by:5
Resources:[PDF] from researchgate.net
:view less
Hidden markov model-based asthmatic wheeze recognition algorithm leveraging the parallel ultra-low-power processor (pulp)
2019
Dinko Oletic, Marko Matijascic, Vedran Bilas, Michele Magno
2019 IEEE Sensors Applications Symposium (SAS), 1-6
:read more
Authors:Dinko Oletic, Marko Matijascic, Vedran Bilas, Michele Magno
Publication date:03/11/2019
Journal:2019 IEEE Sensors Applications Symposium (SAS)
Pages:1-6
Publisher:IEEE
Description:Asthmatic symptoms can be quantified by a wearable sensor system, recording respiratory sounds on patient's skin surface, and performing automated asthmatic wheeze recognition based on time-frequency features. In order to enable long-term autonomy of such sensor system, a crucial design requirement is ensuring energy-efficient yet accurate wheeze recognition performance. We presented a Hidden Markov Model-based algorithm for recognition of wheezing intervals durations, by sequentially extracting individual wheezing-frequency lines from the spectrogram of respiratory sounds. In this paper we compare its implementation on an ARM Cortex-M4 processor and an emerging parallel ultra-low-power processing platform PULP Fulmine. It is shown that the algorithm enables wheeze recognition with 82.85% of sensitivity and 95.61% specificity, for only 0.9-1.6 mW of power. It is experimentally verified that …
Cited by:3
:view less
Self-sustaining acoustic sensor with programmable pattern recognition for underwater monitoring
2019
Philipp Mayer, Michele Magno, Luca Benini
IEEE transactions on instrumentation and measurement 68 (7), 2346-2355
:read more
Authors:Philipp Mayer, Michele Magno, Luca Benini
Publication date:01/20/2019
Journal:IEEE transactions on instrumentation and measurement
Volume:68
Issue:7
Pages:2346-2355
Publisher:IEEE
Description:Minimizing the power consumption of always-on sensors is crucial for extending the lifetime of battery-operated devices that are required to monitor events continuously and for long periods. This paper proposes a novel programmable μW event-driven acoustic detector featuring “always-on” audio pattern recognition. The event-driven detector detects up to eight programmable spectral-temporal features extracted with a low-power single-channel analog circuit and classifies the features by an onboard microcontroller. The event-driven detector is combined with novel microbial fuel cells (MFCs) to achieve self-sustainability in an underwater scenario. Experimental results demonstrate that the power consumption of the detector is only 26.89 μW during always-on mode, achieving up to 59-dB sound pressure level of sensitivity. High detection accuracy of up to 95.89% in recognizing acoustic patterns has been …
Cited by:48
Resources:[PDF] from researchgate.net
:view less
Dataset supporting the article entitled” Energy Harvesting Meets IoT: Fuelling Adoption of Transient Computing in Embedded Systems”
2019
Domenico Balsamo, Michele Magno, Kacper Kubara, Bogdan Lazarescu, Geoff Merrett, Oktay …
:read more
Authors:Domenico Balsamo, Michele Magno, Kacper Kubara, Bogdan Lazarescu, Geoff Merrett, Oktay Cetinkaya
Publication date:01/01/2019
Publisher:University of Southampton
Description:This dataset supports the article entitled: "Energy Harvesting Meets IoT: Fuelling Adoption of Transient Computing in Embedded Systems" accepted for publication in The IEEE 5th World Forum on Internet of Things (WF-IoT).
:view less
Nanowatt wake-up radios: Discrete-components and integrated architectures
2018
Alessia Elgani, Michele Magno, Francesco Renzini, Luca Perilli, E Franchi Scarselli, An…
2018 25th IEEE international conference on electronics, circuits and systems (ICECS), 7…
:read more
Authors:Alessia Elgani, Michele Magno, Francesco Renzini, Luca Perilli, E Franchi Scarselli, Antonio Gnudi, Roberto Canegallo, Giulio Ricotti, Luca Benini
Publication date:12/09/2018
Journal:2018 25th IEEE international conference on electronics, circuits and systems (ICECS)
Pages:793-796
Publisher:IEEE
Description:This work focuses on nano-watt wake-up radio architectures designed to improve the energy efficiency of medium range wireless communication. An integrated solution is presented with the aim of pushing the sensitivity vs. power trade-off to the limit. The key blocks are an envelope detector based on a MOSFET operated in the subthreshold region and an amplifier partly sharing the same bias current. According to simulations, a design based on the STMicroelectronics 90-nm BCD technology achieves an estimated -54-dBm sensitivity at 1.2-V supply with 11-nA total bias current for the envelope detector, the amplifier and the Schmitt trigger. We also present a comparison between integrated solutions and a solution based on discrete components in terms of power consumption, bitrate, addressing capabilities and sensitivity.
Cited by:20
Resources:[PDF] from researchgate.net
:view less
A wake-up radio-based MAC protocol for autonomous wireless sensor networks
2018
Alain Pegatoquet, Trong Nhan Le, Michele Magno
IEEE/ACM Transactions on Networking 27 (1), 56-70
:read more
Authors:Alain Pegatoquet, Trong Nhan Le, Michele Magno
Publication date:11/29/2018
Journal:IEEE/ACM Transactions on Networking
Volume:27
Issue:1
Pages:56-70
Publisher:IEEE
Description:Wireless sensor networks (WSNs) with energy harvesting capabilities have drawn increasing attention in the last few years, as they enable long-term monitoring applications. However, the level of power harvested is usually limited to few mW. To improve the energy efficiency of WSNs, many power management techniques have been proposed to adjust the quality of service according to the harvested energy fluctuations. As wireless communications consume a major fraction of the available energy, numerous medium access control (MAC) protocols have been proposed to minimize energy consumption, latency, and data collisions. In this paper, we present an innovative MAC protocol for energy-harvesting based WSNs exploiting ultralow-power wake-up radios. To overcome the limited range typical of wake-up radios, a multi-hop wake-up scheme based on a dual radio system is proposed enabling asynchronous …
Cited by:57
Resources:[PDF] from researchgate.net
:view less
FPGA implementation of a Kalman-based motion estimator for levitated nanoparticles
2018
Jiawei Liao, Michael Jost, Michael Schaffner, Michele Magno, Matthias Korb, Luca Benini…
IEEE Transactions on Instrumentation and Measurement 68 (7), 2374-2386
:read more
Authors:Jiawei Liao, Michael Jost, Michael Schaffner, Michele Magno, Matthias Korb, Luca Benini, Felix Tebbenjohanns, Rene Reimann, Vijay Jain, Michael Gross, Andrei Militaru, Martin Frimmer, Lukas Novotny
Publication date:11/21/2018
Journal:IEEE Transactions on Instrumentation and Measurement
Volume:68
Issue:7
Pages:2374-2386
Publisher:IEEE
Description:Optically trapped nanoparticles are used in various fields ranging from biophysics to precision sensing. An optically trapped nanoparticle can be regarded as a harmonic oscillator driven by the thermal fluctuations of its environment. Unlocking the potential of optically levitated systems for precision measurements in the classical and the quantum regime requires cooling of the particle motion. In parametric feedback cooling, the center-of-mass motion of a nanoparticle optically levitated in a vacuum is reduced by temporally modulating the optical trapping potential. This technique requires a precise measurement of the particle's motion to derive the feedback signal and is prone to measurement noise and inevitable thermal process noise. In a state-of-the-art implementation, the feedback signal is derived from a simple phase-locked loop (PLL). Kalman filters are regularly deployed in a variety of application scenarios to …
Cited by:21
Resources:[PDF] from academia.edu
:view less
On-demand LoRa: Asynchronous TDMA for energy efficient and low latency communication in IoT
2018
Rajeev Piyare, Amy L Murphy, Michele Magno, Luca Benini
Sensors 18 (11), 3718
:read more
Authors:Rajeev Piyare, Amy L Murphy, Michele Magno, Luca Benini
Publication date:11/01/2018
Journal:Sensors
Volume:18
Issue:11
Pages:3718
Publisher:MDPI
Description:Energy efficiency is crucial in the design of battery-powered end devices, such as smart sensors for the Internet of Things applications. Wireless communication between these distributed smart devices consumes significant energy, and even more when data need to reach several kilometers in distance. Low-power and long-range communication technologies such as LoRaWAN are becoming popular in IoT applications. However, LoRaWAN has drawbacks in terms of (i) data latency; (ii) limited control over the end devices by the gateway; and (iii) high rate of packet collisions in a dense network. To overcome these drawbacks, we present an energy-efficient network architecture and a high-efficiency on-demand time-division multiple access (TDMA) communication protocol for IoT improving both the energy efficiency and the latency of standard LoRa networks. We combine the capabilities of short-range wake-up radios to achieve ultra-low power states and asynchronous communication together with the long-range connectivity of LoRa. The proposed approach still works with the standard LoRa protocol, but improves performance with an on-demand TDMA. Thanks to the proposed network and protocol, we achieve a packet delivery ratio of 100% by eliminating the possibility of packet collisions. The network also achieves a round-trip latency on the order of milliseconds with sensing devices dissipating less than 46 mJ when active and 1.83 μW during periods of inactivity and can last up to three years on a 1200-mAh lithium polymer battery.
Cited by:144
Resources:[HTML] from mdpi.com
:view less
A self-sustaining micro-watt programmable smart audio sensor for always-on sensing
2018
Michele Magno, Philipp Mayer, Luca Benini
2018 Ninth International Green and Sustainable Computing Conference (IGSC), 1-8
:read more
Authors:Michele Magno, Philipp Mayer, Luca Benini
Publication date:10/22/2018
Journal:2018 Ninth International Green and Sustainable Computing Conference (IGSC)
Pages:1-8
Publisher:IEEE
Description:Self-sustainable always-on sensors are crucial for the Internet of Things and its emerging applications. However, achieving perpetual work with active sensors poses many challenges, especially in ultra-low power design and micro-power energy harvesting that can supply the sensors. This paper presents a self-sustaining programmable smart microphone, combining energy harvesting and a micro-power event-driven sensor. The proposed solution can achieve programmable pattern recognition with up to 128 simultaneous time-frequency features exploiting mixed-signal low power design. Experimental results show that the designed event-driven circuit consumes only 26.89 μW in always-on mode, during the time-frequency feature-extraction, while the whole system consumes only 63 μW during pattern recognition including the power for a commercial MEMS microphone and the energy harvesting subsystem. We …
Cited by:3
Resources:[PDF] from researchgate.net
:view less
Embedded classification of local field potentials recorded from rat barrel cortex with implanted multi-electrode array
2018
Xiaying Wang, Michele Magno, Lukas Cavigelli, Mufti Mahmud, Claudia Cecchetto, Stefano …
2018 IEEE Biomedical Circuits and Systems Conference (BioCAS), 1-4
:read more
Authors:Xiaying Wang, Michele Magno, Lukas Cavigelli, Mufti Mahmud, Claudia Cecchetto, Stefano Vassanelli, Luca Benini
Publication date:10/17/2018
Journal:2018 IEEE Biomedical Circuits and Systems Conference (BioCAS)
Pages:1-4
Publisher:IEEE
Description:This paper focuses on ultra-low power embedded classification of neural activities. The machine learning (ML) algorithm has been trained using evoked local field potentials (LFPs) recorded with an implanted 16×16 multi-electrode array (MEA) from the rat barrel cortex while stimulating the whisker. Experimental results demonstrate that ML can be successfully applied to noisy single-trial LFPs. We achieved up to 95.8% test accuracy in predicting the whisker deflection. The trained ML model is successfully implemented on a low-power embedded system with an average consumption of 2.6 mW.
Cited by:14
Resources:[PDF] from ethz.ch
:view less
On-demand TDMA for energy efficient data collection with LoRa and wake-up receiver
2018
Rajeev Piyare, Amy L Murphy, Michele Magno, Luca Benini
2018 14th International Conference on Wireless and Mobile Computing, Networking and Com…
:read more
Authors:Rajeev Piyare, Amy L Murphy, Michele Magno, Luca Benini
Publication date:10/15/2018
Journal:2018 14th International Conference on Wireless and Mobile Computing, Networking and Communications (WiMob)
Pages:1-4
Publisher:IEEE
Description:Low-power and long-range communication technologies such as LoRa are becoming popular in IoT applications due to their ability to cover kilometers range with milliwatt of power consumption. One of the major drawbacks of LoRa is the data latency and the traffic congestion when the number of devices in the network increases. Especially, the latency arises due to the extreme duty cycling of LoRa end-nodes for reducing the overall energy consumption. To overcome this drawback, we propose a heterogeneous network architecture and an energy-efficient On-demand TDMA communication scheme improving both the device lifetime and the data latency of standard LoRa networks. We combine the capabilities of micro-watt wake-up receivers to achieve ultra-low power states and pure asynchronous communication together with the long-range connectivity of LoRa. Experimental results show a data reliability of …
Cited by:50
Resources:[PDF] from arxiv.org
:view less
KRATOS: An Open Source Hardware-Software Platform for Rapid Research in LPWANs
2018
Rajeev Piyare, Amy L Murphy, Michele Magno, Luca Benini
2018 14th International Conference on Wireless and Mobile Computing, Networking and Com…
:read more
Authors:Rajeev Piyare, Amy L Murphy, Michele Magno, Luca Benini
Publication date:10/15/2018
Journal:2018 14th International Conference on Wireless and Mobile Computing, Networking and Communications (WiMob)
Pages:1-4
Publisher:IEEE
Description:Long-range (LoRa) radio technologies have recently gained momentum in the IoT landscape, allowing low-power communications over distances up to several kilometers. As a result, more and more LoRa networks are being deployed. However, commercially available LoRa devices are expensive and propriety, creating a barrier to entry and possibly slowing down developments and deployments of novel applications. Using open-source hardware and software platforms would allow more developers to test and build intelligent devices resulting in a better overall development ecosystem, lower barriers to entry, and rapid growth in the number of IoT applications. Toward this goal, this paper presents the design, implementation, and evaluation of KRATOS, a low-cost LoRa platform running ContikiOS. Both, our hardware and software designs are released as an open-source to the research community.
Cited by:11
Resources:[PDF] from arxiv.org
:view less
Rat cortical layers classification extracting evoked local field potential images with implanted multi-electrode sensor
2018
Xiaying Wang, Michele Magno, Lukas Cavigelli, Mufti Mahmud, Claudia Cecchetto, Stefano …
2018 IEEE 20th International Conference on e-Health Networking, Applications and Servic…
:read more
Authors:Xiaying Wang, Michele Magno, Lukas Cavigelli, Mufti Mahmud, Claudia Cecchetto, Stefano Vassanelli, Luca Benini
Publication date:09/17/2018
Journal:2018 IEEE 20th International Conference on e-Health Networking, Applications and Services (Healthcom)
Pages:1-6
Publisher:IEEE
Description:One of the most ambitious goals of neuroscience and its neuroprosthetic applications is to interface intelligent electronic devices with the biological brain to cure neurological diseases. This emerging research field builds on our growing understanding of brain circuits and on recent technological advances in miniaturization of implantable multi-electrode-arrays (MEAs) to record brain signals at high spatiotemporal resolution. Data processing is needed to extract useful information from the recorded neural activity to better understand the function of underlying neural circuits and, in perspective, to operate neuroprosthetic devices. In this context, machine learning approaches are increasingly used in many application scenarios. This paper focuses on processing data of evoked local field potentials (LFPs) recorded from the rat barrel cortex using a miniaturized 16×16 MEA. We evaluated machine learning algorithms …
Cited by:8
Resources:[PDF] from ethz.ch
:view less
Micro kinetic energy harvesting for autonomous wearable devices
2018
Michele Magno, Dario Kneubühler, Philipp Mayer, Luca Benini
2018 International symposium on power electronics, electrical drives, automation and mo…
:read more
Authors:Michele Magno, Dario Kneubühler, Philipp Mayer, Luca Benini
Publication date:06/20/2018
Journal:2018 International symposium on power electronics, electrical drives, automation and motion (SPEEDAM)
Pages:105-110
Publisher:IEEE
Description:For wearable devices, the availability of energy is one of the main limiting factors of performance and lifetime. To overcome this issue, micro-energy harvesting circuits, which extract energy from the environment, are very promising. Among other environmental sources, kinetic energy could significantly improve the energy availability in wearable applications. However, the majority of kinetic energy harvesting circuits do not perform well with the low-frequency patterns found in human motion and are therefore not suited for wearable devices. This paper aims to overcome this limitation by developing a high-efficiency energy harvesting system, which is optimized for frequencies occurring in human motion. A Micro Generator System (MGS) 26.4, by Kinetron, has been exploited as a kinetic transducer to generate energy. The implemented kinetic harvesting system has been designed to maximize the energy conversion …
Cited by:48
:view less
Energy harvesting for smart city applications
2018
Alex S Weddell, Michele Magno
2018 International symposium on power electronics, electrical drives, automation and mo…
:read more
Authors:Alex S Weddell, Michele Magno
Publication date:06/20/2018
Journal:2018 International symposium on power electronics, electrical drives, automation and motion (SPEEDAM)
Pages:111-117
Publisher:IEEE
Description:The `smart cities' concept is now becoming a reality: cities are increasingly connected and intelligent, with rapid advances in diverse areas including transportation, utilities, and municipal services. These can allow services to be delivered more efficiently and reliably, enriching residents' and visitors' experiences, and the data generated can be used for innovative new applications. While many sensors enabling these applications can be grid-powered, there is an increasing need for autonomous distributed or wearable sensing devices, which may also perform edge analytics. While these systems are typically powered by batteries so that they can be deployed quickly and cheaply, this comes with the cost of periodic battery replacement. This paper surveys the state-of-the-art in smart city sensing applications and considers their future directions, focusing on the power demands of sensors, and considerations for using …
Cited by:31
:view less
Average Modelling of State-of-the-Art Ultra-low Power Energy Harvesting Converter IC
2018
Mojtaba Masoudinejad, Michele Magno, Luca Benini, Michael Ten Hompel
2018 International Symposium on Power Electronics, Electrical Drives, Automation and Mo…
:read more
Authors:Mojtaba Masoudinejad, Michele Magno, Luca Benini, Michael Ten Hompel
Publication date:06/20/2018
Journal:2018 International Symposium on Power Electronics, Electrical Drives, Automation and Motion (SPEEDAM)
Pages:99-104
Publisher:IEEE
Description:Micro-energy harvesting from environmental sources is a promising technology for mobile or unobtrusive battery powered Internet of Things devices with constrains in terms of size and weight. Special integrated circuits aim to manage the voltage matching and power control in between the energy harvesting transducer and the storage. Hence, models to simulate the energy behaviour of these systems are important tools for system engineers. In this paper, a neuronal network model is presented to predict the performance of two state-of-the-art integrated circuits. Required model inputs are voltage and current from the energy harvesting transducer and the voltage level of the storage element. Model provides conversion efficiency as its output. Three different datasets have been collected with in-field experiments to build and evaluate the proposed model. Evaluation of the developed model on all datasets shows …
Cited by:8
Resources:[PDF] from researchgate.net
:view less
Smart wearable wristband for EMG based gesture recognition powered by solar energy harvester
2018
Victor Kartsch, Simone Benatti, Mattia Mancini, Michele Magno, Luca Benini
2018 IEEE international symposium on circuits and systems (ISCAS), 1-5
:read more
Authors:Victor Kartsch, Simone Benatti, Mattia Mancini, Michele Magno, Luca Benini
Publication date:05/27/2018
Journal:2018 IEEE international symposium on circuits and systems (ISCAS)
Pages:1-5
Publisher:IEEE
Description:With the recent improvement of flexible electronics, wearable systems are becoming more and more unobtrusive and comfortable, pervading fitness and health-care applications. Wearable devices allow non-invasive monitoring of vital signs and physiological parameters, enabling advanced Human Machine Interaction (HMI) as well. On the other hand, battery lifetime remains a challenge especially when they are equipped with bio-medical sensors and not used as simple data logger. In this paper, we present a flexible wristband for EMG gesture recognition, designed on a flexible Printed Circuit Board (PCB) strip and powered by a small form-factor flexible solar energy panel. The proposed wristband executes a Support Vector Machine (SVM) algorithm reaching 94.02 % accuracy in recognition of 5 hand gestures. The system targets healthcare and HMI applications, and can be used to monitor patients during …
Cited by:59
:view less
Leveraging energy harvesting and wake-up receivers for long-term wireless sensor networks
2018
Fayçal Ait Aoudia, Matthieu Gautier, Michele Magno, Olivier Berder, Luca Benini
Sensors 18 (5), 1578
:read more
Authors:Fayçal Ait Aoudia, Matthieu Gautier, Michele Magno, Olivier Berder, Luca Benini
Publication date:05/15/2018
Journal:Sensors
Volume:18
Issue:5
Pages:1578
Publisher:MDPI
Description:Wireless sensor nodes are traditionally powered by individual batteries, and a significant effort has been devoted to maximizing the lifetime of these devices. However, as the batteries can only store a finite amount of energy, the network is still doomed to die, and changing the batteries is not always possible. A promising solution is to enable each node to harvest energy directly in its environment, using individual energy harvesters. Moreover, novel ultra-low power wake-up receivers, which allow continuous listening of the channel with negligible power consumption, are emerging. These devices enable asynchronous communication, further reducing the power consumption related to communication, which is typically one the most energy-consuming tasks in wireless sensor networks. Energy harvesting and wake-up receivers can be combined to significantly increase the energy efficiency of sensor networks. In this paper, we propose an energy manager for energy harvesting wireless sensor nodes and an asynchronous medium access control protocol, which exploits ultra-low power wake-up receivers. The two components are designed to work together and especially to fit the stringent constraints of wireless sensor nodes. The proposed approach has been implemented on a real hardware platform and tested in the field. Experimental results demonstrate the benefits of the proposed approach in terms of energy efficiency, power consumption and throughput, which can be up to more than two-times higher compared to traditional schemes.
