Saved in:
Bibliographic Details
Main Authors: Shahrooei, Abolfazl, Arthur, Luke, Patel, Om, Kamper, Derek
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2512.10179
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911312740614144
author Shahrooei, Abolfazl
Arthur, Luke
Patel, Om
Kamper, Derek
author_facet Shahrooei, Abolfazl
Arthur, Luke
Patel, Om
Kamper, Derek
contents High-density surface electromyography (HD-sEMG) provides a noninvasive neural interface for assistive and rehabilitation control, but mapping neural activity to user motor intent remains challenging. We assess a spiking neural network (SNN) as a neuromorphic architecture against a temporal convolutional network (TCN) for decoding fingertip force from motor-unit (MU) firing derived from HD-sEMG. Data were collected from a single participant (10 trials) with two forearm electrode arrays; MU activity was obtained via FastICA-based decomposition, and models were trained on overlapping windows with end-to-end causal convolutions. On held-out trials, the TCN achieved 4.44% MVC RMSE (Pearson r = 0.974) while the SNN achieved 8.25% MVC (r = 0.922). While the TCN was more accurate, we view the SNN as a realistic neuromorphic baseline that could close much of this gap with modest architectural and hyperparameter refinements.
format Preprint
id arxiv_https___arxiv_org_abs_2512_10179
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Assessing Neuromorphic Computing for Fingertip Force Decoding from Electromyography
Shahrooei, Abolfazl
Arthur, Luke
Patel, Om
Kamper, Derek
Machine Learning
Signal Processing
High-density surface electromyography (HD-sEMG) provides a noninvasive neural interface for assistive and rehabilitation control, but mapping neural activity to user motor intent remains challenging. We assess a spiking neural network (SNN) as a neuromorphic architecture against a temporal convolutional network (TCN) for decoding fingertip force from motor-unit (MU) firing derived from HD-sEMG. Data were collected from a single participant (10 trials) with two forearm electrode arrays; MU activity was obtained via FastICA-based decomposition, and models were trained on overlapping windows with end-to-end causal convolutions. On held-out trials, the TCN achieved 4.44% MVC RMSE (Pearson r = 0.974) while the SNN achieved 8.25% MVC (r = 0.922). While the TCN was more accurate, we view the SNN as a realistic neuromorphic baseline that could close much of this gap with modest architectural and hyperparameter refinements.
title Assessing Neuromorphic Computing for Fingertip Force Decoding from Electromyography
topic Machine Learning
Signal Processing
url https://arxiv.org/abs/2512.10179