Search

Your search keyword '"Gosselin, Benoit"' showing total 8 results
Start Over Author "Gosselin, Benoit" Publication Year Range This year
8 results on '"Gosselin, Benoit"'

1. Towards Robust and Interpretable EMG-based Hand Gesture Recognition using Deep Metric Meta Learning

Author

Tam, Simon, Raghu, Shriram Tallam Puranam, Buteau, Étienne, Scheme, Erik, Boukadoum, Mounir, Campeau-Lecours, Alexandre, and Gosselin, Benoit

Subjects
Electrical Engineering and Systems Science - Signal Processing, Computer Science - Artificial Intelligence, Computer Science - Human-Computer Interaction, Computer Science - Machine Learning, Electrical Engineering and Systems Science - Systems and Control
Abstract

Current electromyography (EMG) pattern recognition (PR) models have been shown to generalize poorly in unconstrained environments, setting back their adoption in applications such as hand gesture control. This problem is often due to limited training data, exacerbated by the use of supervised classification frameworks that are known to be suboptimal in such settings. In this work, we propose a shift to deep metric-based meta-learning in EMG PR to supervise the creation of meaningful and interpretable representations. We use a Siamese Deep Convolutional Neural Network (SDCNN) and contrastive triplet loss to learn an EMG feature embedding space that captures the distribution of the different classes. A nearest-centroid approach is subsequently employed for inference, relying on how closely a test sample aligns with the established data distributions. We derive a robust class proximity-based confidence estimator that leads to a better rejection of incorrect decisions, i.e. false positives, especially when operating beyond the training data domain. We show our approach's efficacy by testing the trained SDCNN's predictions and confidence estimations on unseen data, both in and out of the training domain. The evaluation metrics include the accuracy-rejection curve and the Kullback-Leibler divergence between the confidence distributions of accurate and inaccurate predictions. Outperforming comparable models on both metrics, our results demonstrate that the proposed meta-learning approach improves the classifier's precision in active decisions (after rejection), thus leading to better generalization and applicability., Comment: 11 pages, 9 figures, submitted to IEEE Transactions on Neural Networks and Learning Systems

Published
2024

2. Design and Implementation of a Low-Power Low-Noise Biopotential Amplifier in 28 nm CMOS Technology with a Compact Die-Area of 2500 $\mu$m$^2$

Author

Koleibi, Esmaeil Ranjbar, Koua, Konin, Lemaire, William, Benhouria, Maher, Besrour, Marwan, Omrani, Takwa, Ménard, Jérémy, Gauthier, Louis-Philippe, Dridi, Montassar, Mazandarani, Mahziar Serri, Gosselin, Benoit, and Fontaine, Sébastien Royand Réjean

Subjects
Quantitative Biology - Neurons and Cognition, Electrical Engineering and Systems Science - Signal Processing, Electrical Engineering and Systems Science - Systems and Control, Physics - Biological Physics
Abstract

This paper presents a compact low-power, low-noise bioamplifier for multi-channel electrode arrays, aimed at recording action potentials. The design we put forth attains a notable decrease in both size and power consumption. This is achieved by incorporating an active lowpass filter that doesn't rely on bulky DC-blocking capacitors, and by utilizing the TSMC 28 nm HPC CMOS technology. This paper presents extensive simulation results of noise and results from measured performance. With a mid-band gain of 58 dB, a -3 dB bandwidth of 7 kHz (from 150 Hz to 7.1 kHz), and an input-referred noise of 15.8 $\mu$V$_{\rm rms}$ corresponding to a NEF of 12. The implemented design achieves a favourable trade-off between noise, area, and power consumption, surpassing previous findings in terms of size and power. The amplifier occupies the smallest area of 2500 $\mu$m$^2$ and consumes only 3.4 $\mu$W from a 1.2 V power supply corresponding to a power efficiency factor of 175 and an area efficiency factor of 0.43, respectively.

Published
2024

5. Potential of a New, Flexible Electrode sEMG System in Detecting Electromyographic Activation in Low Back Muscles during Clinical Tests: A Pilot Study on Wearables for Pain Management.

Author

Frasie, Antoine, Massé-Alarie, Hugo, Bielmann, Mathieu, Gauthier, Nicolas, Roudjane, Mourad, Pagé, Isabelle, Gosselin, Benoit, Roy, Jean-Sébastien, Messaddeq, Younes, and Bouyer, Laurent J.

Subjects
ERECTOR spinae muscles, BACK muscles, LUMBAR pain, MUSCLE fatigue, PAIN management, MUSCLE growth
Abstract

Background: While low back pain (LBP) is the leading cause of disability worldwide, its clinical objective assessment is currently limited. Part of this syndrome arises from the abnormal sensorimotor control of back muscles, involving increased muscle fatigability (i.e., assessed with the Biering–Sorensen test) and abnormal muscle activation patterns (i.e., the flexion–extension test). Surface electromyography (sEMG) provides objective measures of muscle fatigue development (median frequency drop, MDF) and activation patterns (RMS amplitude change). This study therefore assessed the sensitivity and validity of a novel and flexible sEMG system (NSS) based on PEVA electrodes and potentially embeddable in textiles, as a tool for objective clinical LBP assessment. Methods: Twelve participants wearing NSS and a commercial laboratory sEMG system (CSS) performed two clinical tests used in LBP assessment (Biering–Sorensen and flexion–extension). Erector spinae muscle activity was recorded at T12-L1 and L4-L5. Results: NSS showed sensitivity to sEMG changes associated with fatigue development and muscle activations during flexion–extension movements (p < 0.05) that were similar to CSS (p > 0.05). Raw signals showed moderate cross-correlations (MDF: 0.60–0.68; RMS: 0.53–0.62). Adding conductive gel to the PEVA electrodes did not influence sEMG signal interpretation (p > 0.05). Conclusions: This novel sEMG system is promising for assessing electrophysiological indicators of LBP during clinical tests. [ABSTRACT FROM AUTHOR]