Cited by:42
Resources:[HTML] from mdpi.com
:view less
Time-frequency pattern wake-up detector for low-power always-on sensing of acoustic events
2018
Dinko Oletic, Luka Korman, Michele Magno, Vedran Bilas
2018 IEEE International Instrumentation and Measurement Technology Conference (I2MTC), 1-6
:read more
Authors:Dinko Oletic, Luka Korman, Michele Magno, Vedran Bilas
Publication date:05/14/2018
Journal:2018 IEEE International Instrumentation and Measurement Technology Conference (I2MTC)
Pages:1-6
Publisher:IEEE
Description:In acoustic event detection scenarios, average power consumed for continuous monitoring can be lowered by an low-power always-on sensor interface, waking-up power-hungry signal sampling and processing circuitry only upon detection of the specific audio-pattern. We research on power consumption of such wake-up sensing (WUS) interface consisting of a multichannel programmable analog filtering bank, signal detectors, and a digital wake-up pattern detector circuit. Focusing on the pattern detector, this paper investigates a design performing wake-up upon matching a sequence of its multi-channel inputs against a digitally preset template of time-frequency states. We compare two hardware implementations of a proposed design: one exploiting a dedicated programmable sequential logic chip, and the other on a low-power 16-bit microcontroller (MCU). In most cases, experimental results generally …
Cited by:12
:view less
Combining LoRa and RTK to achieve a high precision self-sustaining geo-localization system
2018
Michele Magno, Stefan Rickli, Josefine Quack, Oliver Brunecker, Luca Benini
2018 17th ACM/IEEE International Conference on Information Processing in Sensor Network…
:read more
Authors:Michele Magno, Stefan Rickli, Josefine Quack, Oliver Brunecker, Luca Benini
Publication date:04/11/2018
Journal:2018 17th ACM/IEEE International Conference on Information Processing in Sensor Networks (IPSN)
Pages:160-161
Publisher:IEEE
Description:High precision Global Navigation Satellite System (GNSS) is a crucial feature for geo-localization to enhance future applications such as self-driving of vehicles. Real Time Kinematic (RTK) is a promising technology to achieve centimeter precision in GNSS, however it requires radio communication and to reduce power consumption this is done at meters range, reducing the use in navigation systems. In this work, we present a high precision low power systems that can be energetically autonomous. The proposed approach exploits a GNSS module with RTK combined with a long-range communication radio (LoRa) to achieve a high-precision localization system with minimal wireless radio infrastructure requirements. Wireless sensor nodes, designed to be energy efficient, comprise the system and they include a solar energy harvesting for self-sustainability. Preliminary experimental results, with in-field …
Cited by:12
Resources:[PDF] from researchgate.net
:view less
Zero-power receiver for touch communication and touch sensing
2018
Raphael Strebel, Michele Magno
2018 17th ACM/IEEE International Conference on Information Processing in Sensor Network…
:read more
Authors:Raphael Strebel, Michele Magno
Publication date:04/11/2018
Journal:2018 17th ACM/IEEE International Conference on Information Processing in Sensor Networks (IPSN)
Pages:150-151
Publisher:IEEE
Description:Intra-body and extra-body communication is an attractive wireless communication method for wearable devices and their applications. In this work, we present the architecture, the design and the implementation of a novel zero-power receiver optimized for intra-body and extra-body communication and on-off keying modulation. The receiver includes an energy-harvesting subsystem that extracts energy from the received message to supply the low power circuits. The proposed zero-power receiver is able to receive and to parse data, as well as wake up external logic when a specific address is detected. The receiver can be used both as an always-on touch sensor to be deployed in the field and as a body communication wake up radio to other nodes on the human body. Experimental results with in-field measurements demonstrate the zero-power of the proposed device and that it is possible to achieve more than 1 …
Cited by:6
Resources:[PDF] from researchgate.net
:view less
Combining microbial fuel cell and ultra-low power event-driven audio detector for zero-power sensing in underwater monitoring
2018
Philipp Mayer, Michele Magno, Luca Benini
2018 IEEE Sensors Applications Symposium (SAS), 1-6
:read more
Authors:Philipp Mayer, Michele Magno, Luca Benini
Publication date:03/12/2018
Journal:2018 IEEE Sensors Applications Symposium (SAS)
Pages:1-6
Publisher:IEEE
Description:Achieving zero-power always-on sensing is an attractive challenge for academic and industrial researchers. Long-term and perpetual monitoring are particularly important for battery-operated systems, such as wearable and IoT devices and necessary in a wide range of applications. Zero-power sensing is crucial for devices that are supposed to collect data and important events in inaccessible places, such as under the water, where the replacement of batteries is almost impossible or inconvenient. In this paper, we present a novel ultra-low power always-on event-driven acoustic sensor able to feature pattern recognition with up to eight simultaneous time-frequency features exploiting mixed-signal low power design. Moreover, this paper achieves a zero-power acoustic smart sensor combining the event-driven acoustic detector with a microbial fuel cell, aiming long-term monitoring in underwater applications …
Cited by:14
:view less
An accurate system for optimal state estimation of a levitated nanoparticle
2018
Michael Jost, Michael Schaffner, Michele Magno, Matthias Korb, Luca Benini, René Reiman…
2018 IEEE Sensors Applications Symposium (SAS), 1-6
:read more
Authors:Michael Jost, Michael Schaffner, Michele Magno, Matthias Korb, Luca Benini, René Reimann, Vijay Jain, Michael Grossi, A Militara, Martin Frimmer, Lukas Novotny
Publication date:03/12/2018
Journal:2018 IEEE Sensors Applications Symposium (SAS)
Pages:1-6
Publisher:IEEE
Description:Experimental setups involving optically levitated nanoparticles are widely used nowadays to study physical phenomena in various fields including biophysics, sensing or quantum mechanics. We focus on parametric cooling of the particle's center-of-mass motion, where the intensity of a laser beam forming an optical trap is modulated to counteract the nanoparticles motion and cools it down to temperatures in the micro-Kelvin regime. Such experimental setups require tight control of the modulation frequency and phase, and are typically prone to measurement noise in the control loop. In this paper we investigate a new approach that incorporates additional knowledge of the physical system and noise characteristics by employing a Kalman filter in the feedback loop, with the aim to improve the overall cooling performance of the experimental arrangement. We develop an accurate state estimation system that is able to …
Cited by:3
Resources:[PDF] from academia.edu
:view less
An energy efficient E-skin embedded system for real-time tactile data decoding
2018
Michele Magno, Ali Ibrahim, Antonio Pullini, Maurizio Valle, Luca Benini
Journal of Low Power Electronics 14 (1), 101-109
:read more
Authors:Michele Magno, Ali Ibrahim, Antonio Pullini, Maurizio Valle, Luca Benini
Publication date:03/01/2018
Journal:Journal of Low Power Electronics
Volume:14
Issue:1
Pages:101-109
Publisher:American Scientific Publishers
Description:Electronic skin (e-skin) is playing a key role in medicine, prosthetic and robot applications. E-skin tries to sense the world like the human skin does, exploiting arrays of sensors that produce a huge amount of data to be processed. Processing tactile data close to the e-skin imposes big challenges in terms of energy efficiency and real-time functionality. Energy efficient is particularly important for wearable and prosthetic applications where e-skin is mainly used as a wearable device supplied by battery. The major challenges it to find a sweet spot between power consumption and performance as tactile data decoding implementation requires high amount of computational power. This paper presents the hardware–software implementation of a complete low power embedded system that matches the computational requirements and the energy efficiency exploiting an ultr-alow power parallel processor. Tactile data …
Cited by:9
:view less
Practical Implementation Aspects of the Data Timed Sending (DTS) Protocol Using Wake-up
2018
Konstantin Chomu Vladimir Atanasovski¹, Liljana Gavrilovska¹, Michele Magno
Pervasive Computing Paradigms for Mental Health: Selected Papers from MindCare 2016, Fa…
:read more
Authors:Konstantin Chomu Vladimir Atanasovski¹, Liljana Gavrilovska¹, Michele Magno
Publication date:02/28/2018
Journal:Pervasive Computing Paradigms for Mental Health: Selected Papers from MindCare 2016, Fabulous 2016, and IIoT 2015
Volume:207
Pages:139
Publisher:Springer
Description:The energy efficient Data Timed Sending (DTS) protocol enables information transfer from sensor nodes to sink host by choosing the appropriate transmission time of a short packet without data payload. Wake-up Radio (WuR) devices allow asynchronous communication of Wireless Sensor Net-works (WSNs) putting the sensor nodes' main radio modules in continuous sleep state thus increasing energy efficiency. A common characteristic for the DTS protocol and WuR is that they are designed for applications where sensors take sparse measurements, typically one measurement every few minutes. This paper investigates the combination of the DTS protocol with WuR into a single inte-grated solution. The analytical analysis shows that the DTS protocol significantly reduces the energy consumption when coupled with WuR making this solution suitable for applications with battery powered WSN (eg body area WSN).
:view less
Long-short range communication network leveraging LoRa™ and wake-up receiver
2018
Fayçal Ait Aoudia, Matthieu Gautier, Michele Magno, Mickaël Le Gentil, Olivier Berder, …
Microprocessors and Microsystems 56, 184-192
:read more
Authors:Fayçal Ait Aoudia, Matthieu Gautier, Michele Magno, Mickaël Le Gentil, Olivier Berder, Luca Benini
Publication date:02/01/2018
Journal:Microprocessors and Microsystems
Volume:56
Pages:184-192
Publisher:Elsevier
Description:Wireless sensor and actuator networks play a central role in the Internet of Things, and a lot of effort is devoted to enable energy efficient and low latency communications. In the recent years, low power communications has evolved towards multi-kilometer ranges and low bit-rate approaches such as LoRa™. However, the medium access layer protocols rely on the well-known duty-cycling schemes, which require a trade-off between power consumption and latency for message transfer from the gateway to the nodes. Domains such as industrial applications in which sensors and actuators are part of the control loop require predictable latency, as well as low power consumption. Emerging ultra-low-power wake-up receivers enable pure-asynchronous communications, allowing both low latency and low power consumption, but at the cost of a lower sensitivity and lower range than traditional wireless receivers and …
Cited by:73
Resources:[PDF] from hal.science
:view less
Vibration Energy Harvesting for Monitoring Dynamical Systems.
2018
Vikram Pakrashi, Giuseppe Marano, Paul Cahill, Shaikh Faruque Ali, Michele Magno
Shock and Vibration 2018, NA-NA
:read more
Authors:Vikram Pakrashi, Giuseppe Marano, Paul Cahill, Shaikh Faruque Ali, Michele Magno
Publication date:01/01/2018
Journal:Shock and Vibration
Volume:2018
Pages:NA-NA
Publisher:John Wiley & Sons, Inc.
Description:The objective of this special issue is to address recent research trends and developments in the application of vibration energy harvesting for the monitoring of dynamical systems. While significant research has been carried out around maximization of harvested energy, the use of such harvesting signatures for the monitoring of dynamical systems is at a nascent stage. This special issue attempts to focus on this aspect. A substantial number of papers were submitted, and after a thorough peer review process, five papers were selected to be included in this special issue. These papers cover important applications in design, analyses, potential, and actual applications on this topic. We believe that the original papers collected in this special issue highlight the contemporary topics in research where vibration energy harvesting signatures can be useful for monitoring of built infrastructure and other dynamical systems …
Cited by:2
:view less
Selected articles from the NGCAS 2017 conference
2018
Maurizio Valle, Ali Ibrahim, Maurizio Martina, Michele Magno
Journal of Low Power Electronics 14 (1), 99-100
:read more
Authors:Maurizio Valle, Ali Ibrahim, Maurizio Martina, Michele Magno
Publication date:01/01/2018
Journal:Journal of Low Power Electronics
Volume:14
Issue:1
Pages:99-100
Publisher:American Scientific Publishers
Description:Selected articles from the NGCAS 2017 conference - Research Collection Header Upper Right Menu Log in de jump to https://www.ethz.ch Research Collection Toggle navigation Upper Right Menu Login Help Help Language Deutsch Toggle navigation Search View Item Home Journal Contributions Other Journal Item View Item Home Journal Contributions Other Journal Item View Item Research Collection Navigational link Search Selected articles from the NGCAS 2017 conference Mendeley CSV RIS BibTeX Thumbnail Metadata only Author Valle, Maurizio Ibrahim, Ali Martina, Maurizio Magno, Michele Show all Date 2018-03 Type Other Journal Item ETH Bibliography yes Altmetrics  Publication status published External links https://doi.org/10.1166/jolpe.2018.1546 Journal / series Journal of Low Power Electronics Volume 14 (1) Pages / Article No. 99 - 100 Publisher American Scientific Publishers More Show all …
:view less
Design and evaluation of a low-power sensor device for induced rockfall experiments
2017
Andrin Caviezel, Michael Schaffner, Lukas Cavigelli, Pascal Niklaus, Yves Bühler, Perry…
IEEE Transactions on Instrumentation and Measurement 67 (4), 767-779
:read more
Authors:Andrin Caviezel, Michael Schaffner, Lukas Cavigelli, Pascal Niklaus, Yves Bühler, Perry Bartelt, Michele Magno, Luca Benini
Publication date:11/28/2017
Journal:IEEE Transactions on Instrumentation and Measurement
Volume:67
Issue:4
Pages:767-779
Publisher:IEEE
Description:Rockfalls have over the last decades become a serious and frequent hazard, especially due to larger variations in precipitation and temperatures, destabilizing rocky slopes in mountainous regions. Hence, civil engineers are applying the latest simulation tools to perform risk assessments and plan mitigation strategies. These tools are based on various models with many parameters that should be calibrated and evaluated with real-world in-field measurement data. In this paper, we present a rugged low-power multisensor node termed StoneNode that has been designed to acquire and log accurate inertial sensor measurements during induced in-field experiments with falling rocks. The node hosts low-power microelectromechanical system sensors with high dynamic ranges sampled up to 1 kHz, and provides a long battery lifetime of up to 56 h, enabling long-lasting field studies with a duration of several working …
Cited by:59
Resources:[PDF] from ethz.ch
:view less
A low-complexity eyewear system for direction-based augmented reality applications
2017
Gabriele Miorandi, Davide Quaglia, Federico Fraccaroli, Walter Vendraminetto, Enrico Gi…
Proceedings of the 15th ACM Conference on Embedded Network Sensor Systems, 1-2
:read more
Authors:Gabriele Miorandi, Davide Quaglia, Federico Fraccaroli, Walter Vendraminetto, Enrico Giordano, Michele Magno
Publication date:11/06/2017
Journal:Proceedings of the 15th ACM Conference on Embedded Network Sensor Systems
Pages:1-2
Description:Augmented reality (AR) applications greatly benefit from direction estimation. In current AR devices, direction estimation is enabled by power hungry technologies such as GPS, management of inertial data and video processing. We present a low-complexity eyewear prototype capable of obtaining directional information from a set of environmental radio sources by using a multi-antenna system patented by Wagoo LLC. Eyewear devices are the natural match for this technology under the assumption that user line of sight represents the main reference for user interaction and orientation. In the demonstration, the prototype detects when a user aims at objects or people that are associated to standard Bluetooth Low Energy emitters (beacons) with a current 30° sensitivity and 5% error rate.
Cited by:1
:view less
Kinetic AC/DC converter for electromagnetic energy harvesting in autonomous wearable devices
2017
Robin Bolt, Michele Magno, Thomas Burger, Aldo Romani, Luca Benini
IEEE Transactions on Circuits and Systems II: Express Briefs 64 (12), 1422-1426
:read more
Authors:Robin Bolt, Michele Magno, Thomas Burger, Aldo Romani, Luca Benini
Publication date:10/31/2017
Journal:IEEE Transactions on Circuits and Systems II: Express Briefs
Volume:64
Issue:12
Pages:1422-1426
Publisher:IEEE
Description:A nano-power integrated circuit is designed to convert the ac output of an electromagnetic micro generator for wearable kinetic energy harvesting to dc usable power. The converter is designed to minimize the quiescent current and to maximize the energy conversion and maximum power point tracking efficiency from the kinetic energy harvester. The architecture implements an ac/dc chopper exploiting the intrinsic inductance of the transducer combined with a zero-drop rectifier. An optimal switching scheme is derived for the converter and a corresponding control circuit is developed and optimized for low power consumption. The converter is designed in an SMIC 130-nm process, and circuit simulations show an efficiency of 87%-88% with respect to the maximum power point of the transducer with a battery supply voltage ranging from 3.5 V to 4.2 V. The quiescent current of the converter is as low as 250 nA.
Cited by:29
Resources:[PDF] from unibo.it
:view less
Long-term monitoring of small-sized birds using a miniaturized bluetooth-low-energy sensor node
2017
Michele Magno, Fabien Vultier, Bence Szebedy, Luca Benini
2017 IEEE SENSORS, 1-3
:read more
Authors:Michele Magno, Fabien Vultier, Bence Szebedy, Luca Benini
Publication date:10/29/2017
Journal:2017 IEEE SENSORS
Pages:1-3
Publisher:IEEE
Description:This paper presents the design and development of an ultra-low power miniaturized and lightweight wireless sensor node. The node is designed to be worn with minimal effort by small-sized birds to collect, process, and send/receive data to/from a remote host via Bluetooth Low-Energy. The main feature of the developed node is the capability to stream continuously compressed or uncompressed audio and temperature data. The nodes can monitor several birds simultaneously and produce high-quality audio streams, one for each bird, with low audio interference. Due to the combination of low-power hardware and software techniques and technologies, the node achieves a lifetime of up to 24h hours with a single zinc-air battery.
Cited by:14
:view less
Energy-efficient context aware power management with asynchronous protocol for body sensor network
2017
Michele Magno, Tommaso Polonelli, Filippo Casamassima, Andres Gomez, Elisabetta Farella…
Mobile Networks and Applications 22 (5), 814-824
:read more
Authors:Michele Magno, Tommaso Polonelli, Filippo Casamassima, Andres Gomez, Elisabetta Farella, Luca Benini
Publication date:10/01/2017
Journal:Mobile Networks and Applications
Volume:22
Issue:5
Pages:814-824
Publisher:Springer US
Description:MEMS sensor technology and advances in electronics, low-power processors and communication have enabled ubiquitous monitoring, providing significant opportunities for a wide range of applications including wearable devices for fitness and health tracking. However, due to the limited form factor required, there remains a challenging issue that limits even more the success of wearable devices: the limited lifetime due to the small energy storages that supply the devices. This limitation affects usability and forces the data processing to keep low-complexity to match the power constraints. As wireless communication is typically the most power hungry activity in wearable sensors devices, many techniques focus on reducing the communication power consumption. For this reason, advanced power management can be exploited to increase the lifetime of the devices. In this work, we present a wireless body area …
Cited by:37
Resources:[PDF] from ethz.ch
:view less
Energy efficient system for tactile data decoding using an ultra-low power parallel platform
2017
Michele Magno, Ali Ibrahim, Antonio Pullini, Maurizio Valle, Luca Benini
2017 New Generation of CAS (NGCAS), 17-20
:read more
Authors:Michele Magno, Ali Ibrahim, Antonio Pullini, Maurizio Valle, Luca Benini
Publication date:09/06/2017
Journal:2017 New Generation of CAS (NGCAS)
Pages:17-20
Publisher:IEEE
Description:The implementation of tactile data decoding on low power embedded system is crucial for the development of e-skin systems that are body worn and supplied by batteries. These embedded electronic systems have to comply with severe constraints imposed by the application, especially real-time functionality battery lifetime. One of the main challenges it to find a sweet spot between power consumption and performance as tactile data decoding implementation requires high amount of computational power. In this paper, we present the assessment of the system energy efficiency of tactile data decoding using an ultra-low power parallel platform. The work performs tactile data decoding using a support vector machine (SVM) based tensor kernel algorithm for input touch modalities classification. To improve the energy efficiency the system use a parallel ultra-low power (PULP) processor that satisfies the computational …
Cited by:11
Resources:[PDF] from researchgate.net
:view less
Biodegradable and highly deformable temperature sensors for the internet of things
2017
Giovanni A Salvatore, Jenny Sülzle, Filippo Dalla Valle, Giuseppe Cantarella, Francesco…
Advanced Functional Materials 27 (35), 1702390
:read more
Authors:Giovanni A Salvatore, Jenny Sülzle, Filippo Dalla Valle, Giuseppe Cantarella, Francesco Robotti, Petar Jokic, Stefan Knobelspies, Alwin Daus, Lars Büthe, Luisa Petti, Norbert Kirchgessner, Raoul Hopf, Michele Magno, Gerhard Tröster
Publication date:09/01/2017
Journal:Advanced Functional Materials
Volume:27
Issue:35
Pages:1702390
Description:Recent advances in biomaterials, thin film processing, and nanofabrication offer the opportunity to design electronics with novel and unique capabilities, including high mechanical stability and biodegradation, which are relevant in medical implants, environmental sensors, and wearable and disposable devices. Combining reliable electrical performance with high mechanical deformation and chemical degradation remains still challenging. This work reports temperature sensors whose material composition enables full biodegradation while the layout and ultrathin format ensure a response time of 10 ms and stable operation demonstrated by a resistance variation of less than 0.7% when the devices are crumpled, folded, and stretched up to 10%. Magnesium microstructures are encapsulated by a compostable‐certified flexible polymer which exhibits small swelling rate and a Young's modulus of about 500 MPa …
Cited by:261
:view less
Precise, energy-efficient data acquisition architecture for monitoring radioactivity using self-sustainable wireless sensor nodes
2017
Andres Gomez, Michele Magno, Marie Francine Lagadec, Luca Benini
IEEE sensors journal 18 (1), 459-469
:read more
Authors:Andres Gomez, Michele Magno, Marie Francine Lagadec, Luca Benini
Publication date:06/16/2017
Journal:IEEE sensors journal
Volume:18
Issue:1
Pages:459-469
Publisher:IEEE
Description:Measuring radiation dosage rates is becoming more and more important in many applications scenarios. Continuously monitoring radiation in contaminated and poorly accessible areas is challenging due to the frequent data collection/transmission combined with long life requirements. We present a self-sustainable wireless sensor node for low power, high precision radiation dosage rate monitoring. We propose an energy-efficient data acquisition algorithm that can reduce the energy per measurement, while guaranteeing minimal loss of precision. The proposed node is designed to work in collaboration with an unmanned aerial vehicle used for two essential mission steps: air-deployment of the wireless sensor nodes at suitable locations, and acquiring data logs via low-power, shortrange radio communication in fly-by mode after a wake-up command. The system uses off-the-shelf components for defining the …
Cited by:31
Resources:[PDF] from ethz.ch
:view less
DeepEmote: Towards multi-layer neural networks in a low power wearable multi-sensors bracelet
2017
Michele Magno, Michael Pritz, Philipp Mayer, Luca Benini
2017 7th IEEE international workshop on advances in sensors and interfaces (IWASI), 32-37
:read more
Authors:Michele Magno, Michael Pritz, Philipp Mayer, Luca Benini
Publication date:06/15/2017
Journal:2017 7th IEEE international workshop on advances in sensors and interfaces (IWASI)
Pages:32-37
Publisher:IEEE
Description:Wearable smart sensing is a promising technology to enhance user experience that has already been exploited in sport/fitness, as well as health and human monitoring. Wearable sensing systems not only provide continuous data monitoring and acquisition, but are also expected to process, and make sense of the acquired data by classification in similar ways as human experts do. Supporting continuous operation on ultra-small batteries poses unique challenges in energy efficiency. In this paper, we present an ultra-low-power bracelet with several sensors that is able to run multi-layer neural networks learning algorithms to process data efficiently. The design combines low-power design, energy efficient algorithms and makes this bracelet suitable for long-term uninterrupted usage with small coin batteries. We demonstrate in-field measurement results that prove that neural networks applications can fit within the …
Cited by:66
Resources:[PDF] from researchgate.net
:view less
Target following on nano-scale unmanned aerial vehicles
2017
Daniele Palossi, Jaskirat Singh, Michele Magno, Luca Benini
2017 7th IEEE international workshop on advances in sensors and interfaces (IWASI), 170…
:read more
Authors:Daniele Palossi, Jaskirat Singh, Michele Magno, Luca Benini
Publication date:06/15/2017
Journal:2017 7th IEEE international workshop on advances in sensors and interfaces (IWASI)
Pages:170-175
Publisher:IEEE
Description:Unmanned Aerial Vehicles (UAVs) with high level autonomous navigation capabilities are a hot topic both in industry and academia due to their numerous applications. However, autonomous navigation algorithms are demanding from the computational standpoint, and it is very challenging to run them on-board of nano-scale UAVs (i.e., few centimeters of diameter) because of the limited capabilities of their MCU-based controllers. This work focuses on the object tracking capability, (i.e., target following capability) on such nano-UAVs. We present a lightweight hardware-software solution, bringing autonomous navigation on a commercial platform using only on-board computational resources. Furthermore, we evaluate a parallel ultra-low-power (PULP) platform that enables the execution of even more sophisticated algorithms. Experimental results demonstrate the benefits of our solution, achieving accurate target …
Cited by:23
Resources:[PDF] from ethz.ch
:view less
Powering smart wearable systems with flexible solar energy harvesting
2017
Petar Jokic, Michele Magno
2017 IEEE International symposium on circuits and systems (ISCAS), 1-4
:read more
Authors:Petar Jokic, Michele Magno
Publication date:05/28/2017
Journal:2017 IEEE International symposium on circuits and systems (ISCAS)
Pages:1-4
Publisher:IEEE
Description:Recent advances in electrical sensing and flexible devices have demonstrated great potential in a wide range of applications including wearable devices for fitness and health care. Flexible plastic substrates, such as polyimide, or transparent conductive polyester are used to fabricate flexible devices that increase the comfort when they are worn by users or patients. However, one challenge that still limits the success of wearable devices is the limited lifetime especially in biomedical applications. Energy harvesting technology is one of the most promising approaches to address the short lifetime of wearable devices. However, harvesting energy for powering wearable devices is more challenging due to strict constraints in terms of size, weight and cost. In this work, we present the design of a wearable smart bracelet that uses thin-film small form factor flexible photovoltaic panels as energy source. The solar energy …
Cited by:103
Resources:[PDF] from researchgate.net
:view less
Wearable energy harvesting: From body to battery
2017
Michele Magno, David Boyle
2017 12th International conference on design & technology of integrated systems in nano…
:read more
Authors:Michele Magno, David Boyle
Publication date:04/04/2017
Journal:2017 12th International conference on design & technology of integrated systems in nanoscale era (DTIS)
Pages:1-6
Publisher:IEEE
Description:Energy Harvesting (EH) technologies provide promising solutions to overcome the short lifetime of wearable devices. In the last decade, EH has matured as a technology and found use in many application scenarios, such as smart grid and wireless sensor networks. Recently, advances have been made in miniaturizing EH devices to supply wearable devices by exploiting ambient energy in the form of motion, thermal gradients, light and electromagnetic radiation. However, harvesting energy from the body for powering wearable devices is more challenging due to strict constraints in terms of size, weight and cost. In this paper, we present a taxonomy of technologies, architectures and design trade-offs for efficient EH systems suitable for wearable devices. Additionally, we provide implementation details, including the conversion stages for kinetic and thermal EH, optimized for the human body. We quantify the energy …
Cited by:88
Resources:[PDF] from researchgate.net
:view less
Session details: Smart energy and automotive systems
2017
Geoff Merrett, Michele Magno
Proceedings of the Conference on Design, Automation & Test in Europe
:read more
Authors:Geoff Merrett, Michele Magno
Publication date:03/27/2017
Journal:Proceedings of the Conference on Design, Automation & Test in Europe
Description:Session details: Smart energy and automotive systems | Proceedings of the Conference on Design, Automation & Test in Europe skip to main content ACM Digital Library home ACM Association for Computing Machinery corporate logo Google, Inc. (search) Advanced Search Browse About Sign in Register Advanced Search Journals Magazines Proceedings Books SIGs Conferences People More Search ACM Digital Library SearchSearch Advanced Search Browse Browse Digital Library Collections More Home Browse by Title Proceedings DATE '17 Session details: Smart energy and automotive systems section Share on Session details: Smart energy and automotive systems Editors: Geoff Merrett, Michele MagnoAuthors Info & Claims DATE '17: Proceedings of the Conference on Design, Automation & Test in Europe Published: 27 March 2017 Publication History 0citation0Downloads Metrics Total Citations0 Total …
:view less
WULoRa: An energy efficient IoT end-node for energy harvesting and heterogeneous communication
2017
Michele Magno, Faycal Ait Aoudia, Matthieu Gautier, Olivier Berder, Luca Benini
Design, Automation & Test in Europe Conference & Exhibition (DATE), 2017, 1528-1533
:read more
Authors:Michele Magno, Faycal Ait Aoudia, Matthieu Gautier, Olivier Berder, Luca Benini
Publication date:03/27/2017
Journal:Design, Automation & Test in Europe Conference & Exhibition (DATE), 2017
Pages:1528-1533
Publisher:IEEE
Description:Intelligent connected objects, which build the IoT, are electronic devices usually supplied by batteries that significantly limit their life-time. These devices are expected to be deployed in very large numbers, and manual replacement of their batteries will severely restrict their large-scale or wide-area deployments. Therefore energy efficiency is of the utmost importance in the design of these devices. The wireless communication between the distributed sensor devices and the host stations can consume significant energy, even more when data needs to reach several kilometers of distance. In this paper, we present an energy-efficient multi-sensing platform that exploits energy harvesting, long-range communication and ultra-low-power short-range wake-up radio to achieve self sustainability in a kilometer range network. The proposed platform is designed with power efficiency in mind and exploits the always-on wake …
Cited by:102
Resources:[PDF] from hal.science
:view less
StoneNode: A low-power sensor device for induced rockfall experiments
2017
Pascal Niklaus, Thomas Birchler, Tim Aebi, Michael Schaffner, Lukas Cavigelli, Andrin C…
2017 IEEE Sensors Applications Symposium (SAS), 1-6
:read more
Authors:Pascal Niklaus, Thomas Birchler, Tim Aebi, Michael Schaffner, Lukas Cavigelli, Andrin Caviezel, Michele Magno, Luca Benini
Publication date:03/13/2017
Journal:2017 IEEE Sensors Applications Symposium (SAS)
Pages:1-6
Publisher:IEEE
Description:Spontaneous occurring rockfalls are a serious danger, especially nowadays as global warming leads to a retrogression of the permafrost, which stabilized terrain in mountainous regions. In order to perform risk assessments and develop mitigation strategies, advanced simulation tools and models have been developed over the last years. These models come with many parameters and need to be calibrated and validated with real-world data to produce reliable estimates. To this end, we developed StoneNode, a rugged, small, low-power sensor device which can be embedded into boulders to measure accelerations and angular velocities. The node employs low-power MEMS sensors with high dynamic range and has a maximum operating time of more than 56 h. First field experiments confirm that the StoneNode is a reliable, easy-to-use device, which greatly facilitates the data acquisition process.
