Low Power Neuromorphic EMG Gesture Classification

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Bezugam, Sai Sukruth, Shaban, Ahmed, Suri, Manan
Format: Preprint
Published: 2022
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916228532011008
author Bezugam, Sai Sukruth
Shaban, Ahmed
Suri, Manan
author_facet Bezugam, Sai Sukruth
Shaban, Ahmed
Suri, Manan
contents EMG (Electromyograph) signal based gesture recognition can prove vital for applications such as smart wearables and bio-medical neuro-prosthetic control. Spiking Neural Networks (SNNs) are promising for low-power, real-time EMG gesture recognition, owing to their inherent spike/event driven spatio-temporal dynamics. In literature, there are limited demonstrations of neuromorphic hardware implementation (at full chip/board/system scale) for EMG gesture classification. Moreover, most literature attempts exploit primitive SNNs based on LIF (Leaky Integrate and Fire) neurons. In this work, we address the aforementioned gaps with following key contributions: (1) Low-power, high accuracy demonstration of EMG-signal based gesture recognition using neuromorphic Recurrent Spiking Neural Networks (RSNN). In particular, we propose a multi-time scale recurrent neuromorphic system based on special double-exponential adaptive threshold (DEXAT) neurons. Our network achieves state-of-the-art classification accuracy (90%) while using ~53% lesser neurons than best reported prior art on Roshambo EMG dataset. (2) A new multi-channel spike encoder scheme for efficient processing of real-valued EMG data on neuromorphic systems. (3) Unique multi-compartment methodology to implement complex adaptive neurons on Intel's dedicated neuromorphic Loihi chip is shown. (4) RSNN implementation on Loihi (Nahuku 32) achieves significant energy/latency benefits of ~983X/19X compared to GPU for batch size as 50.
format Preprint
id arxiv_https___arxiv_org_abs_2206_02061
institution arXiv
publishDate 2022
record_format arxiv
spellingShingle Low Power Neuromorphic EMG Gesture Classification
Bezugam, Sai Sukruth
Shaban, Ahmed
Suri, Manan
Signal Processing
Hardware Architecture
Computer Vision and Pattern Recognition
Human-Computer Interaction
Neural and Evolutionary Computing
EMG (Electromyograph) signal based gesture recognition can prove vital for applications such as smart wearables and bio-medical neuro-prosthetic control. Spiking Neural Networks (SNNs) are promising for low-power, real-time EMG gesture recognition, owing to their inherent spike/event driven spatio-temporal dynamics. In literature, there are limited demonstrations of neuromorphic hardware implementation (at full chip/board/system scale) for EMG gesture classification. Moreover, most literature attempts exploit primitive SNNs based on LIF (Leaky Integrate and Fire) neurons. In this work, we address the aforementioned gaps with following key contributions: (1) Low-power, high accuracy demonstration of EMG-signal based gesture recognition using neuromorphic Recurrent Spiking Neural Networks (RSNN). In particular, we propose a multi-time scale recurrent neuromorphic system based on special double-exponential adaptive threshold (DEXAT) neurons. Our network achieves state-of-the-art classification accuracy (90%) while using ~53% lesser neurons than best reported prior art on Roshambo EMG dataset. (2) A new multi-channel spike encoder scheme for efficient processing of real-valued EMG data on neuromorphic systems. (3) Unique multi-compartment methodology to implement complex adaptive neurons on Intel's dedicated neuromorphic Loihi chip is shown. (4) RSNN implementation on Loihi (Nahuku 32) achieves significant energy/latency benefits of ~983X/19X compared to GPU for batch size as 50.
title Low Power Neuromorphic EMG Gesture Classification
topic Signal Processing
Hardware Architecture
Computer Vision and Pattern Recognition
Human-Computer Interaction
Neural and Evolutionary Computing
url https://arxiv.org/abs/2206.02061