Published
2024
Full Text
View/download PDF

6. A Vital-Signs Monitoring Wristband With Real-Time In-Sensor Data Analysis Using Very Low-Hardware Resources

Author

Mascret, Quentin, Gurve, Dharmendra, Abdou, Abdelrahman, Bhadra, Sharmistha, Lasry, Nathaniel, Mai, Kristiina, Krishnan, Sridhar, and Gosselin, Benoit

Abstract

We present a cost-effective multisensor wristband that monitors vital signs, including heart rate (HR), respiratory rate, and oxygen saturation, with very low-hardware resources, while effectively mitigating motion artifacts. Our system, which operates in real time, optimizes resource utilization and minimizes memory footprint by intelligently managing motion artifacts during vital signs extraction. For this purpose, we introduce a new intelligent domain fusion (IDF) algorithm, which allows to reduce resource allocation during moderate motion artifacts by up to 30% in memory usage, while achieving an average latency of as short as 18 ms in worst case. To further enhance efficiency, our frequency-domain analysis (FDA) is optimized through the utilization of a Z-chirp transform, minimizing memory utilization during Fourier transforms. Our prototype is built around a real-time operating system (freeRTOS) running on an ARM-M4 architecture, enabling Bluetooth lowenergy (BLE) 5.0 control, data processing, and communication. It incorporates an onboard 1-Gbit Nand flash memory for continuous data storage, when no wireless connection is available, offering up to 7 h of uninterrupted sensor data recording. The sensor data collected by our prototype encompass a comprehensive range of raw and processed information critical for monitoring various physiological and environmental parameters in a concise message format comprising a data ID, a data payload, and a timestamp. With a small 250 mAh battery, our prototype provides an autonomy of 18 h of continuous data collection, averaging a mere 10.41 mAh of power consumption.

Published
2024
Full Text
View/download PDF

7. An Ultralow-Power PPG Sensor With Adaptive Predictive Sampling

Author

Ebrahimi, Zobair and Gosselin, Benoit

Abstract

Photoplethysmography (PPG) sensors provide precise vital sign measurements. However, conventional PPG signal detection requires continuous light-emitting diodes (LEDs), resulting in significant power consumption. To cancel dc components, ambient light, and motion artifacts (MAs), PPG sensors incorporate significant signal processing circuitry. This circuitry is critical to cancel interference, increase dynamic range (DR), and improve signal-to-noise ratio (SNR), which further increases power consumption. This article presents a novel PPG sensor that adaptively predicts and samples only the peaks and valleys (PAVs), i.e., the maximum and minimum amplitudes, of the PPG signal. Using the predicted PAVs, the sensor extracts vital signs, including heart rate (HR), HR variability (HRV), oxygen saturation (SpO2), systolic, diastolic, and cardiac cycles, while reducing power consumption by over 87%. Our sampling scheme shows a low mean absolute error (MAE) of 5.76 beats per minute (bpm) when tested on the PPG-DaLiA dataset with data from 15 subjects. Moreover, in a prototype test with five subjects, our sensor was used on various body parts, including the finger, wrist, arm, chest, neck, earlobe, and forehead, during activities, such as walking, typing, and sitting. Achieved MAEs are < 0.5 bpm for HR, < 1% for SpO2, and < 3 ms for HRV, systolic, diastolic, and cardiac cycles, across all subjects.

Published
2024
Full Text
View/download PDF

8. High Precision Ping-pong Auto-zeroed Lock-in Fluorescence Photometry Sensor.

Author

Lazarjan VK, Crochetiere ME, Khiarak MN, Aarani SG, Hosseini SN, Gagnon-Turcotte G, Marquet P, and Gosselin B

Abstract

This paper presents a high-precision CMOS fluorescence photometry sensor using a novel lock-in amplification scheme based on switched-biasing and ping-pong auto-zeroing techniques. The CMOS sensor includes two photodiodes and a lock-in amplifier (LIA) operating at 1 kHz. The LIA comprises a differential low-noise amplifier using a novel switched-biasing ping-pong auto-zeroed scheme, an automatic phase aligner, a programmable gain amplifier, a band-pass filter, a mixer, and an output low-pass filter. The design is fabricated in 0.18-μm CMOS process, and the measurement shows that the LIA can retrieve noisy input signals with a dynamic reserve of 42 dB, while consuming only 0.7 mW from a 1.8 V supply voltage. The measured results show that the LIA can detect a wide range of incident light power from 8 nW to 24 μW. The proposed design is encapsulated in a 3D-printed housing allowing for real-time in vitro biomarker detection. This ambulatory platform uses an LED and a fiber optic to convey the excitation light to the sample and retrieve the fluorescence signal. Experiments with a beads solution diluted in PBS demonstrate that the sensor has a sensitivity of 1:100 k. Experimental results obtained in vitro with NIH3T3 mouse cells tagged with membrane dye show the ability of the prototype to detect different densities of cell culture. The portable prototype, which includes optical filters and a small 30 mm × 36 mm × 30 mm printed circuit board enclosed inside the 3D-printed housing, consumes 36.7 mW and weighs 120 g.

Published
2024
Full Text
View/download PDF

Catalog

Books, media, physical & digital resources
See catalog results