Cited by:26
Resources:[PDF] from ethz.ch
:view less
Demo Abstract: A Low-Complexity Eyewear System for Direction-based Augmented Reality Applications
2017
Gabriele Miorandi, Davide Quaglia, Federico Fraccaroli, Walter Vendraminetto, Enrico Gi…
:read more
Authors:Gabriele Miorandi, Davide Quaglia, Federico Fraccaroli, Walter Vendraminetto, Enrico Giordano, Michele Magno
Publication date:01/01/2017
Description:Augmented reality (AR) applications greatly benefit from direction estimation. In current AR devices, direction estimation is enabled by power hungry technologies such as GPS, management of inertial data and video processing. We present a low-complexity eyewear prototype capable of obtaining directional information from a set of environmental radio sources by using a multi-antenna system patented by Wagoo LLC. Eyewear devices are the natural match for this technology under the assumption that user line of sight represents the main reference for user interaction and orientation. In the demonstration, the prototype detects when a user aims at objects or people that are associated to standard Bluetooth Low Energy emitters (beacons) with a current 30 sensitivity and 5% error rate.
Resources:[PDF] from researchgate.net
:view less
Sensor Systems and Software
2017
Michele Magno, Fabien Ferrero, Vedran Bilas
:read more
Authors:Michele Magno, Fabien Ferrero, Vedran Bilas
Publication date:01/01/2017
Publisher:Springer International Publishing
Description:The 7th EAI International Conference on Sensor Systems and Software—S-CUBE 2016—an international conference in the field of sensors systems, hardware, software, and applications, was held during December 1–2, 2016, in Sophia Antipolis, Nice. The conference broadly focuses on the design, development, and optimization of sensor systems, and this international event provides the opportunity for researchers, technologists, and industry specialists in sensor systems and software to meet and to exchange ideas and information. The conference gave researchers an opportunity to discuss new technologies, interesting approaches, and hardware and software methods for sensing systems and their applications. The proceedings of S-CUBE 2016 are published by Springer in the series Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering (LNICST). This …
Cited by:4
:view less
Human body heat for powering wearable devices: From thermal energy to application
2017
Moritz Thielen, Lukas Sigrist, Michele Magno, Christofer Hierold, Luca Benini
Energy conversion and management 131, 44-54
:read more
Authors:Moritz Thielen, Lukas Sigrist, Michele Magno, Christofer Hierold, Luca Benini
Publication date:01/01/2017
Journal:Energy conversion and management
Volume:131
Pages:44-54
Publisher:Pergamon
Description:Energy harvesting is the key technology to enable self-sustained wearable devices for the Internet of Things and medical applications. Among various types of harvesting sources such as light, vibration and radio frequency, thermoelectric generators (TEG) are a promising option due to their independence of light conditions or the activity of the wearer. This work investigates scavenging of human body heat and the optimization of the power conversion efficiency from body core to the application. We focus on the critical interaction between thermal harvester and power conditioning circuitry and compare two approaches: (1) a high output voltage, low thermal resistance μTEG combined with a high efficiency actively controlled single inductor DC-DC converter, and (2) a high thermal resistance, low electric resistance mTEG in combination with a low-input voltage coupled inductors based DC-DC converter. The mTEG …
Cited by:290
Resources:[PDF] from sciencedirect.com
:view less
A generic framework for modeling MAC protocols in wireless sensor networks
2016
Fayçal Ait Aoudia, Matthieu Gautier, Michele Magno, Olivier Berder, Luca Benini
IEEE/ACM Transactions on Networking 25 (3), 1489-1500
:read more
Authors:Fayçal Ait Aoudia, Matthieu Gautier, Michele Magno, Olivier Berder, Luca Benini
Publication date:12/07/2016
Journal:IEEE/ACM Transactions on Networking
Volume:25
Issue:3
Pages:1489-1500
Publisher:IEEE
Description:Wireless sensor networks are employed in many applications, such as health care, environmental sensing, and industrial monitoring. An important research issue is the design of efficient medium access control (MAC) protocols, which have an essential role for the reliability, latency, throughput, and energy efficiency of communication, especially as communication is typically one of the most energy consuming tasks. Therefore, analytical models providing a clear understanding of the fundamental limitations of the different MAC schemes, as well as convenient way to investigate their performance and optimize their parameters, are required. In this paper, we propose a generic framework for modeling MAC protocols, which focuses on energy consumption, latency, and reliability. The framework is based on absorbing Markov chains, and can be used to compare different schemes and evaluate new approaches. The …
Cited by:47
Resources:[PDF] from hal.science
:view less
Analytical and experimental evaluation of wake-up receivers based protocols
2016
Fayçal Ait Aoudia, Michele Magno, Matthieu Gautier, Olivier Berder, Luca Benini
2016 IEEE Global Communications Conference (GLOBECOM), 1-7
:read more
Authors:Fayçal Ait Aoudia, Michele Magno, Matthieu Gautier, Olivier Berder, Luca Benini
Publication date:12/04/2016
Journal:2016 IEEE Global Communications Conference (GLOBECOM)
Pages:1-7
Publisher:IEEE
Description:Achieving energy efficient wireless communication is the most pursued goal in Wireless Sensor Networks (WSNs), as energy consumption is typically a major barrier to long term applications. In recent years, ultra-low power Wake-up Receivers (WuRx) have emerged, enabling pure asynchronous wireless communication that eliminates energy waste due to idle listening. However, to achieve a significant increase of energy efficiency compared to traditional duty-cycling approaches, Medium Access Control (MAC) protocols exploiting WuRx must be carefully designed. Therefore, we propose an analytical framework to model MAC protocols, leveraging WuRx or not, which gives an important evaluation of power consumption, latency and reliability. This framework was used to both model a WuRx-based MAC protocol, and to model two other state-of-the art MAC protocols for WSNs not using WuRx. Experimental power …
Cited by:24
Resources:[PDF] from hal.science
:view less
Smart LED Lights Control Using Nano-Power Wake Up Radios
2016
Tommaso Polonelli, Michele Magno
International Conference on Sensor Systems and Software, 93-104
:read more
Authors:Tommaso Polonelli, Michele Magno
Publication date:12/01/2016
Journal:International Conference on Sensor Systems and Software
Pages:93-104
Publisher:Springer International Publishing
Description:Wireless sensor networks (WSNs) are widely employed today in real world applications. Smart homes and smart cities are the most promising application currently exploiting WSN. Smart lighting with WSN in particular is promising to achieve a low cost, wireless, easily installed, adaptable system to automatically adjust the light intensity of LED panels, with the aim of saving energy and maintaining user satisfaction. However, lifetime and power consumption of wireless devices are still the most critical challenge that limits the success of this technology. This issue is especially critical when wireless sensor nodes are powered by limited energy storage devices (i.e. small batteries or supercaps). To overcome this issue, major research efforts focus on reducing power consumption, particularly communication, as the radio transceiver is one of the highest power consumers. In this work we present the design and …
Resources:[PDF] from researchgate.net
:view less
A dual processor energy-efficient platform with multi-core accelerator for smart sensing
2016
Antonio Pullini, Stefan Mach, Michele Magno, Luca Benini
International Conference on Sensor Systems and Software, 29-40
:read more
Authors:Antonio Pullini, Stefan Mach, Michele Magno, Luca Benini
Publication date:12/01/2016
Journal:International Conference on Sensor Systems and Software
Pages:29-40
Publisher:Springer International Publishing
Description:Energy-efficient computing has increasingly come into focus of research and industry over the last decade. Ultra-low-power architectures are a requirement for distributed sensing, wearable electronics, Internet of Things and consumer electronics. In this paper, we present a dual-mode platform that includes an ultra-low power Cortex Arm M4 microcontroller coupled with a highly energy efficient multi-core parallel processor. The platform is designed to maximize the energy efficiency in sensors applications by exploiting the Cortex Arm M4 to achieve ultra-low power processing and power management, and enables the multi-core processor to provide additional computational power for near-sensor data centric processing (i.e. accelerating Convolutional Neural Networks for image classification) increasing energy efficiency. The proposed platform enhances the application scenarios where on-board processing (i.e …
Cited by:2
Resources:[PDF] from researchgate.net
:view less
Shelmet: an intelligent self-sustaining multi sensors smart helmet for bikers
2016
Michele Magno, Angelo D’Aloia, Tommaso Polonelli, Lorenzo Spadaro, Luca Benini
International Conference on Sensor Systems and Software, 55-67
:read more
Authors:Michele Magno, Angelo D’Aloia, Tommaso Polonelli, Lorenzo Spadaro, Luca Benini
Publication date:12/01/2016
Journal:International Conference on Sensor Systems and Software
Pages:55-67
Publisher:Springer International Publishing
Description: This paper presents the design of a wearable system to transform a helmet into a smart, multi-sensor connected helmet (SHelmet) to improve motorcycle safety. Low power design and self-sustainability are the key for the usability of our helmet, to avoid frequent battery recharges and dangerous power losses. Hidden in the helmet structure, the designed system is equipped with a dense sensor network including accelerometer, temperature, light, and alcohol gas level, in addition, a Bluetooth low energy module interfaces the device with an on-vehicle IR camera, and eventually the user’s smart phone. To keep the driver focused, the user interface consists of a small non-invasive display combined with a speech recognition system. System architecture is optimized for aggressive power management, featuring an ultra-low power wake-up radio, and fine-grained software-controlled shutdown of all sensing …
Cited by:20
Resources:[PDF] from researchgate.net
:view less
SNW-MAC: An asynchronous protocol leveraging wake-up receivers for data gathering in star networks
2016
Fayçal Ait Aoudia, Matthieu Gautier, Michele Magno, Olivier Berder, Luca Benini
International Conference on Sensor Systems and Software, 3-14
:read more
Authors:Fayçal Ait Aoudia, Matthieu Gautier, Michele Magno, Olivier Berder, Luca Benini
Publication date:12/01/2016
Journal:International Conference on Sensor Systems and Software
Pages:3-14
Publisher:Springer International Publishing
Description:A widespread approach to extend lifetime of battery-powered wireless sensor nodes is duty-cycling, which consists in periodically switching on and off node transceiver. However, energy waste in idle listening periods is still a bottleneck. These periods can be completely removed using emerging ultra-low power wake-up receivers, which continuously listen to the channel with negligible power consumption. In this paper, an asynchronous medium access control protocol is proposed for data gathering in a star network topology. The protocol exploits state-of-the-art wake-up receivers to minimize the energy required to transmit a packet and to make collisions impossible. The proposed approach has been implemented on a real hardware platform and tested in-field. Experimental results demonstrate the benefits of the proposed approach in terms of energy efficiency, power consumption and throughput, which can be …
Cited by:12
Resources:[PDF] from irisa.fr
:view less
Accelerated visual context classification on a low-power smartwatch
2016
Francesco Conti, Daniele Palossi, Renzo Andri, Michele Magno, Luca Benini
IEEE Transactions on Human-Machine Systems 47 (1), 19-30
:read more
Authors:Francesco Conti, Daniele Palossi, Renzo Andri, Michele Magno, Luca Benini
Publication date:11/18/2016
Journal:IEEE Transactions on Human-Machine Systems
Volume:47
Issue:1
Pages:19-30
Publisher:IEEE
Description:Data produced by wearable sensors is key in contexts such as performance enhancement and training help for sports and fitness, continuous monitoring for aging people and for chronic disease management, and in gaming and entertainment. Unfortunately, wearable devices currently in the market are either incapable of complex functionality or severely impaired by short battery lifetime. In this work, we present a smart watch platform based on an ultralow-power (ULP) heterogeneous system composed of a TI MSP430 microcontroller, the PULP programmable parallel accelerator, and a set of ULP sensors, including a camera. The embedded PULP accelerator enables state-of-the-art context classification based on convolutional neural networks to be applied within a sub-10-mW system power envelope. Our methodology enables to reach high accuracy in context classification over five classes (up to 84%, with three …
Cited by:51
Resources:[PDF] from ethz.ch
:view less
Optimum excitations for a dual-band microwatt wake-up radio
2016
Massimo Del Prete, Alessandra Costanzo, Michele Magno, Diego Masotti, Luca Benini
IEEE Transactions on Microwave Theory and Techniques 64 (12), 4731-4739
:read more
Authors:Massimo Del Prete, Alessandra Costanzo, Michele Magno, Diego Masotti, Luca Benini
Publication date:11/17/2016
Journal:IEEE Transactions on Microwave Theory and Techniques
Volume:64
Issue:12
Pages:4731-4739
Publisher:IEEE
Description:To enable pervasive exploitation of wireless sensor networks, semipassive wake-up radios (WuRs) are proposed to minimize the active time of the energy-hungry main communication radio. The most challenging feature is to enhance their sensitivity, the weakest activation signal the receiver is able to sense, which is limited by the minimum turn-on voltage of the diode-based detector. In order to operate the detector at even lower power levels, a strategy to optimize the modulated WuR excitations is presented, exploiting high-peak intermittent continuous waves while preserving the required average power per bit. The design and implementation of an ultralow-power detector, fed by a dual-band antenna and loaded by the WuR backend is presented: 2.45-GHz and 868-MHz operations of the same WuR are demonstrated, with added flexibility and interoperability among different communication bands. We show that a …
Cited by:30
:view less
A smart LED light control system for environmentally friendly buildings
2016
Michele Magno, Tommaso Polonelli, Luca Benini
International Conference on Applications in Electronics Pervading Industry, Environment…
:read more
Authors:Michele Magno, Tommaso Polonelli, Luca Benini
Publication date:09/15/2016
Journal:International Conference on Applications in Electronics Pervading Industry, Environment and Society
Pages:181-189
Publisher:Springer International Publishing
Description:This paper proposes a low cost, wireless, easy to install, adaptable smart LED lighting system to automatically adjust the light intensity of LED panels to save energy and to maintain user satisfaction. The wireless control system is based on ZigBee communication and combines a light sensor with a motion sensor to perform an energy saving algorithm. Measurements of total energy consumption over a continuous six-month period were acquired to verify the performance and evaluate the benefits in terms of power savings of the proposed solution. In the monitored application scenario, the total energy consumption has been reduced by over 60 % during a six-month period and up to 70 % in spring months.
Cited by:2
:view less
Low-power gas sensing using single walled carbon nano tubes in wearable devices
2016
Michele Magno, Vana Jelicic, Kiran Chikkadi, Cosmin Roman, Christofer Hierold, Vedran B…
Ieee sensors journal 16 (23), 8329-8337
:read more
Authors:Michele Magno, Vana Jelicic, Kiran Chikkadi, Cosmin Roman, Christofer Hierold, Vedran Bilas, Luca Benini
Publication date:09/05/2016
Journal:Ieee sensors journal
Volume:16
Issue:23
Pages:8329-8337
Publisher:IEEE
Description:Air quality monitoring is gaining importance in public health due to the increasing level of the pollution in cities. In addition, people are more concerned about their personal exposure and they are interested to know the concentration levels of the pollutants, which surround them. In recent years, a wearable technology can be useful for continuous air quality monitoring when people are moving in urban and industrial environments. As wearable systems are usually battery-powered and gas sensors are power-hungry, energy-efficient design and power management are required. In this paper, we present a two-stage gas sensing concept where novel multiple-single-walled carbon nanotubes (SWCNT) are proposed as detectors for an energy-hungry metal-oxide (MOX)-semiconductor gas sensor. We simulate the system performance combining the low power consumption of SWCNT gas sensors and the more mature …
Cited by:31
Resources:[PDF] from researchgate.net
:view less
InfiniTime: Multi-sensor wearable bracelet with human body harvesting
2016
Michele Magno, Davide Brunelli, Lukas Sigrist, Renzo Andri, Lukas Cavigelli, Andres Gom…
Sustainable Computing: Informatics and Systems 11, 38-49
:read more
Authors:Michele Magno, Davide Brunelli, Lukas Sigrist, Renzo Andri, Lukas Cavigelli, Andres Gomez, Luca Benini
Publication date:09/01/2016
Journal:Sustainable Computing: Informatics and Systems
Volume:11
Pages:38-49
Publisher:Elsevier
Description:Wearable technology is gaining popularity, with people wearing everything “smart” from clothing to glasses and watches. Present-day wearables are typically battery-powered, and their limited lifetime has become the critical issue. Most devices need recharging every few days or even hours, falling short of the expectations for a truly satisfactory user experience. This paper presents the design, implementation and in-field evaluation of InfiniTime, a novel sensor-rich smart bracelet powered by energy harvesting. It is designed to achieve self-sustainability using solar cells with only modest indoor light levels and thermoelectric generators (TEG’s) with small temperature gradients from the body heat. The wearable device is equipped with an ultra-low power camera and a microphone, in addition to accelerometer and temperature sensors commonly used in commercial devices. Experimental characterization of the fully …
Cited by:113
:view less
A low latency and energy efficient communication architecture for heterogeneous long-short range communication
2016
Fayçal Ait Aoudia, Michele Magno, Matthieu Gautier, Olivier Berder, Luca Benini
2016 Euromicro conference on digital system design (DSD), 200-206
:read more
Authors:Fayçal Ait Aoudia, Michele Magno, Matthieu Gautier, Olivier Berder, Luca Benini
Publication date:08/31/2016
Journal:2016 Euromicro conference on digital system design (DSD)
Pages:200-206
Publisher:IEEE
Description:Low power communication has evolved towards multi-kilometer ranges and low bit-rate schemes in recent years. LoRa is an example of such a long-range technology that is triggering increasing interest. Using these technologies, a trade-off must be made between power consumption and latency for message transfer from the gateway to the nodes. However, domains such as industrial applications in which sensors and actuators are part of the control loop require predictable latency, as well as low power consumption. These requirements can be fulfilled using pure-asynchronous communication and idle listening elimination, allowed by emerging ultra-low-power wake-up receivers. On the other hand, state-of-the-art wake-up receivers present low sensitivity compared to traditional wireless node receivers and LoRa, which results in the fact that they can operate in short-range in the order of a few tens of meters. In …
Cited by:28
Resources:[PDF] from researchgate.net
:view less
Evaluation of synchronization protocols for fine-grain HPC sensor data time-stamping and collection
2016
Antonio Libri, Andrea Bartolini, Michele Magno, Luca Benini
2016 International Conference on High Performance Computing & Simulation (HPCS), 818-825
:read more
Authors:Antonio Libri, Andrea Bartolini, Michele Magno, Luca Benini
Publication date:07/18/2016
Journal:2016 International Conference on High Performance Computing & Simulation (HPCS)
Pages:818-825
Publisher:IEEE
Description:Solutions for accurate and fine-grain monitoring are at the basis of the growth of future large-scale green high performance computing (HPC) infrastructures. The capability of these systems to adapt to specific application requirements relies on sensing and correlating several distributed physical parameters with application phases and states. Meeting such requirements allows thus to achieve a better use of the resources, higher throughput and higher energy-efficiency. As the capability of drawing such correlations relies on the synchronization across a network of nodes and measuring devices, the use of synchronization protocols becomes a critical component. Novel low-cost embedded devices start to include hardware support for network synchronization protocols to achieve a high resolution time accuracy. These devices are promising for monitoring physical parameters of HPC infrastructures. In this paper we …
Cited by:18
Resources:[PDF] from ethz.ch
:view less
Kinetic energy harvesting: Toward autonomous wearable sensing for Internet of Things
2016
Michele Magno, Lorenzo Spadaro, Jaskirat Singh, Luca Benini
2016 International Symposium on Power Electronics, Electrical Drives, Automation and Mo…
:read more
Authors:Michele Magno, Lorenzo Spadaro, Jaskirat Singh, Luca Benini
Publication date:06/22/2016
Journal:2016 International Symposium on Power Electronics, Electrical Drives, Automation and Motion (SPEEDAM)
Pages:248-254
Publisher:IEEE
Description:Power supply availability is a limiting factor in wearable devices whose form factor constrains battery size. Wearable harvesters that collect energy from the environment are a promising technology to achieve the long-life goal for truly wearable devices. However, most of the mature energy harvesting approaches usually imply an outdoor setting, using solar panels, wind turbines or high-frequency vibration as energy sources. In particular, most kinetic harvesters are not effective with human motion frequencies and mobility patterns. In this paper, we evaluate and integrate a highly-efficient kinetic harvester circuit to power autonomous wearable devices, exploiting the energy gathered from human motion. For this purpose, a Kinetron Micro Generator System 26.4 (MSG) has been characterized, conversion circuits have been designed and evaluated using off-the-shelf components. The implemented kinetic harvesting …
Cited by:63
Resources:[PDF] from unibo.it
:view less
b+ WSN: Smart beehive with preliminary decision tree analysis for agriculture and honey bee health monitoring
2016
Fiona Edwards-Murphy, Michele Magno, Pádraig M Whelan, John O’Halloran, Emanuel M Popov…
Computers and Electronics in Agriculture 124, 211-219
:read more
Authors:Fiona Edwards-Murphy, Michele Magno, Pádraig M Whelan, John O’Halloran, Emanuel M Popovici
Publication date:06/01/2016
Journal:Computers and Electronics in Agriculture
Volume:124
Pages:211-219
Publisher:Elsevier
Description:United Nations reports throughout recent years have stressed the growing constraint of food supply for Earth’s growing human population. Honey bees are a vital part of the food chain as the most important pollinator for a wide range of crops. It is clear that protecting the population of honey bees worldwide, as well as enabling them to maximise their productivity, is an important concern. In this paper heterogeneous wireless sensor networks are utilised to collect data on a range of parameters from a beehive with the aim of accurately describing the internal conditions and colony activity. The parameters measured were: CO2, O2, pollutant gases, temperature, relative humidity, and acceleration. Weather data (sunshine, rain, and temperature) were also collected to provide an additional analysis dimension. Using a data set from a deployment at a field-deployed beehive, a biological analysis was undertaken to classify …
Cited by:196
:view less
Autonomous smartwatch with flexible sensors for accurate and continuous mapping of skin temperature
2016
Michele Magno, Giovanni A Salvatore, Severin Mutter, Waleed Farrukh, Gerhard Troester, …
2016 IEEE International Symposium on Circuits and Systems (ISCAS), 337-340
:read more
Authors:Michele Magno, Giovanni A Salvatore, Severin Mutter, Waleed Farrukh, Gerhard Troester, Luca Benini
Publication date:05/22/2016
Journal:2016 IEEE International Symposium on Circuits and Systems (ISCAS)
Pages:337-340
Publisher:IEEE
Description:Epidermal sensors, which form an intimate and robust contact with the skin, are capable of providing clinically relevant information about cardiovascular health, electrophysiology and dermatology with high accuracy and in an unobtrusive manner. To enable clinical applications, however, continuous and long-term monitoring is necessary. In addition, wireless and energetically autonomous systems are highly desirable to eliminate the needs of tethers and cables for powering and data transmission. Such requirements call for devices that combine accurate and precise sensing with high performance electronics for signal treatment, communication and power management in formats which conformal laminate on the body. In this work, we present a novel system whose design leverages on the recent developments in low power wearable devices and flexible sensors. It consists of an ultra-low power smartwatch …
Cited by:22
:view less
Experimental analysis of power optimized waveforms for enhancing wake-up radio sensitivity
2016
Massimo Del Prete, Alessandra Costanzo, Diego Masotti, Tommaso Polonelli, Michele Magno…
2016 IEEE MTT-S International Microwave Symposium (IMS), 1-4
:read more
Authors:Massimo Del Prete, Alessandra Costanzo, Diego Masotti, Tommaso Polonelli, Michele Magno, Luca Benini
Publication date:05/22/2016
Journal:2016 IEEE MTT-S International Microwave Symposium (IMS)
Pages:1-4
Publisher:IEEE
Description:To minimize energy consumption of state-of-the-art wireless sensor nodes, asynchronous communication transceivers are adopted, which make use of an ultra-low power wake-up radio (WUR) to minimize the active time of the energy-hungry main communication radio. This work contributes to the ambitious goal of pushing over the minimum average RF power needed to operate the WUR, thus enabling energy-efficient communication in larger areas. To reach this goal a dual-band rectifier, optimized to be loaded by an ultra-low power comparator, is used as WUR detector. Its behavior is experimentally tested under several power-optimized excitation formats. By selecting the proper excitation format the base-band comparator is enabled starting from average RF-power as low as -64.5 dBm.
Cited by:7
:view less
A wake-up receiver with ad-hoc antenna co-design for wearable applications
2016
Tommaso Polonelli, Trinh Le Huy, Leonardo Lizzi, Fabien Ferrero, Michele Magno
2016 IEEE Sensors Applications Symposium (SAS), 1-6
:read more
Authors:Tommaso Polonelli, Trinh Le Huy, Leonardo Lizzi, Fabien Ferrero, Michele Magno
Publication date:04/20/2016
Journal:2016 IEEE Sensors Applications Symposium (SAS)
Pages:1-6
Publisher:IEEE
Description:Body Area Networks (BAN) have received significant attention in recent years and have found a wide range of applications, including wearable devices for fitness and health tracking, and mobile communications. Battery lifetime continues to be the main bottleneck in these small form factor devices, thus low power design and advanced power management techniques are required to sustain the increasing demands on power. As radio transceivers are typically the most power hungry subsystem in a wearable sensors device, optimizations to reduce the communication power consumption, such as using adaptive power management coupled with ultra-low power receivers have been widely investigated. In this work, we focus on the design of a novel wearable wake-up radio consuming only few nW during listening mode, significantly reducing the overall power consumption of communication, which enables …
Cited by:11
:view less
Wake-up receivers for energy efficient and low latency communication
2016
Fayçal Ait Aoudia, Michele Magno, Matthieu Gautier, Olivier Berder, Luca Benini
2016 15th ACM/IEEE International Conference on Information Processing in Sensor Network…
:read more
Authors:Fayçal Ait Aoudia, Michele Magno, Matthieu Gautier, Olivier Berder, Luca Benini
Publication date:04/11/2016
Journal:2016 15th ACM/IEEE International Conference on Information Processing in Sensor Networks (IPSN)
Pages:1-2
Publisher:IEEE
Description:Long lifetime is the most pursued goal in Wireless Sensor Networks (WSNs). As communication is typically the most energy consuming task, a lot of effort has been devoted to design energy efficient communication protocols using duty-cycling in the last decades. However, in the recent years, a new kind of Ultra Low Power (ULP) receivers, called Wake-up Receivers (WuRx), is emerging. These devices allow the continuous monitoring of the wireless channel while having a power consumption orders of magnitude less than typical WSNs transceivers. WuRx can wake-up the rest of the system (microcontroller (MCU) and main radio) using interrupts only when needed, minimizing the idle listening. In this work, we present an experimental and an analytical study which ultimately serve as guidelines for the design of communication protocols leveraging WuRx.
Cited by:8
Resources:[PDF] from hal.science
:view less
An ultra-low power wake up radio with addressing and retransmission capabilities for advanced energy efficient MAC protocols
2016
Tommaso Polonelli, Michele Magno, Luca Benini
2016 15th ACM/IEEE International Conference on Information Processing in Sensor Network…
:read more
Authors:Tommaso Polonelli, Michele Magno, Luca Benini
Publication date:04/11/2016
Journal:2016 15th ACM/IEEE International Conference on Information Processing in Sensor Networks (IPSN)
Pages:1-2
Publisher:IEEE
Description:Wireless sensor networks (WSNs) are today widely employed in real world applications. However, their lifetime is still challenging and the most critical limitation for the success of this technology. In fact, wireless sensors nodes, which are the backbone of the network, are typically powered by limited energy storage devices (i.e. small batteries or supercaps) and their short lifetime is a critical issue. To overcome this limitation a major research effort focuses on reducing power consumption, especially of communication, as the radio transceiver is one of the highest power consumers. A critical energy-efficiency issue in WSN transceivers is idle listening. Wake-up radio receivers are very effective in minimizing idle listening. This fact has resulted in a significant number of wake-up radio receiver architectures proposed in last decade. In this work we present an advanced design and implementation of an advanced wake-up …
Cited by:10
:view less
Kinetisee-a perpetual wearable camera acquisition system with a kinetic harvester
2016
Lorenzo Spadaro, Michele Magno, Luca Benini
2016 15th ACM/IEEE International Conference on Information Processing in Sensor Network…
:read more
Authors:Lorenzo Spadaro, Michele Magno, Luca Benini
Publication date:04/11/2016
Journal:2016 15th ACM/IEEE International Conference on Information Processing in Sensor Networks (IPSN)
Pages:1-2
Publisher:IEEE
Description:Wearable devices are massively entering in our life and they are more and more pushing the interest big electronic producer. Then, today many company are offering wearable "smart" objects to be worn which enable a wide range of application (form sport & fitness, to entrainment, from tracking to health care). A common issue of wearable device that is reducing the appeal of them is the limited lifetime due to limited energy that can be stored in them batteries. Self-sustainable devices which can avoid to recharge or replace the batteries, as it happens in automatic quartz watches, is still a dream for wearable devices. This paper presents a wearable device with an ultra low camera, which can achieve this dream. To achieve this goal, the Wearable camera has been carefully designed with low power consumption in mind and leveraging a kinetic energy harvester to scavenge energy from the human body movements …
Cited by:16
:view less
Magonode++-a wake-up-radio-enabled wireless sensor mote for energy-neutral applications
2016
Mario Paoli, Dora Spenza, Chiara Petrioli, Michele Magno, Luca Benini
2016 15th ACM/IEEE International Conference on Information Processing in Sensor Network…
:read more
Authors:Mario Paoli, Dora Spenza, Chiara Petrioli, Michele Magno, Luca Benini
Publication date:04/11/2016
Journal:2016 15th ACM/IEEE International Conference on Information Processing in Sensor Networks (IPSN)
Pages:1-2
Publisher:IEEE
Description:The combination of low-power design, energy harvesting and ultra-low-power wake-up radios is paving the way for perpetual operation of Wireless Sensor Networks (WSNs). In this work we present the MagoNode++, a novel WSN platform supporting energy harvesting and radio-triggered wake ups for energy- neutral applications. The MagoNode++ features an energy- harvesting subsystem composed by a light or thermoelectric harvester, a battery manager and a power manager module. It further integrates a state-of-the-art RF Wake-Up Receiver (WUR) that enables low-latency asynchronous communication, virtually eliminating idle listening at the main transceiver. Experimental results show that the MagoNode++ consumes only 2.8uA with the WUR in idle listening and the rest of the platform in sleep state, making it suitable for energy-constrained WSN scenarios and for energy-neutral applications.
Cited by:34
Resources:[PDF] from uniroma1.it
:view less
An energy aware adaptive sampling algorithm for energy harvesting WSN with energy hungry sensors
2016
Bruno Srbinovski, Michele Magno, Fiona Edwards-Murphy, Vikram Pakrashi, Emanuel Popovici
Sensors 16 (4), 448
:read more
Authors:Bruno Srbinovski, Michele Magno, Fiona Edwards-Murphy, Vikram Pakrashi, Emanuel Popovici
Publication date:03/28/2016
Journal:Sensors
Volume:16
Issue:4
Pages:448
Publisher:MDPI
Description:Wireless sensor nodes have a limited power budget, though they are often expected to be functional in the field once deployed for extended periods of time. Therefore, minimization of energy consumption and energy harvesting technology in Wireless Sensor Networks (WSN) are key tools for maximizing network lifetime, and achieving self-sustainability. This paper proposes an energy aware Adaptive Sampling Algorithm (ASA) for WSN with power hungry sensors and harvesting capabilities, an energy management technique that can be implemented on any WSN platform with enough processing power to execute the proposed algorithm. An existing state-of-the-art ASA developed for wireless sensor networks with power hungry sensors is optimized and enhanced to adapt the sampling frequency according to the available energy of the node. The proposed algorithm is evaluated using two in-field testbeds that are supplied by two different energy harvesting sources (solar and wind). Simulation and comparison between the state-of-the-art ASA and the proposed energy aware ASA (EASA) in terms of energy durability are carried out using in-field measured harvested energy (using both wind and solar sources) and power hungry sensors (ultrasonic wind sensor and gas sensors). The simulation results demonstrate that using ASA in combination with an energy aware function on the nodes can drastically increase the lifetime of a WSN node and enable self-sustainability. In fact, the proposed EASA in conjunction with energy harvesting capability can lead towards perpetual WSN operation and significantly outperform the state-of-the-art ASA.
Cited by:80
Resources:[HTML] from mdpi.com
Full View
:view less
Low-power multichannel spectro-temporal feature extraction circuit for audio pattern wake-up
2016
Dinko Oletic, Vedran Bilas, Michele Magno, Norbert Felber, Luca Benini
2016 Design, automation & test in Europe conference & exhibition (DATE), 355-360
:read more
Authors:Dinko Oletic, Vedran Bilas, Michele Magno, Norbert Felber, Luca Benini
Publication date:03/14/2016
Journal:2016 Design, automation & test in Europe conference & exhibition (DATE)
Pages:355-360
Publisher:IEEE
Description:In many distributed sensing applications, continuous sensor monitoring requires processing with a significant energy footprint, which hinders autonomous operation and battery lifetime of sensor nodes. In our research we explore the power savings gained by splitting the hardware architecture for continuous monitoring into two stages: an always-on ultra-low-power mixed-signal wake-up circuit placed near the sensor, performing coarse recognition (e.g. wake-up circuit) and waking up the main digital processing unit only on event detection. This enables for activation of energy-hungry digital processing only at the rate of event occurrence without penalising responsiveness and monitoring continuity. We focus on the wake-up circuit performing recognition of spectro-temporal audio patterns, consisting of spectro-temporal feature extraction, and the classification sub-circuits. We propose a novel design of the feature …
Cited by:14
Resources:[PDF] from date-conference.com
:view less
Dynamic energy burst scaling for transiently powered systems
2016
Andres Gomez, Lukas Sigrist, Michele Magno, Luca Benini, Lothar Thiele
2016 Design, Automation & Test in Europe Conference & Exhibition (DATE), 349-354
:read more
Authors:Andres Gomez, Lukas Sigrist, Michele Magno, Luca Benini, Lothar Thiele
Publication date:03/14/2016
Journal:2016 Design, Automation & Test in Europe Conference & Exhibition (DATE)
Pages:349-354
Publisher:IEEE
Description:Energy harvesting is generally seen to be the key to power cyber-physical systems in a low-cost, long term, efficient manner. However, harvesting has traditionally been coupled with large energy storage devices to mitigate the effects of the source's variability. The emerging class of transiently powered systems avoids this issue by performing computation only as a function of the harvested energy, minimizing the obtrusive and expensive storage element. In this work, we present an efficient Energy Management Unit (EMU) to supply generic loads when the average harvested power is much smaller than required for sustained system operation. By building up charge to a pre-defined energy level, the EMU can generate short energy bursts predictably, even under variable harvesting conditions. Furthermore, we propose a dynamic energy burst scaling (DEBS) technique to adjust these bursts to the load's requirements …
Cited by:91
Resources:[PDF] from ethz.ch
:view less
Design, implementation, and performance evaluation of a flexible low-latency nanowatt wake-up radio receiver
2016
Michele Magno, Vana Jelicic, Bruno Srbinovski, Vedran Bilas, Emanuel Popovici, Luca Benini
IEEE Transactions on Industrial Informatics 12 (2), 633-644
:read more
Authors:Michele Magno, Vana Jelicic, Bruno Srbinovski, Vedran Bilas, Emanuel Popovici, Luca Benini
Publication date:02/05/2016
Journal:IEEE Transactions on Industrial Informatics
Volume:12
Issue:2
Pages:633-644
Publisher:IEEE
Description:Wireless sensor networks (WSNs) have received significant attention in recent years and have found a wide range of applications, including structural and environmental monitoring, mobile health, home automation, Internet of Things, and others. As these systems are generally battery operated, major research efforts focus on reducing power consumption, especially for communication, as the radio transceiver is one of the most power-hungry components of a WSN. Moreover, with the advent of energy-neutral systems, the emphasis has shifted toward research in microwatt (or even nanowatt) communication protocols or systems. A significant number of wake-up radio receiver (WUR) architectures have been proposed to reduce the communication power of WSN nodes. In this work, we present an optimized ultra-low power (nanowatt) wake-up receiver for use in WSNs, designed with low-cost off-the-shelf components …
Cited by:198
Resources:[PDF] from unibo.it
:view less
A dual-band wake-up radio for ultra-low power wireless sensor networks
2016
Massimo Del Prete, Diego Masotti, Alessandra Costanzo, Michele Magno, Luca Benini
2016 IEEE Topical Conference on Wireless Sensors and Sensor Networks (WiSNet), 81-84
:read more
Authors:Massimo Del Prete, Diego Masotti, Alessandra Costanzo, Michele Magno, Luca Benini
Publication date:01/24/2016
Journal:2016 IEEE Topical Conference on Wireless Sensors and Sensor Networks (WiSNet)
Pages:81-84
Publisher:IEEE
Description:Wake-up radio is an emerging technology for smart sensor networks and the Internet of Things with the ambitious goal of minimizing the power needed to communicate, thus enabling a new generation of applications. Wake-up radios should exhibit low latency coupled with high sensitivity, addressing capabilities with ultra-low power budget. They may be combined with existing radio transceivers and power management units to reduce the overall communication power while maintaining a high performance. This paper presents a 2.45 GHz and 868 MHz wake-up radio with the above mentioned characteristics. Dual band is exploited to increase the flexibility of the wakeup radio, allowing interoperability with the two most common bands used in Wireless Sensors Network and Internet of Things. Simulations results present a system with sensitivity as low as -55 dBm at 868 MHz and -53 dBm at 2.45 GHz.
Cited by:15
:view less
Special Issue on Wearable and Ego-Vision Systems for Augmented Experience
2016
G Serra, R Cucchiara, KM Kitani, J Civera, F Conti, D Palossi, R Andri, M Magno, L Beni…
IEEE Trans. Human-Mach. Syst 47 (1), 1-5
:read more
Authors:G Serra, R Cucchiara, KM Kitani, J Civera, F Conti, D Palossi, R Andri, M Magno, L Benini, K Ozcan, S Velipasalar, PK Varshney, A Brutti, A Cavallaro, F Grijalva, VRML Maike, LC Martini, D Florencio, MCC Baranauskas, A Rocha, S Goldenstein
Publication date:01/01/2016
Journal:IEEE Trans. Human-Mach. Syst
Volume:47
Issue:1
Pages:1-5
Description:Presents the table of contents for this issue of the periodical.
Cited by:5
:view less
Ultra-low power context recognition fusing sensor data from an energy-neutral smart watch
2015
Michele Magno, Lukas Cavigelli, Renzo Andri, Luca Benini
International Internet of Things Summit, 331-343
:read more
Authors:Michele Magno, Lukas Cavigelli, Renzo Andri, Luca Benini
Publication date:10/27/2015
Journal:International Internet of Things Summit
Pages:331-343
Publisher:Springer International Publishing
Description:Today sensors and wearable technologies are gaining popularity, with people increasingly surrounded by “smart” objects. Machine learning is used with great success in wearable devices and sensors in several real-world applications. In this paper we address the challenges of context recognition on low energy and self-sustainable wearable devices. We present an energy efficient multi-sensor context recognition system based on decision tree to classify 3 different indoor or outdoor contexts. An ultra-low power smart watch provided with a micro-power camera, microphone, accelerometer, and temperature sensors has been used to real field tests. Experimental results demonstrate both high mean accuracy of 81.5 % (up to 89 % peak) and low energy consumption (only 2.2 mJ for single classification) of the solution, and the possibility to achieve a self-sustainable system in combination with body worn energy …
Cited by:5
Resources:[PDF] from ethz.ch
:view less
Practical Implementation Aspects of the Data Timed Sending (DTS) Protocol Using Wake-up Radio (WuR)
2015
Konstantin Chomu, Vladimir Atanasovski, Liljana Gavrilovska, Michele Magno
International Symposium on Pervasive Computing Paradigms for Mental Health, 139-144
:read more
Authors:Konstantin Chomu, Vladimir Atanasovski, Liljana Gavrilovska, Michele Magno
Publication date:10/26/2015
Journal:International Symposium on Pervasive Computing Paradigms for Mental Health
Pages:139-144
Publisher:Springer International Publishing
Description: The energy efficient Data Timed Sending (DTS) protocol enables information transfer from sensor nodes to sink host by choosing the appropriate transmission time of a short packet without data payload. Wake-up Radio (WuR) devices allow asynchronous communication of Wireless Sensor Networks (WSNs) putting the sensor nodes’ main radio modules in continuous sleep state thus increasing energy efficiency. A common characteristic for the DTS protocol and WuR is that they are designed for applications where sensors take sparse measurements, typically one measurement every few minutes. This paper investigates the combination of the DTS protocol with WuR into a single integrated solution. The analytical analysis shows that the DTS protocol significantly reduces the energy consumption when coupled with WuR making this solution suitable for applications with battery powered WSN (e.g. body area WSN).
:view less
Context aware power management enhanced by radio wake up in body area networks
2015
Filippo Casamassima, Michele Magno, Elisabetta Farella, Luca Benini
2015 IEEE 13th International Conference on Embedded and Ubiquitous Computing, 76-82
:read more
Authors:Filippo Casamassima, Michele Magno, Elisabetta Farella, Luca Benini
Publication date:10/21/2015
Journal:2015 IEEE 13th International Conference on Embedded and Ubiquitous Computing
Pages:76-82
Publisher:IEEE
Description:Wireless body area networks (WBANs) have the huge potential to enhance people's lives. They are already present in many application domains, for instance sport and fitness, but they are wide spreading in particular in health and rehabilitation. However, there are still challenging issues that limit their wide diffusion in real life: primarily, the limited lifetime due to the batteries that usually supply the devices. This limitation affects usability and force the data processing to be simple to match the power constraints. This work tries to address the energy limitation by enabling both efficient and complex signal-processing applications and extension of lifetime. We present a power management strategy combining an ultra-low power wake up radio with context awareness. The context aware power manager based on activity recognition decides which nodes must be activated exploiting a nano-power wake up radio and …
Cited by:3
:view less
A 2.4 GHz-868 MHz dual-band wake-up radio for wireless sensor network and IoT
2015
Massimo Del Prete, Diego Masotti, Alessandra Costanzo, Michele Magno, Luca Benini
2015 IEEE 11th International Conference on Wireless and Mobile Computing, Networking an…
:read more
Authors:Massimo Del Prete, Diego Masotti, Alessandra Costanzo, Michele Magno, Luca Benini
Publication date:10/19/2015
Journal:2015 IEEE 11th International Conference on Wireless and Mobile Computing, Networking and Communications (WiMob)
Pages:322-328
Publisher:IEEE
Description:Wake-up radio is an emerging technology with the ambitious goal of reducing the communication power consumption in smart sensor networks and Internet of Things. This reduction in power consumption will enable a new generation of applications which could achieve a longer lifetime than is achievable today. Wake up radios are required to work with a low power budget and should exhibit low latency coupled with high sensitivity and addressing capabilities. Typically they are combined with existing radio transceiver and power management techniques to reduce the overall communication power while maintaining the same communication performance. This paper presents a dual band (2.4GHz and 868MHz) wake up radio with the above mentioned characteristics. The dual band solution is exploited to increase the flexibility of the wake up radio, allowing interoperability with the two most common frequencies …
Cited by:23
:view less
Extending body sensor nodes’ lifetime using a wearable Wake-up Radio
2015
Andres Gomez, Michele Magno, Xin Wen, Luca Benini
Future Access Enablers of Ubiquitous and Intelligent Infrastructures, 108-117
:read more
Authors:Andres Gomez, Michele Magno, Xin Wen, Luca Benini
Publication date:09/23/2015
Journal:Future Access Enablers of Ubiquitous and Intelligent Infrastructures
Pages:108-117
Publisher:Springer International Publishing
Description:Body Area Networks (BAN) have received significant attention in recent years and have found a wide range of applications, including wearable devices for fitness and health tracking, mobile communications, among others. Energy storage devices such as batteries continue to be a bottleneck in these small form factor devices, thus requiring advanced power management techniques to sustain devices’ increasing power and lifetime demands. As radio transceivers are typically the most power hungry subsystem in wearable sensors devices, many techniques focus to reduce the communication power consumption. In this work, we focus on wake-up radios as a novel technology which can be in listening mode consuming only few nW, significantly reducing the overall power consumption of communication. We evaluate the performance of state-of-the-art wake-up receivers (WUR) in the BAN context, and the tradeoffs …
Cited by:2
Resources:[PDF] from semanticscholar.org
:view less
An automatic, wireless audio recording node for analysis of beehives
2015
Fiona Edwards Murphy, Bruno Srbinovski, Michele Magno, Emanuel M Popovici, Pádraig M Wh…
2015 26th Irish Signals and Systems Conference (ISSC), 1-6
:read more
Authors:Fiona Edwards Murphy, Bruno Srbinovski, Michele Magno, Emanuel M Popovici, Pádraig M Whelan
Publication date:06/24/2015
Journal:2015 26th Irish Signals and Systems Conference (ISSC)
Pages:1-6
Publisher:IEEE
Description:Monitoring the sounds emitted by honey bees in a beehive is an important activity for beekeepers to ensure that their bee colonies remain healthy and to maximise productivity. A particular reproductive event called “swarming”, involves the departure of a queen bee with a large portion of the hive population. Swarming can be identified through sound, and if allowed to occur unchecked can lead to a drop in hive productivity or, in extreme cases, colony death. A method of effectively alerting the keeper that such an event is imminent would aid in protecting the honey bee population and reducing beekeeping costs. In this paper, a solution using off the shelf Wireless Sensor Network (WSN) technologies with low power signal processing to monitor colony sound, as well as the temperature and humidity of the hive interior is presented. The system provides alerts to the beekeeper when an event is detected. The node was …
Cited by:16
:view less
Towards Internet of Things for event-driven low-power gas sensing using carbon nanotubes
2015
Vana Jelicic, Michele Magno, Kiran Chikkadi, Cosmin Roman, Christofer Hierold, Vedran B…
2015 6th International Workshop on Advances in Sensors and Interfaces (IWASI), 271-276
:read more
Authors:Vana Jelicic, Michele Magno, Kiran Chikkadi, Cosmin Roman, Christofer Hierold, Vedran Bilas, Luca Benini
Publication date:06/18/2015
Journal:2015 6th International Workshop on Advances in Sensors and Interfaces (IWASI)
Pages:271-276
Publisher:IEEE
Description:One of most important applications of sensing devices under the Internet of Things paradigm is air quality monitoring, which is particularly useful in urban and industrial environments where air pollution is an increasing public health problem. As these sensing systems are usually battery-powered and gas sensors are power-hungry, energy-efficient design and power management are required to extend the device's lifetime. In this paper, we present a two-stage concept where a novel low-power carbon nanotube is used as a gas detector for an energy-consuming metal-oxide (MOX) semiconductor gas sensor. We propose a design of a heterogeneous sensor node where we exploit the low-power nanotube gas sensor and the more accurate MOX sensor. This work performs energy consumption simulations for three event-driven scenarios to evaluate the power consumption reduction, as well as the limitations of …
Cited by:13
Resources:[PDF] from unibo.it
:view less
Big brother for bees (3B)—Energy neutral platform for remote monitoring of beehive imagery and sound
2015
Fiona Edwards Murphy, Michele Magno, Liam O'Leary, Killian Troy, Pádraig Whelan, Emanue…
2015 6th International Workshop on Advances in Sensors and Interfaces (IWASI), 106-111
:read more
Authors:Fiona Edwards Murphy, Michele Magno, Liam O'Leary, Killian Troy, Pádraig Whelan, Emanuel M Popovici
Publication date:06/18/2015
Journal:2015 6th International Workshop on Advances in Sensors and Interfaces (IWASI)
Pages:106-111
Publisher:IEEE
Description:Honey bees have played a major role in the history and development of humankind, in particular for nutrition and agriculture. The most important role of the western honey bee (Apis mellifera) is that of pollination. A large amount of crops consumed throughout the world today are pollinated by the activity of the honey bee. It is estimated that the total value of these crops stands at 155 billion euro annually. The goal of the work outlined in this paper was to use wireless sensor network technology to monitor a colony within the beehive with the aim of collecting image and audio data. These data allows the beekeeper to obtain a much more comprehensive view of the in-hive conditions, an indication of flight direction, as well as monitoring the hive outside of the traditional beekeeping times, i.e. during the night, poor weather, and winter months. This paper outlines the design of a fully autonomous beehive monitoring …
Cited by:56
Resources:[PDF] from researchgate.net
:view less
Asynchronous on demand MAC protocol using wake-up radio in wireless body area network
2015
Trong Nhan Le, Alain Pegatoquet, Michele Magno
2015 6th International Workshop on Advances in Sensors and Interfaces (IWASI), 228-233
:read more
Authors:Trong Nhan Le, Alain Pegatoquet, Michele Magno
Publication date:06/18/2015
Journal:2015 6th International Workshop on Advances in Sensors and Interfaces (IWASI)
Pages:228-233
Publisher:IEEE
Description:A fast growing class of sensing technology is wearable, where network nodes are tightly coupled with the human body. Wireless body area networks (WBAN) technology has gained popularity over the last few years, with a wide range of applications covered, in particular in health and rehabilitation. Wearable and pervasive computing are able to sense, monitor and process the data to provide smart assistance and context-aware ambient intelligence environments. However present-day WBAN devices are mainly battery-powered and due to energy issue they need to be recharged every day or even hours and thus they miss the expectations for a truly unobtrusive user experience. This work presents a novel energy-efficient asynchronous MAC protocol using a nano-watt wake up radio with addressing capabilities to reduce the energy consumption of the communication and then extend the WBAN life time. We …
Cited by:30
Resources:[PDF] from researchgate.net
:view less
Accelerating real-time embedded scene labeling with convolutional networks
2015
Lukas Cavigelli, Michele Magno, Luca Benini
Proceedings of the 52nd Annual Design Automation Conference, 1-6
:read more
Authors:Lukas Cavigelli, Michele Magno, Luca Benini
Publication date:06/07/2015
Journal:Proceedings of the 52nd Annual Design Automation Conference
Pages:1-6
Description:Today there is a clear trend towards deploying advanced computer vision (CV) systems in a growing number of application scenarios with strong real-time and power constraints. Brain-inspired algorithms capable of achieving record-breaking results combined with embedded vision systems are the best candidate for the future of CV and video systems due to their flexibility and high accuracy in the area of image understanding. In this paper, we present an optimized convolutional network implementation suitable for real-time scene labeling on embedded platforms. We show that our algorithm can achieve up to 96GOp/s, running on the Nvidia Tegra K1 embedded SoC. We present experimental results, compare them to the state-of-the-art, and demonstrate that for scene labeling our approach achieves a 1.5x improvement in throughput when compared to a modern desktop CPU at a power budget of only 11 W.
Cited by:143
Resources:[PDF] from ethz.ch
:view less
An energy neutral wearable camera with EPD display
2015
Jetmir Nehani, Davide Brunelli, Michele Magno, Lukas Sigrist, Luca Benini
Proceedings of the 2015 workshop on Wearable Systems and Applications, 1-6
:read more
Authors:Jetmir Nehani, Davide Brunelli, Michele Magno, Lukas Sigrist, Luca Benini
Publication date:05/18/2015
Journal:Proceedings of the 2015 workshop on Wearable Systems and Applications
Pages:1-6
Description:Wearable technologies are flooding the consumer market, and have massively entered the market of electronic consumers and people are now surrounded by an increasing number of "smart" objects to wear. The main issue that limits the success of these devices is limited battery lifetime. Energy-neutral operation, which does not require battery recharging or replacement (similar to automatic quartz watches) is highly desirable in this context. In this paper, we present the first energy-neutral wearable device, equipped with an ultra low power camera and an electrophoretic display (EPD) which is supplied by a solar energy harvester. The novel design includes several hardware and software optimizations to achieve energy neutrality. In particular, we implemented innovative methods for displaying gray-scale images to obtain up to 9 gray-scale levels using a black-and-white display. This reduces by 43.7% the energy …
Cited by:9
Resources:[PDF] from unitn.it
:view less
Development of an heterogeneous wireless sensor network for instrumentation and analysis of beehives
2015
Fiona Edwards Murphy, Emanuel Popovici, Padraig Whelan, Michele Magno
2015 IEEE International Instrumentation and Measurement Technology Conference (I2MTC) P…
:read more
Authors:Fiona Edwards Murphy, Emanuel Popovici, Padraig Whelan, Michele Magno
Publication date:05/11/2015
Journal:2015 IEEE International Instrumentation and Measurement Technology Conference (I2MTC) Proceedings
Pages:346-351
Publisher:IEEE
Description:Honey bees have held a critical role in agriculture and nutrition from the dawn of human civilisation. The most crucial role of the bee is pollination; the value of pollination dependant crops is estimated at € 155 billion per year with honey bees identified as the most important pollinator insect. It is clear that honey bees are a vitally important part of the environment which cannot be allowed to fall into decline. The project outlined in this paper uses Wireless Sensor Network (WSN) technology to monitor a beehive colony and collect key information about activity/environment within a beehive as well as its surrounding area. This project uses low power WSN technologies, including novel sensing techniques, energy neutral operation, and multi-radio communications; together with cloud computing to monitor the behaviour within a beehive. The insights gained through this activity could reduce long term costs and improve …
Cited by:76
:view less
Beyond duty cycling: Wake-up radio with selective awakenings for long-lived wireless sensing systems
2015
Dora Spenza, Michele Magno, Stefano Basagni, Luca Benini, Mario Paoli, Chiara Petrioli
2015 IEEE conference on computer communications (INFOCOM), 522-530
:read more
Authors:Dora Spenza, Michele Magno, Stefano Basagni, Luca Benini, Mario Paoli, Chiara Petrioli
Publication date:04/26/2015
Journal:2015 IEEE conference on computer communications (INFOCOM)
Pages:522-530
Publisher:IEEE
Description:Emerging wake-up radio technologies have the potential to bring the performance of sensing systems and of the Internet of Things to the levels of low latency and very low energy consumption required to enable critical new applications. This paper provides a step towards this goal with a twofold contribution. We first describe the design and prototyping of a wake-up receiver (WRx) and its integration to a wireless sensor node. Our WRx features very low power consumption (<; 1.3μW), high sensitivity (up to -55dBm), fast reactivity (wake-up time of 130μs), and selective addressing, a key enabler of new high performance protocols. We then present ALBA-WUR, a cross-layer solution for data gathering in sensing systems that redesigns a previous leading protocol, ALBA-R, extending it to exploit the features of our WRx. We evaluate the performance of ALBA-WUR via simulations, showing that the use of the WRx …
Cited by:188
Resources:[PDF] from uniroma1.it
:view less
b+ WSN: Smart beehive for agriculture, environmental, and honey bee health monitoring—Preliminary results and analysis
2015
Fiona Edwards Murphy, Michele Magno, Padraig Whelan, Emanuel Popo Vici
2015 IEEE sensors applications symposium (SAS), 1-6
:read more
Authors:Fiona Edwards Murphy, Michele Magno, Padraig Whelan, Emanuel Popo Vici
Publication date:04/13/2015
Journal:2015 IEEE sensors applications symposium (SAS)
Pages:1-6
Publisher:IEEE
Description:In recent years, various United Nations reports have stressed the growing constraint of food supply for Earth's growing human population. Honey bees are a vital part of the food chain as the most important pollinator insect for a wide range of crops. It is clear that protecting the population of honey bees worldwide, as well as enabling them to maximise their productivity, is an important concern. The work described in this paper utilised heterogeneous wireless sensor networks technologies to gather data unobtrusively from a beehive, describing the conditions and activity of the honey bee colony. A wide range of sensors were deployed for monitoring the multidimensional conditions within a living beehive (including oxygen, carbon dioxide, pollutant levels, temperature, and humidity). Meteorological and environmental conditions outside the hive were also monitored throughout the deployment. The data were then …
Cited by:64
:view less
Self-powered wireless sensor nodes for monitoring radioactivity in contaminated areas using unmanned aerial vehicles
2015
Andres Gomez, Marie Francine Lagadec, Michele Magno, Luca Benini
2015 IEEE sensors applications symposium (SAS), 1-6
:read more
Authors:Andres Gomez, Marie Francine Lagadec, Michele Magno, Luca Benini
Publication date:04/13/2015
Journal:2015 IEEE sensors applications symposium (SAS)
Pages:1-6
Publisher:IEEE
Description:A self-sustainable wireless sensor node for the monitoring radiation in contaminated and poorly accessible areas is presented. The node is designed to work in collaboration with an unmanned aerial vehicle used for two essential mission steps: air-deploying the wireless sensor nodes at suitable locations and acquiring data logs via ultra-low power, short-range radio communication in fly-by mode, after a wake-up routine. The system allows for the use of off-the-shelf components for defining mission, drop-zone and trajectory, for compressing data, and for communication management. The node is equipped with a low-power nuclear radiation sensor and it was designed and implemented with self-sustainability in mind as it will be deployed in hazardous, inaccessible areas. To this end, the proposed node uses a combination of complementary techniques: a low-power microcontroller with non-volatile memory, energy …
Cited by:19
Resources:[PDF] from researchgate.net
:view less
Energy aware adaptive sampling algorithm for energy harvesting wireless sensor networks
2015
Bruno Srbinovski, Michele Magno, Brendan O'Flynn, Vikram Pakrashi, Emanuel Popovici
2015 IEEE sensors applications symposium (SAS), 1-6
:read more
Authors:Bruno Srbinovski, Michele Magno, Brendan O'Flynn, Vikram Pakrashi, Emanuel Popovici
Publication date:04/13/2015
Journal:2015 IEEE sensors applications symposium (SAS)
Pages:1-6
Publisher:IEEE
Description:Wireless sensor nodes have a limited power budget, while they are often expected to be functional for a very long period of time once deployed in the field. Therefore, the minimization of energy consumption and energy harvesting technology are key tools for maximization of network lifetime and achieving self sustainability in Wireless Sensor Networks (WSN). This paper proposes an energy aware Adaptive Sampling Algorithm (ASA) for WSN with power hungry sensors and harvesting capabilities. An existing ASA developed for wireless sensor networks with power hungry sensors is optimized and enhanced to adapt the sampling frequency according to the available energy of the node. The proposed algorithm is evaluated using an in-field testbed with a sensor node which incorporates a wind harvester and a power hungry wind speed/direction sensor. Simulation and comparison between an existing ASA and the …
Cited by:60
Resources:[PDF] from academia.edu
:view less
An Autonomous Multi-Sensor Wearable Device with Human Body Harvesting
2015
Michele Magno
Embedded Software and Micro-Electronics Conference (eSAME 2015)
:read more
Authors:Michele Magno
Publication date:01/01/2015
Journal:Embedded Software and Micro-Electronics Conference (eSAME 2015)
Publisher:Embedded Software and Micro-Electronics Conference (eSAME 2015)
Description:An Autonomous Multi-Sensor Wearable Device with Human Body Harvesting - Research Collection Header Upper Right Menu Log in de jump to https://www.ethz.ch Research Collection Toggle navigation Upper Right Menu Login Help Help Language Deutsch Toggle navigation Search View Item Home Conference Contributions Other Conference Item View Item Home Conference Contributions Other Conference Item View Item Research Collection Navigational link Search An Autonomous Multi-Sensor Wearable Device with Human Body Harvesting Mendeley CSV RIS BibTeX Thumbnail Metadata only Author Magno, Michele Date 2015 Type Other Conference Item ETH Bibliography yes Altmetrics Publication status published Publisher Embedded Software and Micro-Electronics Conference (eSAME 2015) Event Embedded Software and Micro-Electronics Conference (eSAME 2015) , Nice, France , November 5, …
:view less
Ultra-low power context recognition fusing sensor data achieving a self-sustainable smart watch
2015
Michele Magno, Lukas Cavigelli, Renzo Andri, Luca Benini
6th EAI International Conference on Sensor Systems and Software
:read more
Authors:Michele Magno, Lukas Cavigelli, Renzo Andri, Luca Benini
Publication date:01/01/2015
Journal:6th EAI International Conference on Sensor Systems and Software
Description:Ultra-low power context recognition fusing sensor data achieving a self-sustainable smart watch - Research Collection Header Upper Right Menu Log in de jump to https://www.ethz.ch Research Collection Toggle navigation Upper Right Menu Login Help Help Language Deutsch Toggle navigation Search View Item Home Conference Contributions Other Conference Item View Item Home Conference Contributions Other Conference Item View Item Research Collection Navigational link Search Ultra-low power context recognition fusing sensor data achieving a self-sustainable smart watch Mendeley CSV RIS BibTeX Thumbnail Metadata only Author Magno, Michele Cavigelli, Lukas Andri, Renzo Benini, Luca cc Show all Date 2015 Type Other Conference Item ETH Bibliography yes Altmetrics Publication status unpublished Event 6th EAI International Conference on Sensor Systems and Software , Rome, Italy , …
Cited by:1
:view less
A low cost, highly scalable wireless sensor network solution to achieve smart LED light control for green buildings
2014
Michele Magno, Tommaso Polonelli, Luca Benini, Emanuel Popovici
IEEE Sensors Journal 15 (5), 2963-2973
:read more
Authors:Michele Magno, Tommaso Polonelli, Luca Benini, Emanuel Popovici
Publication date:12/22/2014
Journal:IEEE Sensors Journal
Volume:15
Issue:5
Pages:2963-2973
Publisher:IEEE
Description:Reducing energy demand in the residential and industrial sectors is an important challenge worldwide. In particular, lights account for a great portion of total energy consumption, and unfortunately a huge amount of this energy is wasted. Light-emitting diode (LED) lights are being used to light offices, houses, industrial, or agricultural facilities more efficiently than traditional lights. Moreover, the light control systems are introduced to current markets, because the installed lighting systems are outdated and energy inefficient. However, due to high costs, installation issues, and difficulty of maintenance; existing light control systems are not successfully applied to home, office, and industrial buildings. This paper proposes a low cost, wireless, easy to install, adaptable, and smart LED lighting system to automatically adjust the light intensity to save energy and maintaining user satisfaction. The system combines motion …
Cited by:248
Resources:[PDF] from researchgate.net
:view less
Wake-up radio receiver based power minimization techniques for wireless sensor networks: A review
2014
Michele Magno, Stevan Marinkovic, Bruno Srbinovski, Emanuel M Popovici
Microelectronics Journal 45 (12), 1627-1633
:read more
Authors:Michele Magno, Stevan Marinkovic, Bruno Srbinovski, Emanuel M Popovici
Publication date:12/01/2014
Journal:Microelectronics Journal
Volume:45
Issue:12
Pages:1627-1633
Publisher:Elsevier
Description:In a short period of time Wireless Sensor Networks (WSN) captured the imagination of many researchers with the number of applications growing rapidly. The applications span large domains including mobile digital health, structural and environmental monitoring, smart home, energy efficient buildings, agriculture, smart cities, etc. WSN are also an important contributor to the fast emerging Internet of Things infrastructure. Some of the design specifications for WSN include reliability, accuracy, cost, deployment versatility, power consumption, etc. Power consumption is (most often) the dominant constraint in designing such systems. This constraint has multi-dimensional implications such as battery type and size, energy harvester design, lifetime of the deployment, intelligent sensing capability, etc. Power optimization techniques have to explore a large design search space. Energy neutral system implementation is the …
Cited by:61
Resources:[PDF] from researchgate.net
:view less
A low power wireless node for contact and contactless heart monitoring
2014
Michele Magno, Christian Spagnol, Luca Benini, Emanuel Popovici
Microelectronics Journal 45 (12), 1656-1664
:read more
Authors:Michele Magno, Christian Spagnol, Luca Benini, Emanuel Popovici
Publication date:12/01/2014
Journal:Microelectronics Journal
Volume:45
Issue:12
Pages:1656-1664
Publisher:Elsevier
Description:Ubiquitous vital signs sensing and processing are promising alternatives to conventional clinical and ambulatory healthcare. Novel sensors, low power solutions for processing and wireless connectivity are creating new opportunities for wearable devices which allow continuous and long term monitoring, while maintaining freedom of movement for the users. This paper presents a low-power embedded platform with novel high sensitivity electric potential dry surface sensors that can be used in either contact or non-contact mode to measure biomedical signals. The proposed low power system is optimized to compute the heart rate and respiratory rate close to the sensors. This approach reduces the amount of data that needs to be transmitted to a host device. It allows also the platform to be autonomous and wearable or even be used in cars for applications such as driver drowsiness detection. Experimental …
Cited by:53
Resources:[PDF] from academia.edu
:view less
Video Surveillance Applications based on ultra-low power sensors
2014
Valeria Loscrì, Michele Magno, Rosario Surace
International Conference on Ad Hoc Networks, 235-244
:read more
Authors:Valeria Loscrì, Michele Magno, Rosario Surace
Publication date:11/27/2014
Journal:International Conference on Ad Hoc Networks
Pages:235-244
Publisher:Springer International Publishing
Description:Power consumption is an important goal for many applications, expecially when the power can be wasted doing nothing. Video surveillance is one of this application where the camera can be on for long period without “see” nothing. For this reason several power management techniques were carried out in order to reduce the activities of the camera when it is not needed. In this work we focus on surveillance applications performed through Video Surveillance Camera (VSC) that are not permanently active, but need to be properly “woken-up”, by specific ultra Low Power wireless Sensor Nodes (LPSN) able to monitor continuously the area. named. The LPSN are equipped by Piezoelectric “Passive” Infrared (PIR) sensors to detect the movement, thus they have a specific transmission range (to wirelessly send the “wake-up” messages to the camera sensor device) and a sensing range to detect events of interest (i.e. a …
Resources:[PDF] from hal.science
:view less
Infinitime: A multi-sensor energy neutral wearable bracelet
2014
Michele Magno, Danilo Porcarelli, Davide Brunelli, Luca Benini
International Green Computing Conference, 1-8
:read more
Authors:Michele Magno, Danilo Porcarelli, Davide Brunelli, Luca Benini
Publication date:11/03/2014
Journal:International Green Computing Conference
Pages:1-8
Publisher:IEEE
Description:Wearable technology is gaining popularity, with people wearing everything "smart" from clothing to glasses and watches. Nowadays wearables are battery-powered and a critical issue is the limited lifetime. So most devices have to be recharged every few days or even hours and thus they miss the expectations for a truly unobtrusive user experience. This paper presents InfiniTIME, a novel sensor-rich smart bracelet powered by small photovoltaic cells, designed to achieve energy neutrality even with modest indoor light levels. Experimental characterization of the fully operational prototype demonstrates a wide range of energy optimization techniques used to achieve the neutrality target. Simulations using energy intake measurements from various deployment scenarios confirm that the InfiniTIME achieves energy neutrality with indoor lighting levels in an office for several realistic application scenarios featuring data …
Cited by:26
:view less
An ultra low power high sensitivity wake-up radio receiver with addressing capability
2014
Michele Magno, Luca Benini
2014 IEEE 10th International Conference on Wireless and Mobile Computing, Networking an…
:read more
Authors:Michele Magno, Luca Benini
Publication date:10/08/2014
Journal:2014 IEEE 10th International Conference on Wireless and Mobile Computing, Networking and Communications (WiMob)
Pages:92-99
Publisher:IEEE
Description:In power-limited wireless devices such as wireless sensor networks, wearable components, and Internet of Things devices energy efficiency is a critical concern. These devices are usually battery operated and have a radio transceiver that is typically their most power-hungry block. Wake-up radio schemes can be used to achieve a reasonable balance among energy consumption, range, data receiving capabilities and response time. In this paper, a high-sensitivity low power wake-up radio receiver (WUR) for wireless sensor networks is presented. The wake-up radio is comprised of a fully passive differential RF-to-DC converter that rectifies the incident RF signal, a low-power comparator and an ultra low power microcontroller to detects the envelope of the on-off keying (OOK) wake-up data used as address. We designed and implemented a novel low power tunable wake up radio with addressing capability, a …
Cited by:96
Resources:[PDF] from researchgate.net
:view less
Design and implementation of a multi sensors self sustainable wearable device
2014
Danilo Porcarelli, Irene Donati, Jetmir Nehani, Davide Brunelli, Michele Magno, Luca Be…
2014 6th European Embedded Design in Education and Research Conference (EDERC), 16-20
:read more
Authors:Danilo Porcarelli, Irene Donati, Jetmir Nehani, Davide Brunelli, Michele Magno, Luca Benini
Publication date:09/11/2014
Journal:2014 6th European Embedded Design in Education and Research Conference (EDERC)
Pages:16-20
Publisher:IEEE
Description:Wearable electronics is increasingly attracting researchers and manufacturers for the application opportunities it opens. Chip makers are responding to the hot wearable-computer trend with new components, microcontrollers and sensors. The most critical challenge is the autonomy of the systems. Even if battery management can help in extending the lifetime, the trade-off between features given by a multisensory platforms and autonomy can determine if a platform will win or not in the marketplace. In this paper we present a bracelet device, which attempts to maximize the capability of sensors on board, while still keeping the energy consumption low. Aggressive power management and an accurate selection of the sensors are addressed in this paper to demonstrate the effectiveness of our design.
Cited by:7
:view less
An embedded smart agile pixel imager for lasers
2014
J Pablo La Torre, M Junaid Amin, Michele Magno, Nabeel A Riza
2014 6th European Embedded Design in Education and Research Conference (EDERC), 230-234
:read more
Authors:J Pablo La Torre, M Junaid Amin, Michele Magno, Nabeel A Riza
Publication date:09/11/2014
Journal:2014 6th European Embedded Design in Education and Research Conference (EDERC)
Pages:230-234
Publisher:IEEE
Description:The growing number of laser beam applications in the last few years has created a compelling case for efforts towards track and measure of the profile of laser beams. Laser beam imaging techniques can be embedded through the hardware and software co-design for developing embedded systems at a fraction of the cost, weight and volume and in less time than it would take to develop computer-based alternatives keeping the same accuracy. A smart agile pixel laser beam imager based on an embedded platform is presented in this paper. The design uses a Digital Micromirror Device along with a microcontroller and point photo-detectors to make a compact system having small sized components. This embedded imager is experimentally demonstrated for Gaussian laser beam profiling. The proposed design is suitable for industrial laser based applications requiring accurate two dimensional beam irradiance …
Cited by:5
:view less
A Multi Harvester with Hydrogen Fuel Cell for Outdoor Applications
2014
Davide Brunelli, Michele Magno, Danilo Porcarelli, Luca Benini
Applications in Electronics Pervading Industry, Environment and Society, 103-112
:read more
Authors:Davide Brunelli, Michele Magno, Danilo Porcarelli, Luca Benini
Publication date:06/22/2014
Journal:Applications in Electronics Pervading Industry, Environment and Society
Pages:103-112
Publisher:Springer International Publishing
Description:Energy availability and long term operation are key challenges for wireless sensor networks and for all the applications where the devices are battery operated. For this reason energy harvesting is becoming very important for powering ubiquitously deployed sensor networks and mobile electronics. One of most important goal for the next generation of power supply units for standalone embedded systems is to power nearly perpetually the devices when the scavenger is exposed to reasonable environmental energy conditions. However, due to the unpredictable nature of the environmental sources, prolonged lacks of energy intake usually happen. The last frontiers of perpetual operating systems is combining different energy harvesters in a single unit and using green energy supply with high energy density as micro hydrogen fuel cells. In this paper we introduce a Smart Power Unit (SPU) for embedded system …
:view less
A portable hybrid hydrogen fuel cell-battery power unit for wireless sensor network
2014
Michele Magno, Luca Benini, Roberta Giuffrida, Salvatore Leonardi, Davide Brunelli
2014 International Symposium on Power Electronics, Electrical Drives, Automation and Mo…
:read more
Authors:Michele Magno, Luca Benini, Roberta Giuffrida, Salvatore Leonardi, Davide Brunelli
Publication date:06/18/2014
Journal:2014 International Symposium on Power Electronics, Electrical Drives, Automation and Motion
Pages:173-178
Publisher:IEEE
Description:Hydrogen fuel cells are considered one of the most promising alternatives to batteries, because of their higher energy density and they are not affected by issues related to self-discharge. Fuel cells are very attractive for devices with long lifetime requirements. Unfortunately, fuel cells suffer from slow dynamic response to load changes and require active gas flow control. These issues have not been previously addressed for portable systems and small scale fuel-cells. This work presents a hybrid hydrogen micro fuel cell/ Li-Ion battery power unit for embedded systems and wireless sensor networks which tackles these issues. The power system is microcontroller-based and it provides a driver circuits to control the hydrogen flow closing and opening an electro-valve certified for hydrogen gas. We first describe the fuel cell implementation we characterize its power delivery capability. Next, we present the architecture of …
Cited by:10
:view less
Benefits of wake-up radio in energy-efficient multimodal surveillance wireless sensor network
2014
Vana Jelicic, Michele Magno, Davide Brunelli, Vedran Bilas, Luca Benini
IEEE Sensors Journal 14 (9), 3210-3220
:read more
Authors:Vana Jelicic, Michele Magno, Davide Brunelli, Vedran Bilas, Luca Benini
Publication date:05/26/2014
Journal:IEEE Sensors Journal
Volume:14
Issue:9
Pages:3210-3220
Publisher:IEEE
Description:Scarce energy budget of battery-powered wireless sensor nodes calls for cautious power management not to compromise performance of the system. To reduce both energy consumption and delay in energy-hungry wireless sensor networks for latency-restricted surveillance scenarios, this paper proposes a multimodal two-tier architecture with wake-up radio receivers. In video surveillance applications, using information from distributed low-power pyroelectric infrared (PIR) sensors, which detect human presence limits the activity of cameras and reduces their energy consumption. PIR sensors transmit the information about the event to camera nodes using wake-up radio receivers. We show the benefits of wake-up receivers over duty cycling in terms of overcoming energy consumption versus latency tradeoff (proved with two orders of magnitude lower latency—only 9 ms). At the same time, the power consumption …
Cited by:103
Resources:[PDF] from academia.edu
:view less
A high-sensitivity fully passive wake-up radio front-end for wireless sensor nodes
2014
Pouya Kamalinejad, Kamyar Keikhosravy, Michele Magno, Shahriar Mirabbasi, Victor CM Leu…
2014 IEEE International Conference on Consumer Electronics (ICCE), 209-210
:read more
Authors:Pouya Kamalinejad, Kamyar Keikhosravy, Michele Magno, Shahriar Mirabbasi, Victor CM Leung, Luca Benini
Publication date:01/10/2014
Journal:2014 IEEE International Conference on Consumer Electronics (ICCE)
Pages:209-210
Publisher:IEEE
Description:A high-sensitivity fully passive 868-MHz wake-up radio (WUR) front-end for wireless sensor network nodes is presented. The front-end does not have an external power source and extracts the entire energy from the radio-frequency (RF) signal received at the antenna. A high-efficiency differential RF-to-DC converter rectifies the incident RF signal and drives the circuit blocks including a low-power comparator and reference generators; and at the same time detects the envelope of the on-off keying (OOK) wake-up signal. The front-end is designed and simulated 0.13μm CMOS and achieves a sensitivity of -33 dBm for a 100 kbps wake-up signal.
Cited by:31
:view less
Applications in Electronics Pervading Industry, Environment and Society
2014
Davide Brunelli, Michele Magno, Danilo Porcarelli, Luca Benini
LECTURE NOTES IN ELECTRICAL ENGINEERING 289, 103-112
:read more
Authors:Davide Brunelli, Michele Magno, Danilo Porcarelli, Luca Benini
Publication date:01/01/2014
Journal:LECTURE NOTES IN ELECTRICAL ENGINEERING
Volume:289
Pages:103-112
Publisher:Springer Verlag
Description:Energy availability and long term operation are key challenges for wireless sensor networks and for all the applications where the devices are battery operated. For this reason energy harvesting is becoming very important for powering ubiquitously deployed sensor networks and mobile electronics. One of most important goal for the next generation of power supply units for standalone embedded systems is to power nearly perpetually the devices when the scavenger is exposed to reasonable environmental energy conditions. However, due to the unpredictable nature of the environmental sources, prolonged lacks of energy intake usually happen. The last frontiers of perpetual operating systems is combining different energy harvesters in a single unit and using green energy supply with high energy density as micro hydrogen fuel cells. In this paper we introduce a Smart Power Unit (SPU) for embedded system which incorporates energy harvesters from sun and wind and uses hydrogen fuel cell as alternative energy storage. The power unit can work as a long-term battery or providing serial communication to exchange power information and to perform power management. In fact the core of the SPU is an ultra low power micro controller which is in charge to do the power activities such as Maximum Power Point Tracking for the harvesters, fuel cell activation, energy prediction, adaptive power management on board, battery monitoring and communications with powered systems. Experimental results and simulations shows the high efficiency (up to 90%) of the power conversion subsystem. Finally a real deployment in a structural health monitoring …
Cited by:2
:view less
Nano power wake up radio receivers to eliminate idle-listening consumption in wireless sensor network
2014
Michele Magno
ACROSS Workshop on Cooperative Systems (WoCS 2014)
:read more
Authors:Michele Magno
Publication date:01/01/2014
Journal:ACROSS Workshop on Cooperative Systems (WoCS 2014)
Description:Nano power wake up radio receivers to eliminate idle-listening consumption in wireless sensor network - Research Collection Header Upper Right Menu Log in de jump to https://www.ethz.ch Research Collection Toggle navigation Upper Right Menu Login Help Help Language Deutsch Toggle navigation Search View Item Home Conference Contributions Other Conference Item View Item Home Conference Contributions Other Conference Item View Item Research Collection Navigational link Search Nano power wake up radio receivers to eliminate idle-listening consumption in wireless sensor network Mendeley CSV RIS BibTeX Thumbnail Metadata only Author Magno, Michele Date 2014 Type Other Conference Item ETH Bibliography yes Altmetrics Publication status published Event ACROSS Workshop on Cooperative Systems (WoCS 2014) , Dubrovnik, Croatia , September 10-12, 2014 Organisational unit …
:view less
WSN Power management: nano power wake up radios
2014
Michele Magno
2014 Conference on Sensors, Energy harvesting, wireless Network and Smart Objects (SENSO)
:read more
Authors:Michele Magno
Publication date:01/01/2014
Journal:2014 Conference on Sensors, Energy harvesting, wireless Network and Smart Objects (SENSO)
Publisher:2014 Conference on Sensors, Energy harvesting, wireless Network and Smart Objects (SENSO)
Description:WSN Power management: nano power wake up radios - Research Collection Header Upper Right Menu Log in de jump to https://www.ethz.ch Research Collection Toggle navigation Upper Right Menu Login Help Help Language Deutsch Toggle navigation Search View Item Home Conference Contributions Other Conference Item View Item Home Conference Contributions Other Conference Item View Item Research Collection Navigational link Search WSN Power management: nano power wake up radios Mendeley CSV RIS BibTeX Thumbnail Metadata only Author Magno, Michele Date 2014 Type Other Conference Item ETH Bibliography yes Altmetrics Publication status unpublished Publisher 2014 Conference on Sensors, Energy harvesting, wireless Network and Smart Objects (SENSO) Event 2014 Conference on Sensors, Energy harvesting, wireless Network and Smart Objects (SENSO) , Aix en Provence, …
:view less
Design and implementation of a heterogeneous, power efficient wireless sensor network for smart toys
2014
F Edwards Murphy, Michele Magno, Emanuel Popovici
International Workshop on Robotic Sensor Networks, Cyber-Physical Systems Week
:read more
Authors:F Edwards Murphy, Michele Magno, Emanuel Popovici
Publication date:01/01/2014
Journal:International Workshop on Robotic Sensor Networks, Cyber-Physical Systems Week
Description:Toys play a vitally important role in the lives of children, with critical roles relating to social development, education and entertainment. In this paper, a platform for interactive toys using ultra low power Wireless Sensor Network (WSN) technologies is proposed and developed. These are implemented through the integration of WSN technology into a number of off the shelf micro-robotic toys. The heterogeneous network devices react together, controlled by an external environmental interface realized through the addition of a wireless microphone node acting as a network coordinator. This creates an engaging, interactive concert scenario which responds to music with synchronized dancing and light displays. The proposed WSN interface improves the versatility and application range of intelligent toys at a very low cost and low power overhead. This work represents a first step in the development of intelligent interfaces for enhanced interaction with toys for children. Experimental results show the low power features of the solution and the possibility of providing long lasting real world application scenarios, including potential application of an ultra-low power wake up radio.
Cited by:2
Resources:[PDF] from buffalo.edu
:view less
Demo abstract: smartSync; when toys meet wireless sensor networks
2013
Fiona Edwards-Murphy, Michele Magno, Aidan Frost, Amy Long, Naomi Corbett, Emanuel Popo…
Real-World Wireless Sensor Networks: Proceedings of the 5th International Workshop, REA…
:read more
Authors:Fiona Edwards-Murphy, Michele Magno, Aidan Frost, Amy Long, Naomi Corbett, Emanuel Popovici
Publication date:12/20/2013
Journal:Real-World Wireless Sensor Networks: Proceedings of the 5th International Workshop, REALWSN 2013, Como (Italy), September 19-20, 2013
Pages:91-96
Publisher:Springer International Publishing
Description:Since ancient times, toys have captured the imagination of children the world over with major roles in learning and entertainment. This chapter presents SmartSync, a platform for interactive toys using ultra low power Wireless Sensor/Actuation Network (WSN) technologies. These technologies are integrated into a number of off-the shelf micro-robots and colour LED arrays, making them fully autonomous. A demo system has been developed in which wireless micro-robots and the colour LED arrays interact with a wireless microphone to create an interactive concert scenario. The LED lights and dancing robots are synchronised with music through the WSN. In the final demonstration, the effectiveness of the dancing robots and lights are shown when they respond to traditional Irish music. The WSN interface added improves versatility and accessibility to such toys at a very low cost and low power overhead. This work …
Cited by:3
Resources:[PDF] from academia.edu
:view less
Ensuring survivability of resource-intensive sensor networks through ultra-low power overlays
2013
Michele Magno, David Boyle, Davide Brunelli, Emanuel Popovici, Luca Benini
IEEE Transactions on Industrial Informatics 10 (2), 946-956
:read more
Authors:Michele Magno, David Boyle, Davide Brunelli, Emanuel Popovici, Luca Benini
Publication date:12/18/2013
Journal:IEEE Transactions on Industrial Informatics
Volume:10
Issue:2
Pages:946-956
Publisher:IEEE
Description:Nodes in wireless sensor networks (WSNs) typically have limited power supply and networks are often expected to be functional for extended periods. Therefore, the minimization of energy consumption and the maximization of network lifetime are key objectives in WSN. This paper proposes an overlay, energy optimized, sensor network to extend the functional lifetime of an energy-intensive sensor network application. The overlay network consists of additional nodes that exploit recent advances in energy harvesting and wake-up radio technologies, coupled with an application specific, complementary, ultra-low power sensor. The experimental results and simulations demonstrate that this approach can ensure survivability of energy-inefficient sensor networks. Simulating applications using energy-intensive video cameras and air quality sensors, combined with the proposed overlayed ultra-low power sensor …
Cited by:98
:view less
Ultra low power asynchronous MAC protocol using wake-up radio for energy neutral WSN
2013
Trong Nhan Le, Michele Magno, Alain Pegatoquet, Olivier Berder, Olivier Sentieys, Emanu…
Proceedings of the 1st International Workshop on Energy Neutral Sensing Systems, 1-6
:read more
Authors:Trong Nhan Le, Michele Magno, Alain Pegatoquet, Olivier Berder, Olivier Sentieys, Emanuel Popovici
Publication date:11/13/2013
Journal:Proceedings of the 1st International Workshop on Energy Neutral Sensing Systems
Pages:1-6
Description:To extend the system lifetime of WSN, energy harvesting techniques have been considered as potential solutions for long-term operations. Instead of minimizing the consumed energy as for the case of battery-powered systems, the harvesting node is adapted to Energy Neutral Operation (ENO) to achieve a theoretically infinite lifetime. Therefore, consumed energy due to communications is the critical issue to increase the system performance. In this paper, a nano-watt wake-up radio receiver (WUR) is used cooperatively with the main transceiver in order to reduce the wasted energy of idle listening in asynchronous MAC protocols where the node is waiting for potential messages, while still maintaining the same reactivity. Simulation results show that the throughput can be improve up to 82% with 53% energy saving compared to non-WUR approach of the TICER protocol. Our simulations are performed on …
Cited by:56
Resources:[PDF] from inria.fr
:view less
Heterogeneous multi-harvester for wireless sensor networks
2013
Danilo Porcarelli, Michele Magno, Davide Brunelli, Luca Benini
Proceedings of the 1st International Workshop on Energy Neutral Sensing Systems, 1-2
:read more
Authors:Danilo Porcarelli, Michele Magno, Davide Brunelli, Luca Benini
Publication date:11/13/2013
Journal:Proceedings of the 1st International Workshop on Energy Neutral Sensing Systems
Pages:1-2
Description:The majority of Wireless Sensor Networks (WSNs) applications requires long-term and unattended operation for each wireless sensor node. Scavenging energy from the surrounding environment has become an established technique to match the power demand of the nodes and to overcome the bottlenecks due to the battery-powered devices. In this demonstration we will show a microcontroller-based architecture which can collect energy from light and air-flow by performing high-efficiency conversion (higher than 80%)and maximum power point tracking algorithms. Experimental results obtained from the deployment in a structural health monitoring system in Switzerland have shown that energy neutrality is achievable in real-life scenarios.
:view less
Powering wireless sensor nodes with micro fuel cells
2013
Michele Magno, Davide Brunelli, Luca Benini, Roberta Giuffrida, Salvatore Leonardi, And…
Proceedings of the 1st International Workshop on Energy Neutral Sensing Systems, 1-2
:read more
Authors:Michele Magno, Davide Brunelli, Luca Benini, Roberta Giuffrida, Salvatore Leonardi, Andrea Lazzara
Publication date:11/13/2013
Journal:Proceedings of the 1st International Workshop on Energy Neutral Sensing Systems
Pages:1-2
Description:A novel approach to achieve long term system operation is using hydrogen fuel cells, which feature much higher energy density if compared with standard batteries. In this demonstrator we show a power unit which activates the hydrogen flow through an electrovalve to recharge the batteries, minimizing hydrogen waste and significantly boosting lifetime. Experimental results demonstrate 85% of efficiency.
:view less
Wearable low power dry surface wireless sensor node for healthcare monitoring application
2013
Michele Magno, Luca Benini, Christian Spagnol, E Popovici
2013 IEEE 9th international conference on wireless and mobile computing, networking and…
:read more
Authors:Michele Magno, Luca Benini, Christian Spagnol, E Popovici
Publication date:10/07/2013
Journal:2013 IEEE 9th international conference on wireless and mobile computing, networking and communications (WiMob)
Pages:189-195
Publisher:IEEE
Description:Nowadays, the technology advancements of sensors, low power mixed-signal/RF circuits, wireless communication and Wireless Sensor Networks (WSNs) have enabled the design of compact, low power, high performance and low cost solutions for a wide range of applications, surveillance, building monitoring, sports/fitness, and of particular interesting are applications for health care. Novel sensors for human biomedical signal together with wireless connectivity and low power solutions are creating new opportunities for wearable devices which allow continuous monitoring together with freedom of movement of the users. This paper presents a low-power wearable sensor networks platform for on-body physiological measurements and wireless data communications. The platform hosts novel high sensitivity electric potential dry surface sensors that can be used in either contact or non-contact mode to measure ECG …
Cited by:71
Resources:[PDF] from researchgate.net
:view less
Low-power wireless accelerometer-based system for wear detection of bandsaw blades
2013
Michele Magno, E Popovici, Alessandro Bravin, Antonio Libri, Marco Storace, Luca Benini
2013 11th IEEE International Conference on Industrial Informatics (INDIN), 630-635
:read more
Authors:Michele Magno, E Popovici, Alessandro Bravin, Antonio Libri, Marco Storace, Luca Benini
Publication date:07/29/2013
Journal:2013 11th IEEE International Conference on Industrial Informatics (INDIN)
Pages:630-635
Publisher:IEEE
Description:The paper provides a framework to save energy and reduce the operative cost of some of today's industrial machinery. Low cost and low power wireless sensor networks is a novel approach to monitoring the tools in order to save energy and keep the tools monitored. Cutting tool wear degrades the product quality in manufacturing processes and also could have implications in health and safety of use. Monitoring tool wear value online is therefore needed to prevent degradation in machine quality. Unfortunately there is no direct way of measuring the tool wear online which is also very low cost. In this work is presented a low power and low cost accelerometer-based system for wear detection of bandsaw blade. The algorithm uses a simple data processing directly on board that can extract features and perform a classification on the state of the blade. Low power design of the node, on board processing and wake up …
Cited by:7
Resources:[PDF] from researchgate.net
:view less
A power-aware multi harvester power unit with hydrogen fuel cell for embedded systems in outdoor applications
2013
Michele Magno, Danilo Porcarelli, Luca Benini, Davide Brunelli
2013 International Green Computing Conference Proceedings, 1-6
:read more
Authors:Michele Magno, Danilo Porcarelli, Luca Benini, Davide Brunelli
Publication date:06/27/2013
Journal:2013 International Green Computing Conference Proceedings
Pages:1-6
Publisher:IEEE
Description:Energy availability and long term operation are key challenges for wireless sensor networks and the applications where embedded devices are battery-operated and they should operate unattended for tens of years. For this reason energy harvesting (EH) is becoming very important for powering ubiquitously deployed sensor networks and mobile electronics. In this paper we introduce a Smart Power Unit (SPU) for embedded systems which integrates energy harvesters from the sun and wind with hydrogen fuel cells especially designed for outdoor applications. The power unit can work as a standard battery or providing serial communication to exchange power information to achieve power management.Experimental results show the high efficiency (up to 90%) of the power conversion subsystem and the perpetual work. Deployment in a structural health monitoring in Switzerland demonstrates that perpetual energy …
Cited by:6
Resources:[PDF] from researchgate.net
:view less
Extended wireless monitoring through intelligent hybrid energy supply
2013
Michele Magno, David Boyle, Davide Brunelli, Brendan O'Flynn, Emanuel Popovici, Luca Be…
IEEE Transactions on Industrial Electronics 61 (4), 1871-1881
:read more
Authors:Michele Magno, David Boyle, Davide Brunelli, Brendan O'Flynn, Emanuel Popovici, Luca Benini
Publication date:06/18/2013
Journal:IEEE Transactions on Industrial Electronics
Volume:61
Issue:4
Pages:1871-1881
Publisher:IEEE
Description:This paper presents the design, implementation, and characterization of a hardware platform applicable to wireless structural health monitoring (WSHM). The primary design goal is to devise a system capable of persistent operation for the duration of the life cycle of a target structure. It should be deployable during the construction phase and reconfigurable thereafter, suitable for continuous long-term monitoring. In addition to selecting the most energy efficient useful components to ensure the lowest possible power consumption, it is necessary to consider sources of energy other than, or complementary to, batteries. Thus, the platform incorporates multisource energy harvesting, electrochemical fuel cell (FC), energy storage, recharging capability, and intelligent operation through real-time energy information exchange with the primary controller. It is shown that, with appropriate integration, the device will have …
Cited by:123
:view less
Power management techniques for wireless sensor networks: a review
2013
Emanuel Popovici, Michele Magno, Stevan Marinkovic
5th IEEE International Workshop on Advances in Sensors and Interfaces IWASI, 194-198
:read more
Authors:Emanuel Popovici, Michele Magno, Stevan Marinkovic
Publication date:06/13/2013
Journal:5th IEEE International Workshop on Advances in Sensors and Interfaces IWASI
Pages:194-198
Publisher:IEEE
Description:During recent years, Wireless Sensor Networks captured the imagination of many researchers with number of applications growing rapidly. Power consumption is (most often) the dominant constraint in designing such systems. This constraint has multi-dimensional implications such as battery type and size, energy harvester design, lifetime of the deployment, etc. Energy neutral system implementation is the ultimate goal in wireless sensor networks and represents a hot topic of research. Several recent advances promise significant reduction of the overall sensor network power consumption. These advances include novel sensors and sensor interfaces, low power wireless transceivers, low power processing, etc. Power optimization techniques have to explore a large design search space. This paper reviews a number of system level power management methodologies for Wireless Sensor Networks which use ultra …
Cited by:71
Resources:[PDF] from researchgate.net
:view less
A versatile biomedical wireless sensor node with novel drysurface sensors and energy efficient power management
2013
Michele Magno, Luca Benini, L Gaggero, JP La Torre Aro, E Popovici
5th IEEE International Workshop on Advances in Sensors and Interfaces IWASI, 217-222
:read more
Authors:Michele Magno, Luca Benini, L Gaggero, JP La Torre Aro, E Popovici
Publication date:06/13/2013
Journal:5th IEEE International Workshop on Advances in Sensors and Interfaces IWASI
Pages:217-222
Publisher:IEEE
Description:Technology advancements of sensors, low power mixed-signal/RF circuits, and Wireless Sensor Networks (WSNs) made it possible to construct compact and low cost solutions for a wide range of applications such as healthcare, surveillance, building monitoring, sports and fitness, etc. A new emerging generation of WSN is the Body Sensor Network which is suitable to monitor of the human body, mainly for health care applications but also for sports and fitness. Due to the growing interest in this area, novel sensors for monitoring bio-electric signals like ECG, EMG, EOG and EEG are being developed. In this paper we present a low-power designed body sensor networks (BSN) platform for on-body physiological measurements and wireless data communications. The BSN node is capable of hosting high sensitivity electric potential dry surface sensors that can be used in either contact or non-contact mode to measure …
Cited by:29
Resources:[PDF] from researchgate.net
:view less
Multimodal video analysis on self-powered resource-limited wireless smart camera
2013
Michele Magno, Federico Tombari, Davide Brunelli, Luigi Di Stefano, Luca Benini
IEEE Journal on Emerging and Selected Topics in Circuits and Systems 3 (2), 223-235
:read more
Authors:Michele Magno, Federico Tombari, Davide Brunelli, Luigi Di Stefano, Luca Benini
Publication date:04/23/2013
Journal:IEEE Journal on Emerging and Selected Topics in Circuits and Systems
Volume:3
Issue:2
Pages:223-235
Publisher:IEEE
Description:Surveillance is one of the most promising applications for wireless sensor networks, stimulated by a confluence of simultaneous advances in key disciplines: computer vision, image sensors, embedded computing, energy harvesting, and sensor networks. However, computer vision typically requires notable amounts of computing performance, a considerable memory footprint and high power consumption. Thus, wireless smart cameras pose a challenge to current hardware capabilities in terms of low-power consumption and high imaging performance. For this reason, wireless surveillance systems still require considerable amount of research in different areas such as mote architectures, video processing algorithms, power management, energy harvesting and distributed engine. In this paper, we introduce a multimodal wireless smart camera equipped with a pyroelectric infrared sensor and solar energy harvester …
Cited by:66
Resources:[PDF] from archive.org
:view less
A survey of multi-source energy harvesting systems
2013
Alex S Weddell, Michele Magno, Geoff V Merrett, Davide Brunelli, Bashir M Al-Hashimi, L…
2013 Design, Automation & Test in Europe Conference & Exhibition (DATE), 905-908
:read more
Authors:Alex S Weddell, Michele Magno, Geoff V Merrett, Davide Brunelli, Bashir M Al-Hashimi, Luca Benini
Publication date:03/18/2013
Journal:2013 Design, Automation & Test in Europe Conference & Exhibition (DATE)
Pages:905-908
Publisher:IEEE
Description:Energy harvesting allows low-power embedded devices to be powered from naturally-ocurring or unwanted environmental energy (e.g. light, vibration, or temperature difference). While a number of systems incorporating energy harvesters are now available commercially, they are specific to certain types of energy source. Energy availability can be a temporal as well as spatial effect. To address this issue, ‘hybrid’ energy harvesting systems combine multiple harvesters on the same platform, but the design of these systems is not straight-forward. This paper surveys their design, including trade-offs affecting their efficiency, applicability, and ease of deployment. This survey, and the taxonomy of multi-source energy harvesting systems that it presents, will be of benefit to designers of future systems. Furthermore, we identify and comment upon the current and future research directions in this field.
Cited by:172
Resources:[PDF] from soton.ac.uk
:view less
Combination of hybrid energy harvesters with MEMS piezoelectric and nano-Watt radio wake up to extend lifetime of system for wireless sensor nodes
2013
Michele Magno, Nathan Jackson, Alan Mathewson, Luca Benini, E Popovici
26th International Conference on Architecture of Computing Systems 2013, 1-6
:read more
Authors:Michele Magno, Nathan Jackson, Alan Mathewson, Luca Benini, E Popovici
Publication date:02/19/2013
Journal:26th International Conference on Architecture of Computing Systems 2013
Pages:1-6
Publisher:VDE
Description:Power consumption is a critical issue in Wireless Sensor Networks(WSN) applications and typically the energy consumed by the wireless communication dominates. Reducing the WSN node activity and the communication energy can extend the lifetime of the node considerably. This work presents a direct application approach to extend the lifetime of a wireless senor node using a MEMS piezoelectric energy harvesting device in combination with a nano-Watt wake-up radio receiver, in order to build an efficient power device. The design of the power device will be connected to each node as a normal battery bringing the wake-up radio capabilities. Two scenarios were implemented to use the power unit as a wireless switch with harvesters, or to use the power management wake up polices while the MEMS piezoelectric harvester was designed as a power supply directly to the wake up radio receiver. The …
Cited by:60
Resources:[HTML] from academia.edu
:view less
Évaluation de la précision en virgule fixe dans le cas des structures conditionnelles
2013
Jean Charles Naud, Daniel Menard, Olivier Sentieys
Revue des Sciences et Technologies de l'Information-Série TSI: Technique et Science Inf…
:read more
Authors:Jean Charles Naud, Daniel Menard, Olivier Sentieys
Publication date:01/01/2013
Journal:Revue des Sciences et Technologies de l'Information-Série TSI: Technique et Science Informatiques
Volume:32
Issue:2
Pages:179-201
Description:UNIV-NANTES EC-PARIS UNIV-RENNES1 CNRS INRIA INSA-RENNES IRISA IETR IETR-INSA IRISA-D3 INRIA2 UR1-MATH-STIC UR1-UFR-ISTIC IETR-VAADER UNIV-RENNES INSA-GROUPE UR1-MATH-NUM NANTES-UNIVERSITE
:view less
Analytic comparison of wake-up receivers for WSNs and benefits over the wake-on radio scheme
2012
Vana Jelicic, Michele Magno, Davide Brunelli, Vedran Bilas, Luca Benini
Proceedings of the 7th ACM workshop on Performance monitoring and measurement of hetero…
:read more
Authors:Vana Jelicic, Michele Magno, Davide Brunelli, Vedran Bilas, Luca Benini
Publication date:10/21/2012
Journal:Proceedings of the 7th ACM workshop on Performance monitoring and measurement of heterogeneous wireless and wired networks
Pages:99-106
Description:Since in most wireless sensor network (WSN) scenarios nodes must operate autonomously for months or years, power management of the radio (usually consuming the largest amount of node's energy) is crucial. In particular, reducing the power consumption during listening plays a fundamental role in the whole energy balance of a sensor node, since shutting down the receiver when no messages are expected can remarkably increase the autonomy. Idle listening is a hard challenge because incoming messages are often unpredictable and developers have to trade off low power consumption and high quality of service. This paper is focusing on benefits of introducing a wake-up receiver over simple duty-cycling (wake-on radio). We analyze and compare the existing wake-up receiver prototypes and explore their benefits using simulations of two typical scenarios: with and without addressing requirements. A …
Cited by:119
:view less
Combined methods to extend the lifetime of power hungry WSN with multimodal sensors and nanopower wakeups
2012
Michele Magno, Stevan Marinkovic, Davide Brunelli, Luca Benini, Emanuel Popovici
2012 8th International Wireless Communications and Mobile Computing Conference (IWCMC),…
:read more
Authors:Michele Magno, Stevan Marinkovic, Davide Brunelli, Luca Benini, Emanuel Popovici
Publication date:08/27/2012
Journal:2012 8th International Wireless Communications and Mobile Computing Conference (IWCMC)
Pages:112-117
Publisher:IEEE
Description:During recent years, there has been a growing interest on wireless sensor networks (WSNs) and on the opportunities opened by this technology. Since the energy consumption is a bottleneck in WSNs, reducing it has a significant impact on the applicability of this technology. Typically, the energy consumed by wireless communication and by power-hungry sensors as CMOS imagers or Gas sensors, is dominant over the power required for computation or other activities of the node. Hence, an efficient management of the resources leading to a reduction of unnecessary communication and minimizing the use of power-hungry sensor while keeping the same performance is desirable to extend the life-time of the network. In this paper we address the challenges of exploiting wake-up receivers and heterogeneous sensors in WSN applications to reduce the average power consumption of individual nodes. In particular …
Cited by:15
:view less
Context-adaptive multimodal wireless sensor network for energy-efficient gas monitoring
2012
Vana Jelicic, Michele Magno, Davide Brunelli, Giacomo Paci, Luca Benini
IEEE Sensors journal 13 (1), 328-338
:read more
Authors:Vana Jelicic, Michele Magno, Davide Brunelli, Giacomo Paci, Luca Benini
Publication date:08/27/2012
Journal:IEEE Sensors journal
Volume:13
Issue:1
Pages:328-338
Publisher:IEEE
Description:We present a wireless sensor network (WSN) for monitoring indoor air quality, which is crucial for people's comfort, health, and safety because they spend a large percentage of time in indoor environments. A major concern in such networks is energy efficiency because gas sensors are power-hungry, and the sensor node must operate unattended for several years on a battery power supply. A system with aggressive energy management at the sensor level, node level, and network level is presented. The node is designed with very low sleep current consumption (only 8 μA), and it contains a metal oxide semiconductor gas sensor and a pyroelectric infrared (PIR) sensor. Furthermore, the network is multimodal; it exploits information from auxiliary sensors, such as PIR sensors about the presence of people and from the neighbor nodes about gas concentration to modify the behavior of the node and the measuring …
Cited by:243
Resources:[PDF] from researchgate.net
:view less
A multi-harvester architecture with hybrid storage devices and smart capabilities for low power systems
2012
Danilo Porcarelli, Davide Brunelli, Michele Magno, Luca Benini
International Symposium on Power Electronics Power Electronics, Electrical Drives, Auto…
:read more
Authors:Danilo Porcarelli, Davide Brunelli, Michele Magno, Luca Benini
Publication date:06/20/2012
Journal:International Symposium on Power Electronics Power Electronics, Electrical Drives, Automation and Motion
Pages:946-951
Publisher:IEEE
Description:The increasing attention on energy autonomous sensing and computing systems which can operate unattended tens of years, have made energy harvesting and power conversion techniques key technologies for the future. The goal is to power systems nearly perpetually if the scavenger is exposed to reasonable environmental energy conditions. However, the system is still threatened to run out of energy, if a prolonged lack of energy intake happens. The last frontiers of perpetual operating systems is combining cutting edge technologies for energy generation from the environment and long-term and green energy supply using small factor fuel cells with few cm3. In this paper we introduce an hybrid power architecture which improves embedded systems power availability. We present a Smart Power Unit (SPU) that is a power supply architecture which manages both energy harvesting and novel fuel cells …
Cited by:59
Resources:[PDF] from researchgate.net
:view less
Smart power unit with ultra low power radio trigger capabilities for wireless sensor networks
2012
Michele Magno, Stevan Marinkovic, Davide Brunelli, Emanuel Popovici, Brendan O'Flynn, L…
2012 Design, Automation & Test in Europe Conference & Exhibition (DATE), 75-80
:read more
Authors:Michele Magno, Stevan Marinkovic, Davide Brunelli, Emanuel Popovici, Brendan O'Flynn, Luca Benini
Publication date:03/12/2012
Journal:2012 Design, Automation & Test in Europe Conference & Exhibition (DATE)
Pages:75-80
Publisher:IEEE
Description:This paper presents the design, implementation and characterization of an energy-efficient smart power unit for a wireless sensor network with a versatile nano-Watt wake up radio receiver. A novel Smart Power Unit has been developed featuring multi-source energy harvesting, multi-storage adaptive recharging, electrochemical fuel cell integration, radio wake-up capability and embedded intelligence. An ultra low power on board microcontroller performs maximum power point tracking (MPPT) and optimized charging of supercapacitor or Li-Ion battery at the maximum efficiency. The power unit can communicate with the supplied node via serial interface (I2C or SPI) to provide status of resources or dynamically adapt its operational parameters. The architecture is very flexible: it can host different types of harvesters (solar, wind, vibration, etc.). Also, it can be configured and controlled by using the wake-up radio to …
Cited by:68
Resources:[PDF] from academia.edu
:view less
Endless Smart Power for WSNs: Combining Multiple Harvesting and Fuel Cells
2012
Michele Magno, Danilo Porcarelli, Davide Brunelli, Luca Benini
EWSN 2012, 86
:read more
Authors:Michele Magno, Danilo Porcarelli, Davide Brunelli, Luca Benini
Publication date:02/15/2012
Journal:EWSN 2012
Pages:86
Description:During recent years, there has been a growing interest on wireless sensor networks (WSNs) and on the opportunities opened by this technology. Since the energy consumption is a bottleneck in WSNs, extending the lifetime has a significant impact on the applicability of this technology. We present in this work the design, implementation and characterisation of a novel power unit including intelligence, ambient available energy harvesting (EH) from multiple sources, storage, electrochemical fuel cell integration, and recharging capability, which acts as the power layer for the node the node The power unit is focused to allow the node to operate perpetually in outdoor scenario. We prototyped and tested the nodes, and used their characterization to demonstrate through measures the high efficiency.
Resources:[PDF] from elsevierpure.com
:view less
Towards persistent structural health monitoring through sustainable wireless sensor networks
2011
David Boyle, Michele Magno, Brendan O'Flynn, Davide Brunelli, Emanuel Popovici, Luca Be…
2011 Seventh International Conference on Intelligent Sensors, Sensor Networks and Infor…
:read more
Authors:David Boyle, Michele Magno, Brendan O'Flynn, Davide Brunelli, Emanuel Popovici, Luca Benini
Publication date:12/06/2011
Journal:2011 Seventh International Conference on Intelligent Sensors, Sensor Networks and Information Processing
Pages:323-328
Publisher:IEEE
Description:This paper documents the design, implementation and characterisation of a wireless sensor node (GENESI Node v1.0), applicable to long-term structural health monitoring. Presented is a three layer abstraction of the hardware platform; consisting of a Sensor Layer, a Main Layer and a Power Layer. Extended operational lifetime is one of the primary design goals, necessitating the inclusion of supplemental energy sources, energy awareness, and the implementation of optimal components (microcontroller(s), RF transceiver, etc.) to achieve lowest-possible power consumption, whilst ensuring that the functional requirements of the intended application area are satisfied. A novel Smart Power Unit has been developed; including intelligence, ambient available energy harvesting (EH), storage, electrochemical fuel cell integration, and recharging capability, which acts as the Power Layer for the node. The functional …
Cited by:51
Resources:[PDF] from ucc.ie
:view less
Energy-aware objects abandon/removal detection
2011
Alessandro Lanza, Michele Magno, Davide Brunelli, Luigi Di Stefano, Luca Benini
2011 8th IEEE International Conference on Advanced Video and Signal Based Surveillance …
:read more
Authors:Alessandro Lanza, Michele Magno, Davide Brunelli, Luigi Di Stefano, Luca Benini
Publication date:08/30/2011
Journal:2011 8th IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS)
Pages:443-448
Publisher:IEEE
Description:A major issue for video surveillance embedded systems is the need to continuously perform a number of highly demanding operations even when the analyzed scene does not show peculiar or interesting features, so that power consumption is a critical issue. In this paper we present a low-power multimodal embedded video surveillance system aimed at detecting objects abandoned/removed in/from a static monitored scene. Energy-awareness is achieved by means of an efficient and scalable objects abandon/removal detection algorithm, a Linux governor that controls CPU frequency and operating mode so as to establish an optimal trade-off between fulfilling the application efficiency-accuracy requirements and maximizing battery life and, finally, a pyroelectric infrared sensor that allows to wake up the CPU only when video processing is actually needed.
Cited by:4
:view less
Design, characterization and management of a wireless sensor network for smart gas monitoring
2011
Vana Jeličić, Michele Magno, Giacomo Paci, Davide Brunelli, Luca Benini
2011 4th IEEE International Workshop on Advances in Sensors and Interfaces (IWASI), 115…
:read more
Authors:Vana Jeličić, Michele Magno, Giacomo Paci, Davide Brunelli, Luca Benini
Publication date:06/28/2011
Journal:2011 4th IEEE International Workshop on Advances in Sensors and Interfaces (IWASI)
Pages:115-120
Publisher:IEEE
Description:Air quality monitoring in indoor environments is of great significance for comfort and health, especially nowadays that people spend more than 80% of the day indoor. We propose a flexible wireless system able to detect polluted air and dangerous situations in a complex and large environment. It is important for ambient intelligent systems to be unobtrusive and to optimize the power consumption of the platforms in order to be able to live on batteries for several years. We present a system with aggressive energy management that involves three levels: sensor level, node level and network level. The sensor board we designed is a wireless sensor network (WSN) node, with very low sleep current consumption (only 8 µA). It contains two modalities — a gas sensor and a Pyroelectric InfraRed (PIR) sensor. The network is multimodal: it uses information from the PIR sensor and neighbor nodes to detect the presence of …
Cited by:68
:view less
GENESI: Wireless sensor networks for structural monitoring
2011
Brendan O'Flynn, David Boyle, Emanuel M Popovici, Michele Magno, C Petrioli
35th International Conference of IMAPS-CPMT IEEE Poland, Gdansk-Sobieszewo, Poland, 21-…
:read more
Authors:Brendan O'Flynn, David Boyle, Emanuel M Popovici, Michele Magno, C Petrioli
Publication date:01/01/2011
Journal:35th International Conference of IMAPS-CPMT IEEE Poland, Gdansk-Sobieszewo, Poland, 21-24 Sep, 2011.
Description:The GENESI project has the ambitious goal of bringing WSN technology to the level where it can provide the core of the next generation of systems for structural health monitoring that are long lasting, pervasive and totally distributed and autonomous. This goal requires embracing engineering and scientific challenges never successfully tackled before. Sensor nodes will be redesigned to overcome their current limitations, especially concerning energy storage and provisioning (we need devices with virtually infinite lifetime) and resilience to faults and interferences (for reliability and robustness). New software and protocols will be defined to fully take advantage of the new hardware, providing new paradigms for cross-layer interaction at all layers of the protocol stack and satisfying the requirements of a new concept of Quality of Service (QoS) that is application-driven, truly reflecting the end user perspective and expectations. The GENESI project will develop long lasting sensor nodes by combining cutting edge technologies for energy generation from the environment (energy harvesting) and green energy supply (small form factor fuel cells); GENESI will define models for energy harvesting, energy conservation in super-capacitors and supplemental energy availability through fuel cells, in addition to the design of new algorithms and protocols for dynamic allocation of sensing and communication tasks to the sensors. The project team will design communication protocols for large scale heterogeneous wireless sensor/actuator networks with energy-harvesting capabilities and define distributed mechanisms for context assessment and situation …
Cited by:2
Resources:[PDF] from ucc.ie
:view less
An energy efficient multimodal wireless video sensor network with eZ430–RF2500 modules
2010
Vana Jeličić, Michele Magno, Davide Brunelli, Vedran Bilas, Luca Benini
5th International Conference on Pervasive Computing and Applications, 161-166
:read more
Authors:Vana Jeličić, Michele Magno, Davide Brunelli, Vedran Bilas, Luca Benini
Publication date:12/01/2010
Journal:5th International Conference on Pervasive Computing and Applications
Pages:161-166
Publisher:IEEE
Description:In video surveillance there is an ever-growing demand for heavily distributed radio cooperating objects that Wireless Sensor Networks (WSNs) can satisfy. We present a preliminary study of an energy efficient multimodal WVSN using a main node deciding which camera to trigger based on the information from a Pyroelectric InfraRed (PIR) network. The evaluation of the proposed approach against the solution with PIRs onboard shows significantly reduced cameras' ON-time, enabling network lifetime prolongation up to 75%. Furthermore, including cameras ' available energy in wake-up rules, which would be significant for the networks comprising a photovoltaic power source, augments additionally the system's lifetime. The performance of our approach is evaluated in MATLAB simulation.
Cited by:47
Resources:[PDF] from researchgate.net
:view less
Energy efficient cooperative multimodal ambient monitoring
2010
Michele Magno, Davide Brunelli, Piero Zappi, Luca Benini
European Conference on Smart Sensing and Context, 56-70
:read more
Authors:Michele Magno, Davide Brunelli, Piero Zappi, Luca Benini
Publication date:11/14/2010
Journal:European Conference on Smart Sensing and Context
Pages:56-70
Publisher:Springer Berlin Heidelberg
Description:Wireless Video Sensor Networks (WVNs) are lively interest in the research community as flexible means for monitoring isolated areas. WVN effectiveness can be augmented when coupled with a network of low-power, low-cost Pyroelectric InfraRed (PIR) detectors to form a multimodal surveillance system. Autonomy is a key issue as battery replacement is often impractical and even using energy scavenging techniques, such as solar harvester, ad-hoc power management policies are essential to extend network lifetime. In this paper we propose a cooperative policy to manage power consumption of a WVN powered by solar scavengers and supported by a network of PIR sensors that perform a coarse classification of movements. A cost function is calculated by each VSN according to its available energy and information from the PIR network. Such functions are used by a distributed energy aware policy that selects …
Cited by:9
:view less
Energy aware multimodal embedded video surveillance
2010
Michele Magno, Alessandro Lanza, Davide Brunelli, Luigi Di Stefano, Luca Benini
2010 18th IEEE/IFIP International Conference on VLSI and System-on-Chip, 264-269
:read more
Authors:Michele Magno, Alessandro Lanza, Davide Brunelli, Luigi Di Stefano, Luca Benini
Publication date:09/27/2010
Journal:2010 18th IEEE/IFIP International Conference on VLSI and System-on-Chip
Pages:264-269
Publisher:IEEE
Description:One of the major challenges in embedded system is reduction of power consumption. So far most of the microprocessors provide power saving mechanisms by changing the power operating mode as well as the frequency and core voltage at runtime. One of best methods is the management of available resources and operating systems like Linux define subsystems for power consumption management which require coordination and cooperation of hardware, kernel, and user-space applications, offering power savings options when the CPU is active as well as when it is inactive. In this paper we present a multimodal embedded visual surveillance system for the detection of abandoned/removed objects which exploits a Linux governor to control CPU frequency and operating mode to establish an optimal trade-off between fulfilling the application response time and accuracy requirements and maximizing battery life …
Cited by:3
:view less
Sistemi riconfigurabili a basso consumo per applicazioni di monitoraggio distribuito
2010
Michele Magno
:read more
Authors:Michele Magno
Publication date:05/06/2010
Publisher:alma
Description:The term Ambient Intelligence (AmI) refers to a vision on the future of the information society where smart, electronic environment are sensitive and responsive to the presence of people and their activities (Context awareness). In an ambient intelligence world, devices work in concert to support people in carrying out their everyday life activities, tasks and rituals in an easy, natural way using information and intelligence that is hidden in the network connecting these devices. This promotes the creation of pervasive environments improving the quality of life of the occupants and enhancing the human experience. AmI stems from the convergence of three key technologies: ubiquitous computing, ubiquitous communication and natural interfaces. Ambient intelligent systems are heterogeneous and require an excellent cooperation between several hardware/software technologies and disciplines, including signal processing, networking and protocols, embedded systems, information management, and distributed algorithms. Since a large amount of fixed and mobile sensors embedded is deployed into the environment, the Wireless Sensor Networks is one of the most relevant enabling technologies for AmI. WSN are complex systems made up of a number of sensor nodes which can be deployed in a target area to sense physical phenomena and communicate with other nodes and base stations. These simple devices typically embed a low power computational unit (microcontrollers, FPGAs etc.), a wireless communication unit, one or more sensors and a some form of energy supply (either batteries or energy scavenger modules). WNS promises of …
Resources:[PDF] from unibo.it
:view less
An Energy Efficient Multimodal Wireless Video Sensor Network with eZ430-RF2500 modules
2010
Vana Jeliþiü, Michele Magno, Davide Brunelli, Vedran Bilas, Luca Benini
:read more
Authors:Vana Jeliþiü, Michele Magno, Davide Brunelli, Vedran Bilas, Luca Benini
Publication date:01/01/2010
Description:In video surveillance there is an ever-growing demand for heavily distributed radio cooperating objects that Wireless Sensor Networks (WSNs) can satisfy. We present a preliminary study of an energy efficient multimodal WVSN using a main node deciding which camera to trigger based on the information from a Pyroelectric InfraRed (PIR) network. The evaluation of the proposed approach against the solution with PIRs onboard shows significantly reduced cameras’ ON-time, enabling network lifetime prolongation up to 75%. Furthermore, including cameras’ available energy in wake-up rules, which would be significant for the networks comprising a photovoltaic power source, augments additionally the system’s lifetime. The performance of our approach is evaluated in MATLAB simulation.
:view less
Multimodal abandoned/removed object detection for low power video surveillance systems
2009
Michele Magno, Federico Tombari, Davide Brunelli, Luigi Di Stefano, Luca Benini
2009 Sixth IEEE international conference on advanced video and signal based surveillanc…
:read more
Authors:Michele Magno, Federico Tombari, Davide Brunelli, Luigi Di Stefano, Luca Benini
Publication date:09/02/2009
Journal:2009 Sixth IEEE international conference on advanced video and signal based surveillance
Pages:188-193
Publisher:IEEE
Description:Low-cost and low-power video surveillance systems based on networks of wireless video sensors will enter soon the marketplace with the promise of flexibility, quick deployment and providing accurate and real-time visual data. Energy autonomy and efficiency of the implemented algorithms are undoubtedly the primary design challenges to be addressed on systems subject to low computational capabilities and memory constraints. In this paper we present a low-power video sensor node designed for low-cost video surveillance which is able to detect abandoned and removed objects. The system exploits multi-modal sensor integration which saves on-board power consumption. In particular a pyroelectric infrared (PIR) sensor is exploited to optimize the use of the camera, grabbing images only when required in order to obtain the maximum efficiency from event recognition. Our fixed-point ARM-based approach is …
Cited by:65
Resources:[PDF] from researchgate.net
:view less
Adaptive power control for solar harvesting multimodal wireless smart camera
2009
Michele Magno, Davide Brunelli, Lothar Thiele, Luca Benini
2009 Third ACM/IEEE International Conference on Distributed Smart Cameras (ICDSC), 1-7
:read more
Authors:Michele Magno, Davide Brunelli, Lothar Thiele, Luca Benini
Publication date:08/30/2009
Journal:2009 Third ACM/IEEE International Conference on Distributed Smart Cameras (ICDSC)
Pages:1-7
Publisher:IEEE
Description:Energy efficiency for wireless smart camera networks is one of the major efforts in the distributed monitoring and surveillance community. If video cameras are equipped with circuits that receive and convert energy from regenerative sources such as solar cells, an effective power management becomes essential for the design of small sized and perpetually powered devices, which can be deployed unattended for years and feature smart vision applications. In this paper we present a simple but optimal power management tailored for multi-modal video sensor nodes and based on model predictive controller (MPC) principles. The system is designed for low-power and low-cost video surveillance and exploits small solar cells for battery recharging and pyroelectric infrared (PIR) sensors to provide low-power monitoring when the camera is not needed. The aim of this work is to show how an adaptive controller helps the …
Cited by:44
:view less
A solar-powered video sensor node for energy efficient multimodal surveillance
2008
Michele Magno, Davide Brunelli, Piero Zappi, Luca Benini
2008 11th EUROMICRO Conference on Digital System Design Architectures, Methods and Tool…
:read more
Authors:Michele Magno, Davide Brunelli, Piero Zappi, Luca Benini
Publication date:09/03/2008
Journal:2008 11th EUROMICRO Conference on Digital System Design Architectures, Methods and Tools
Pages:512-519
Publisher:IEEE
Description:Building an energy efficient wireless vision network for monitoring and surveillance is one of the major efforts in the sensor network community. We present a multi-modal video sensor node designed for low-power and low-cost video surveillance, traffic control and people detection based on wireless sensor networks. It is equipped with a solar energy harvesting unit, which extends the autonomy ofthe nodes considerably using a solar cell of 70 cm2 and exploits CMOS video camera and Pyroelectric InfraRed (PIR) sensors to reduce remarkably the power consumption of the system in absence of events. The on-board microprocessor enables image classification using algorithms basedon support vector machines (SVM). We describe hardware-software architecture of the video sensor node and characterization in terms of power consumption and accuracy. Finally simulation results demonstrate the effectiveness of …
Cited by:39
:view less
A Self-powered Video Node Triggered by PIR Sensors
2008
M Magno, Davide Brunelli, P Zappi, L Benini
Fifth European conference on Wireless Sensor Networks, ---
:read more
Authors:M Magno, Davide Brunelli, P Zappi, L Benini
Publication date:01/01/2008
Journal:Fifth European conference on Wireless Sensor Networks
Pages:---
Publisher:SpringerLink
Description:A Self-powered Video Node Triggered by PIR Sensors IRIS IRIS Home Sfoglia Macrotipologie & tipologie Autore Titolo Riviste Serie IT Italiano Italiano English English LOGIN 1.IRIS 2.SIARI UNITN 3.04 Convegni (Proceedings) 4.04.3 Poster presentato a convegno (Poster presented at Conference or Workshop) A Self-powered Video Node Triggered by PIR Sensors Brunelli, Davide; 2008-01-01 Scheda breve Scheda completa Scheda completa (DC) Anno di deposito (Filing date) 2008 Titolo del volume (Proceedings title) Fifth European conference on Wireless Sensor Networks Luogo di edizione (Place of publication) -- Casa editrice (Publisher) SpringerLink Tutti gli autori M., Magno; Brunelli, Davide; P., Zappi; L., Benini Appare nelle tipologie: 04.3 Poster presentato a convegno (Poster presented at Conference or Workshop) File in questo prodotto: Non ci sono file associati a questo prodotto. …
:view less
Multi-modal video surveillance aided by pyroelectric infrared sensors
2008
Michele Magno, Federico Tombari, Davide Brunelli, Luigi Di Stefano, Luca Benini
Workshop on Multi-camera and Multi-modal Sensor Fusion Algorithms and Applications-M2SF…
:read more
Authors:Michele Magno, Federico Tombari, Davide Brunelli, Luigi Di Stefano, Luca Benini
Publication date:01/01/2008
Journal:Workshop on Multi-camera and Multi-modal Sensor Fusion Algorithms and Applications-M2SFA2 2008
Description:The interest in low-cost and small size video surveillance systems able to collaborate in a network has been increasing over the last years. Thanks to the progress in low-power design, research has greatly reduced the size and the power consumption of such distributed embedded systems providing flexibility, quick deployment and allowing the implementation of effective vision algorithms performing image processing directly on the embedded node. In this paper we present a multi-modal video sensor node designed for low-power and low-cost video surveillance able to detect changes in the environment. The system is equipped with a CMOS video camera and a Pyroelectric InfraRed (PIR) sensor exploited to reduce remarkably the power consumption of the system in absence of events. The on-board microprocessor implements an NCC-based change detection algorithm. We analyze different configurations and characterize the system in terms of runtime execution and power consumption.
Cited by:15
Resources:[PDF] from hal.science
:view less
A low-power wireless video sensor node for distributed object detection
2007
Aliaksei Kerhet, Michele Magno, Francesco Leonardi, Andrea Boni, Luca Benini
journal of real-time image processing 2 (4), 331-342
:read more
Authors:Aliaksei Kerhet, Michele Magno, Francesco Leonardi, Andrea Boni, Luca Benini
Publication date:12/01/2007
Journal:journal of real-time image processing
Volume:2
Issue:4
Pages:331-342
Publisher:Springer-Verlag
Description:In this paper we propose MicrelEye, a wireless video node for cooperative distributed video processing applications that involve image classification. The node is equipped with a low-cost VGA CMOS image sensor, a reconfigurable processing engine (FPGA, Microcontroller, SRAM) and a Bluetooth 100-m transceiver. It has a size of few cubic centimeters and its typical power consumption is approximately ten times less than that of typical commercial DSP-based solutions. As regards classification, a highly optimized hardware-oriented support vector machine-like (SVM-like) algorithm called ERSVM is proposed and implemented. We describe our hardware and software architecture, its performance and power characteristics. The case study considered in this paper is people detection. The obtained results suggest that the present technology allows for the design of simple intelligent video nodes capable of …
Cited by:76
:view less
Distributed video surveillance using hardware-friendly sparse large margin classifiers
2007
Aliaksei Kerhet, Francesco Leonardi, Andrea Boni, Paolo Lombardo, Michele Magno, Luca B…
2007 IEEE Conference on Advanced Video and Signal Based Surveillance, 87-92
:read more
Authors:Aliaksei Kerhet, Francesco Leonardi, Andrea Boni, Paolo Lombardo, Michele Magno, Luca Benini
Publication date:09/05/2007
Journal:2007 IEEE Conference on Advanced Video and Signal Based Surveillance
Pages:87-92
Publisher:IEEE
Description:In contrast to video sensors which just "watch " the world, present-day research is aimed at developing intelligent devices able to interpret it locally. A number of such devices are available on the market, very powerful on the one hand, but requiring either connection to the power grid, or massive rechargeable batteries on the other. MicrelEye, the wireless video sensor node presented in this paper, targets a different design point: portability and a scanty power budget, while still providing a prominent level of intelligence, namely objects classification. To deal with such a challenging task, we propose and implement a new SVM-like hardware-oriented algorithm called ERSVM. The case study considered in this work is people detection. The obtained results suggest that the present technology allows for the design of simple intelligent video nodes capable of performing local classification tasks.
Cited by:38
Resources:[PDF] from researchgate.net
:view less
Reconfiguration strategies for environmentally powered devices: theoretical analysis and experimental validation
2007
Alex E Şuşu, Michele Magno, Andrea Acquaviva, David Atienza, Giovanni De Micheli
Transactions on High-Performance Embedded Architectures and Compilers I, 341-360
:read more
Authors:Alex E Şuşu, Michele Magno, Andrea Acquaviva, David Atienza, Giovanni De Micheli
Publication date:07/21/2007
Journal:Transactions on High-Performance Embedded Architectures and Compilers I
Pages:341-360
Publisher:Springer Berlin Heidelberg
Description:Environmental energy is becoming a feasible alternative to traditional energy sources for ultra low-power devices such as sensor nodes. These devices can run reactive applications that adapt their control flow depending on the sensed data. In order to reduce the energy consumption of the platform and also to meet the timing constraints imposed by the application, we propose to dynamically reconfigure the system through the use of Field Programmable Gate Array (FPGA) fabric such that it executes more efficiently the tasks of the application. In this paper we present a new approach that enables the designer to efficiently explore different reconfiguration strategies for environmentally powered systems. For this we define a stochastic model of a harvesting video sensor node that captures the behavior of the node and of its environment. We use this approach to investigate the impact of different reconfiguration …
Cited by:25
Resources:[PDF] from epfl.ch
:view less
A Low-Power Configurable Wireless Video Sensor Node for Distributed Vision Applications.
2007
Michele Magno, Luca Benini
Proceedings of International Conference on Distributed Smart Cameras (ICDSC-07), 390-391
:read more
Authors:Michele Magno, Luca Benini
Publication date:01/01/2007
Journal:Proceedings of International Conference on Distributed Smart Cameras (ICDSC-07)
Pages:390-391
Publisher:sl
Description:A Low-Power Configurable Wireless Video Sensor Node for Distributed Vision Applications. IRIS IRIS Home Sfoglia Macrotipologie & tipologie Autore Titolo Riviste Serie IT Italiano Italiano English English LOGIN 1.IRIS 2.UNIBO 3.4 - Contributo in Atti di convegno 4.4.01 Contributo in Atti di convegno . M. Magno, L. Benini (2007). A Low-Power Configurable Wireless Video Sensor Node for Distributed Vision Applications.. sl : sn A Low-Power Configurable Wireless Video Sensor Node for Distributed Vision Applications. MAGNO, MICHELE;BENINI, LUCA 2007 Abstract . Scheda breve Scheda completa Scheda completa (DC) Anno 2007 Titolo del volume Proceedings of International Conference on Distributed Smart Cameras (ICDSC - 07) Pagina iniziale 390 Pagina finale 391 Citazione M. Magno, L. Benini (2007). A Low-Power Configurable Wireless Video Sensor Node for Distributed Vision Applications.. sl : sn Tutti …
:view less
WEB CHAIRS
Michele Magno, David Cumming, Eugenio Di Sciascio, Georges Gielen, Jan M Rabaey, Chris …
:read more
Authors:Michele Magno, David Cumming, Eugenio Di Sciascio, Georges Gielen, Jan M Rabaey, Chris Van Hoof, Valerio Francesco Annese, Domenico Balsamo, Luca Benini, ETH Zurich, Eugenio Cantatore, Domenico Caputo, Stefano D’Amico, Giampiero de Cesare, Elisabetta Farella, ICT Center, Marco Fattori, Giuseppe Ferri, Maher Kayal, Philipp Mayer, Linda Milor, Eugenio Nappi, Jun Ohta, Krikor B Ozanyan, Tommaso Polonelli, Emanuel Popovici, Michele Ruta, Pietro Siciliano IMM-CNR, Roland Thewes, Andrei Vladimirescu, TU Delft
Description:IWASI 2025 Committees Page 1 ORGANIZING COMMITTEE GENERAL CHAIRS Daniela De Venuto Politecnico di Bari and INFN Michele Magno ETH Zurich STEERING COMMITTEE David Cumming Glasgow University Eugenio Di Sciascio Politecnico di Bari Georges Gielen KU Leuven Jan M. Rabaey University of California at Berkeley Chris Van Hoof KU Leuven PROGRAM COMMITTEE Valerio Francesco Annese Italian Institute of Technology Domenico Balsamo Newcastle University Luca Benini University of Bologna and ETH Zurich Eugenio Cantatore Eindhoven University of Technology Domenico Caputo Sapienza University of Rome Stefano D’Amico University of Salento Giampiero de Cesare Sapienza University of Rome Luigi Dilillo IES/CNRS/UM Elisabetta Farella Fondazione Bruno Kessler - ICT Center Marco Fattori Eindhoven University of Technology Giuseppe Ferri Università degli Studi dell’Aquila …
:view less
SPONSORS 3 FOREWORD 9 ORGANIZING COMMITTEE 11 SESSION 1 12
Jan Rabaey, Silvano Cortesi, Lukas Schulthess, Michele Magno, A Novel Current-Mode EMG …
:read more
Authors:Jan Rabaey, Silvano Cortesi, Lukas Schulthess, Michele Magno, A Novel Current-Mode EMG Interface, Riccardo Olivieri, Gianluca Barile, Vincenzo Stornelli, Davide Ciarrocchi, Martina Fonte, Alessandro Zompanti, Giuseppe Ferri, Francesco Anelli, Antonella Maria Loconsole, Francesco Prudenzano, Georges Gielen, Benjamin Hodo, Tommaso Polonelli, Amirhossein Moallemi, Luca Benini, Dominic Lightbody, Duc-Minh Ngo, Andriy Temko, Colin Murphy, Emanuel Popovici, Nicola Lovecchio, Giulia Petrucci, Fabio Cappelli, Martina Baldini, Giampiero De Cesare, Domenico Caputo, Zoltan Marcsek, Tino Gfrörer, Chi-Ching Hsu, Christian Franck, Chiara Botrugno, Kanika Dheman, Pietro Bonazzi, Giulio Trono, Pasquale Tondo, Vincenzo Scarola, Donato Lacedonia, Francesco Dell’Olio, Shengyu Duan, Rishad Shafik, Alex Yakovlev, Vincenzina Zecchino, Luigi Lombardi, Cristoforo Marzocca, Gianvito Matarrese, Pietro Patimisco, Angelo Sampaolo, Vincenzo Spagnolo, Pietro Bartoli, Varsha Jayaprakash, Julian Moosmann, Philipp Mayer, Franco Zappa, Luca Tognoni, Neil Reichlin, Edoardo Ghignone, Nicolas Baumann, Steven Marty, Liam Boyle
Description:IWASI 2025 TOC Page 1 CONTENTS SPONSORS 3 FOREWORD 9 ORGANIZING COMMITTEE 11 SESSION 1 12 Keynote 1: The “Compute Continuum” and its Energetics. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 12 Jan Rabaey, University of California at Berkeley, USA WakeMod: A 6.9µW Ultra-Low Power Wake-Up Radio Module with -72.6dBm Sensitivity for On-Demand IoT . . . . . 13 Silvano Cortesi, Lukas Schulthess and Michele Magno A Novel Current-Mode EMG Interface . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 19 Riccardo Olivieri, Gianluca Barile, Vincenzo Stornelli, Davide Ciarrocchi, Martina Fonte, Alessandro Zompanti and Giuseppe Ferri All-Fiber In-Line Mach-Zehnder Interferometer for High-Resolution Sensing. . . . . . . . . . . . . . . . . . . . . . . . . . . . . 25 Francesco Anelli, Antonella Maria Loconsole and Francesco Prudenzano Keynote 2: Ultra-low-power circuit design for edge …
Resources:[PDF] from ieee.org
:view less
Practice Paper
M Magno, V Abou Khalil, C Schurgers
:read more
Authors:M Magno, V Abou Khalil, C Schurgers
Description:This practice paper introduces the project-based approach of the Center for Project-Based Learning within the Department of Information Technology and Electrical Engineering of ETH Zürich. This center’s approach to education is built around a three-stage education model that includes projects early on in the students' educational journeys, gradually increasing their complexity in alignment with their growing level of experience. This approach ensures students develop both technical expertise and essential professional skills necessary for their engineering careers, scaffolding course work, small scale group projects and interdisciplinary flagship projects. The center is further enhanced by an evidence-based approach to continued improvement, using regular surveys, reflective journals, and research
Resources:[PDF] from epfl.ch
:view less
A Generic Framework for Modeling MAC Protocols in Wireless Sensor Networks
Fay ็ al Ait Aoudia, Matthieu Gautier, Michele Magno, Olivier Berder, Luca Benini
:read more
Authors:Fay ็ al Ait Aoudia, Matthieu Gautier, Michele Magno, Olivier Berder, Luca Benini
Description:Wireless sensor networks are employed in many applications, such as health care, environmental sensing, and industrial monitoring. An important research issue is the design of efficient medium access control (MAC) protocols, which have an essential role for the reliability, latency, throughput, and energy efficiency of communication, especially as communication is typically one of the most energy consuming tasks. Therefore, analytical models providing a clear understanding of the fundamental limitations of the different MAC schemes, as well as convenient way to investigate their performance and optimize their parameters, are required. In this paper, we propose a generic framework for modeling MAC protocols, which focuses on energy consumption, latency, and reliability. The framework is based on absorbing Markov chains, and can be used to compare different schemes and evaluate new approaches. The …
:view less
SPECIAL ISSUE ON INTEGRATED SENSING, COMPUTING, AND COMMUNICATION FOR INTERNET OF ROBOTIC THINGS
H Xiao, Z Huang, Z Xu, S Yang, W Wang, L Zhong, C Xu, C Friess, V Niculescu, T Polonell…
:read more
Authors:H Xiao, Z Huang, Z Xu, S Yang, W Wang, L Zhong, C Xu, C Friess, V Niculescu, T Polonelli, M Magno, L Benini, R Su, R Wang, S Duan
Description:Table of Contents Page 1 IEEE COMPUTER SOCIETY 15 OCTOBER 2024 VOLUME 11 NUMBER 20 IITJAU (ISSN 2327-4662) SPECIAL ISSUE ON INTEGRATED SENSING, COMPUTING, AND COMMUNICATION FOR INTERNET OF ROBOTIC THINGS SPECIAL ISSUE PAPERS Task-Driven Cooperative Internet of Robotic Things Crowdsourcing: From the Perspective of Hierarchical Game Theoretic ................................................ H. Xiao, Z. Huang, Z. Xu, S. Yang, W. Wang, L. Zhong, and C. Xu 32350 Fully Onboard SLAM for Distributed Mapping With a Swarm of Nano-Drones . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . ................................................... C. Friess, V. Niculescu, T. Polonelli, M. Magno, and L. Benini 32363 Self-Attention Factor Graph Neural Network for Multiagent Collaborative Target Tracking . . . . . . . . . . . . . . . . . . . . . . . . . . . ........................................................................... C. Xu, R. Su, R. Wang, and S. Duan 32381 …
Resources:[PDF] from ieee.org
:view less
Best Poster Presentation
Tommaso Polonelli, Gian Hug, Michele Magno
:read more
Authors:Tommaso Polonelli, Gian Hug, Michele Magno
Description:Best Poster Presentation | IEEE Conference Publication | IEEE Xplore Best Poster Presentation Published in: 2024 International Symposium on Power Electronics, Electrical Drives, Automation and Motion (SPEEDAM) Article #: Date of Conference: 19-21 June 2024 Date Added to IEEE Xplore: 05 August 2024 ISBN Information: Electronic ISBN: 979-8-3503-8759-9 Print on Demand(PoD) ISBN: 979-8-3503-8760-5 ISSN Information: Electronic ISSN: 2835-8457 Print on Demand(PoD) ISSN: 2835-8449 INSPEC Accession Number: Persistent Link: https://xplorestaging.ieee.org/servlet/opac?punumber=10609025 More » Publisher: IEEE IEEE Account Change Username/Password Update Address Purchase Details Payment Options Order History View Purchased Documents Profile Information Communications Preferences Profession and Education Technical Interests Need Help? US & Canada: +1 800 678 4333 …
:view less
2024 IEEE/ACM Ninth International Conference on Internet-of-Things Design and Implementation (IoTDI)| 979-8-3503-7025-6/24/$31.00© 2024 IEEE| DOI: 10.1109/IoTDI61053. 2024.00032
Fawad Ahmad, Adeyinka Akintola, Homa Alemzadeh, Bayan Al Muhander, Alex Cabral, Tiani C…
:read more
Authors:Fawad Ahmad, Adeyinka Akintola, Homa Alemzadeh, Bayan Al Muhander, Alex Cabral, Tiani Chen-Troester, Geffen Cooper, Farooq Dar, Kenneth DeHaan, Kanika Dheman, Yuqi Dong, Wan Du, Mohammed Elbadry, Allen-Jasmin Farcas, Huber Flores, Guanyu Gao, Xueren Ge, Pradipta Ghosh, Marco Giordano, Sathish Gopalakrishnan, Ramesh Govindan, Mahanth Gowda, Ashikul Haque, Tianda Huang, Sneha Iyer, Saahith Janapati, Boyu Jiang, Timothy K Johnsen, Li Ju, Kumseok Jung, Raja Jurdak, Sion Kim, Ramana Rao Kompella, Hugo Latapie, Myungjin Lee, Branden Leong, Marco Levorato, Shenghui Li, Vincent Liew, Yu-An Lin, Yuan Lin-Huang, Miaomiao Liu, Tao Liu, Mohan Liyanage, Taiting Lu, Michele Magno, Radu Marculescu, Peter Milder, Afnan Mir, Gargi Mitra, Amy V Mueller, Edith CH Ngai, Ngoc Thi Nguyen, Petteri Nurmi, Mayowa Olapade, Abdul-Rasheed Ottun, Weiwu Pang, Monica Passanantti, Karthik Pattabiraman, Ali Payani, Charith Perera, Marko Radeta, Gowri Ramachandran, Omer Rana, Arya Rathee, Andrea Ronco, Abusayeed Saifullah, Philipp Schilk, Prithvi Senthilkumar, Hui-Xin Shih, Christina Shin, Francisco Airton Silva, Hyun Joon Song
Description:Author Index | IEEE Conference Publication | IEEE Xplore Author Index Published in: 2024 IEEE/ACM Ninth International Conference on Internet-of-Things Design and Implementation (IoTDI) Article #: Date of Conference: 13-16 May 2024 Date Added to IEEE Xplore: 24 June 2024 ISBN Information: Electronic ISBN: 979-8-3503-7025-6 Print on Demand(PoD) ISBN: 979-8-3503-7026-3 INSPEC Accession Number: Persistent Link: https://xplorestaging.ieee.org/servlet/opac?punumber=10562147 More » Publisher: IEEE IEEE Account Change Username/Password Update Address Purchase Details Payment Options Order History View Purchased Documents Profile Information Communications Preferences Profession and Education Technical Interests Need Help? US & Canada: +1 800 678 4333 Worldwide: +1 732 981 0060 Contact & Support About IEEE Xplore Contact Us Help Accessibility Terms of Use …
:view less
WRISTSENSE 2023: WRISTSENSE 2023: Ninth Workshop on sensing systems and applications using wrist worn smart devices-Program
Paul Lukowicz, Mengxi Liu, Michele Magno, Kexuan Guo, Varsha Sharma, Shalini Mukhopadhy…
:read more
Authors:Paul Lukowicz, Mengxi Liu, Michele Magno, Kexuan Guo, Varsha Sharma, Shalini Mukhopadhyay, Sakyajit Bhattacharya, Billy Dawton, Shigemi Ishida, Yutaka Arakawa
Description:WRISTSENSE 2023: WRISTSENSE 2023: Ninth Workshop on sensing systems and applications using wrist worn smart devices - Program Toggle navigation IEEE Computer Society Digital Library Jobs Tech News Resource Center Press Room Advertising About Us IEEE IEEE Computer Society IEEE Computer Society Digital Library My Subscriptions Magazines Journals Conference Proceedings Institutional Subscriptions IEEE IEEE Computer Society More Jobs Tech News Resource Center Press Room Advertising About Us Cart All Advanced Search Conference Cover Image Download 1.Home 2.Proceedings 3.percom-workshops 2023 WRISTSENSE 2023: WRISTSENSE 2023: Ninth Workshop on sensing systems and applications using wrist worn smart devices - Program 2023, pp. 62-63, DOI Bookmark: 10.1109/PerComWorkshops56833.2023.10150356 Keywords Authors WRISTSENSE 2023: …
:view less
Ultra Low Power Eye Tracking with QVar Sensors
Nicolas Schärer, Federico Villani, Michele Magno
:read more
Authors:Nicolas Schärer, Federico Villani, Michele Magno
Description:Smart wearables is a growing market, and with devices such as Smart Glasses and AR/VR Headsets, eye-tracking is a must for user interaction. Current solutions such as image recognition require high power consumption. Thus, extending battery life and reducing the footprint of such systems is a necessity, and can be achieved by using Low Power novel QVar sensors. The end goal of this project is to embed the solution in regular glasses, though an intermediate achievement would be to do it on VR/AR headsets. This would be made easier thanks to the large skin contact area of those devices. This is why a ski mask is used as the base of the prototype. It allows for easy exploration of different configurations.
:view less
Conditional Execution Of Cascaded Models Improves The Accuracy-Efficiency Trade-Off
Luzian Lebovitz, Lukas Cavigelli, Michele Magno, Lorenz K Muller
:read more
Authors:Luzian Lebovitz, Lukas Cavigelli, Michele Magno, Lorenz K Muller
Description:The compute effort required to perform inference on state-of-the-art deep learning models is ever growing. Practical applications are commonly limited to a certain cost per inference. Cascades of pretrained models with conditional execution address these requirements based on the intuition that some inputs are easy enough that they can be processed correctly by a small model allowing for an early exit. If the small model is not sufficiently confident in its prediction, the input is passed on to a larger model. The selection of the confidence threshold allows to trade off compute effort against accuracy. In this work, we explore the effective design of model cascades, and thoroughly evaluate the impact on the accuracy-compute trade-off. We find that they not only interpolate favorably between pretrained models, but that this trade-off curve commonly outperforms single models. This allows us to redefine most of the ImageNet Pareto front already with 2-model cascades, achieving an average reduction in compute effort at equal accuracy of almost 3.1x above 86% and more than 1.9x between 80% and 86% top-1 accuracy. We confirm the wide applicability and effectiveness of the method on the GLUE benchmark. We release the code to reproduce our experiments in the supplementary material and use only publicly available models and datasets.
Resources:[PDF] from openreview.net
:view less
Ultra Low Power Asynchronous MAC Protocol using Wake-Up Radio for Energy Neutral Wireless Sensor Network
Trong Nhan Le, Michele Magno, Alain Pegatoquet, Olivier Berder, Olivier Sentieys, Emanu…
:read more
Authors:Trong Nhan Le, Michele Magno, Alain Pegatoquet, Olivier Berder, Olivier Sentieys, Emanuel Popovici
Description:Ultra Low Power Asynchronous MAC Protocol using Wake-Up Radio for Energy Neutral Wireless Sensor Network Page 1 Ultra Low Power Asynchronous MAC Protocol using Wake-Up Radio for Energy Neutral Wireless Sensor Network 1 Trong Nhan Le 1,2, Michele Magno3, Alain Pegatoquet2, Olivier Berder1, Olivier Sentieys1 and Emanuel Popovici3 1INRIA/University of Rennes 1 (ENSSAT), 2LEAT/University of Nice, 3University College Cork 1{trong-nhan.le, sentieys, oberder}@irisa.fr 2{alain.pegatoquet}@unice.fr 3{m.magno, e.popovici}@ucc.ie Page 2 • Medical and Health Monitoring Ultra Low Power Asynchronous MAC Protocol using Wake-Up Radio 2 Energy Harvesting (EH) WSN Applications • Structure Health Monitoring • Wireless Sensor Networks • Smart building Page 3 Harvesting Energy Sources Multiple-sources 3 Ultra Low Power Asynchronous MAC Protocol using Wake-Up Radio Heat Micropelt […
Resources:[PDF] from archive.org
:view less
Low Power Embedded Gesture Recognition Using Novel Short-Range Radar Sensors
Michele Magno, Emanuel Eggimann, Jonas Erb, Philipp Mayer, Luca Benini
:read more
Authors:Michele Magno, Emanuel Eggimann, Jonas Erb, Philipp Mayer, Luca Benini
Description:Human-computer interface (HCI) is an attractive scenario and a wide range of solutions, strategies, and technologies have been proposed recently. A very promising novel sensing technology is high frequency and short-range Doppler-radar. Previous works on Doppler-radar have achieved high accuracies on multiple different static, as well as dynamic hand-gestures [1]-[3]. In particular, the Soli system using short-range sensors developed at Google [4], in collaboration with Infineon, shows differentiation between" dynamic hand gestures" and" static hand postures". In particular, dynamic refers to the fact that the hand (or part of it) is in continuous motion during the gesture, while a static posture does not contain any movement. However, the proposed model in [4] uses more than 600MB of memory that is not matching the memory of low power microcontroller. Moreover, the Soli sensors are consuming more than 300mW of power that will drain the battery in a few minutes of use [6]. This work proposes a low-power high-accuracy embedded hand-gesture recognition using low power short-range radar sensors from Acconeer. The hardware and software match the requirements for battery-operated wearable devices. A 2D Convolutional Neural Network (CNN) using range frequency Doppler features is combined with a Temporal Convolutional Neural Network (TCN) for time sequence prediction. The final algorithm has a model size of only 45723 parameters, yielding a memory footprint of only 91kB. Two datasets containing 11 challenging hand gestures performed by 26 different people have been recorded containing a total of 20210 gesture …
Resources:[PDF] from tinyml.org
:view less
SPECIAL SECTION ON SENSOR APPLICATIONS SYMPOSIUM
V Roscher, KR Riemschneider, NN Mai-Khanh, S Nakajima, T Iizuka, Y Mita, K Asada, N Cen…
:read more
Authors:V Roscher, KR Riemschneider, NN Mai-Khanh, S Nakajima, T Iizuka, Y Mita, K Asada, N Cennamo, F Mattiello, RV Galatus, E Voiculescu, L Zeni, JO Alvarez, E Buzi, RW Adams, M Deffenbaugh, A Caviezel, M Schaffner, L Cavigelli, P Niklaus, Y Bühler, P Bartelt, M Magno, L Benini
Description:Presents the table of contents for this issue of this publication.
:view less
SPECIAL SECTION ON THE 2018 IEEE SENSORS APPLICATIONS SYMPOSIUM
S Oho, Y Kaneko, M Hara, Y Oose, J Fukuda, P Mayer, M Magno, L Benini, B Andò, S Baglio…
:read more
Authors:S Oho, Y Kaneko, M Hara, Y Oose, J Fukuda, P Mayer, M Magno, L Benini, B Andò, S Baglio, V Marletta, R Crispino, A Pistorio
Description:Table of contents Page 1 JULY 2019 VOLUME 68 NUMBER 7 IEIMAO (ISSN 0018-9456) SURVEY/REVIEW PAPER Built-in Self-Test, Design-for-Testing, Fault Diagnosis and Fault-Tolerance Tacholess Speed Estimation in Order Tracking: A Review With Application to Rotating Machine Fault Diagnosis .................. ............................................................................................................ S. Lu, R. Yan, Y. Liu, and Q. Wang 2315 SPECIAL SECTION ON THE 2018 IEEE SENSORS APPLICATIONS SYMPOSIUM GUEST EDITORIAL Special Section on the 2018 IEEE Sensors Applications Symposium ......................................... GS Gupta and V. Bilas 2333 SPECIAL SECTION PAPERS Acoustics and Ultrasonics Instrumentation and Measurements Practical Aspects of Ultrasonic Rotary Encoder—Probe Placing, Real-Time Operation, and Automotive Bench Test ................ ....................................................................................... S. Oho, Y. Kaneko, M…
Resources:[PDF] from archive.org
:view less
IEEE Sensors Council
Michele Magno, Vedran Bilas, Dario Pompili, Gourab Sen Gupta
:read more
Authors:Michele Magno, Vedran Bilas, Dario Pompili, Gourab Sen Gupta
Description:Embedded Systems and Smart Sensors are gaining increasing prominence in the research community. The reason lies in the degree of pervasiveness that embedded systems have allowed them to achieve. Embedded intelligent sensor systems, defined as sensors capable of processing information with algorithms in-situ interfacing with the external environment to provide feedback, are now widespread in everyday life. Progress in this area is now driven by the need for embedded sensor systems comprising one or more low-power and resource-constrained elements organized in an extensive network. This pushes to develop sensors systems based on new hardware, lightweight machine learning algorithms, and software that are energy and computationally efficient. Moreover, the machine learning algorithms run in tiny low-power processors (including microcontrollers, milliwatts ASIC and FPGA) with few …
:view less
Extended Wireless Monitoring through Intelligent Hybrid Energy Supply
David Boyle, Michele Magno, Davide Brunelli
:read more
Authors:David Boyle, Michele Magno, Davide Brunelli
Description:SHM is performed to manage risk. It is typically done using wired systems collecting environmental data over long periods of time.
:view less
A self-powered video sensor node triggered by PIR sensors
Michele Magno, Davide Brunelli, Piero Zappi, Luca Benini
:read more
Authors:Michele Magno, Davide Brunelli, Piero Zappi, Luca Benini
Description:This paper describes a multi-modal video sensor node designed for low-power and low-cost video surveillance systems, traffic control and people or object tracking based on wireless sensor networks. It is equipped with a solar energy harvesting module which extends the autonomy of the nodes considerably using a solar cell of 70 cm2. The developed prototype mounts a CMOS video camera and Pyroelectric InfraRed (PIR) sensors, which allow to reduce remarkably the power consumption of the systems in absence of events to detect without losses in the accuracy of the application. Wireless communication capabilities have been provided through a suitable interface which can host either Zigbee compliant transceiver or Bluetooth. The on-board microprocessor enables complex image processing such as image classification using algorithms based on a support vector machine (SVM). We describe hardware-software architecture of the video sensor node and characterization in terms of power consumption. I. INTRODUCTION AND RELATED WORK Low-cost video surveillance systems based on wireless sensor networks will enter soon the marketplace with the promise of flexibility, quickly deployment and providing accurate and real-time visual data. However, many technical problems have to be still overcome for a widespread diffusion of such a technology. For instance, although research continues to develop higher energy-density batteries, the amount of available energy on board still severely limits the lifespan of distributed battery operated embedded systems. This leads to the fact that a major challenge with a Wireless Video sensor …
:view less
Q-VDiT: Accurate Quantized Video Diffusion Transformer with Salient Data and Sparse Token Distillation
Weilun Feng, Haotong Qin, Chuanguang Yang, Xiangqi Li, Han Yang, Yuqi Li, Zhulin An, Li…
The Thirty-ninth Annual Conference on Neural Information Processing Systems
:read more
Authors:Weilun Feng, Haotong Qin, Chuanguang Yang, Xiangqi Li, Han Yang, Yuqi Li, Zhulin An, Libo Huang, Michele Magno, Yongjun Xu
Journal:The Thirty-ninth Annual Conference on Neural Information Processing Systems
Description:Diffusion transformers have emerged as the mainstream paradigm for video generation models. However, the use of up to billions of parameters incurs significant computational costs. Quantization offers a promising solution by reducing memory usage and accelerating inference. Nonetheless, we observe that the joint modeling of spatial and temporal information in video diffusion models (V-DMs) leads to extremely long token sequences, which introduces high calibration variance and learning challenges. To address these issues, we propose **Q-VDiT**, a post-training quantization framework for V-DMs that leverages **S**alient data and **S**parse token distillation. During the calibration phase, we identify that quantization performance is highly sensitive to the choice of calibration data. To mitigate this, we introduce *Hessian-aware Salient Data Selection*, which constructs high-quality calibration datasets by considering …
:view less
:back to overview