An LSTM Feature Imitation Network for Hand Movement Recognition from sEMG Signals

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Wu, Chuheng, Atashzar, S. Farokh, Ghassemi, Mohammad M., Alhanai, Tuka
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916546323939328
author Wu, Chuheng
Atashzar, S. Farokh
Ghassemi, Mohammad M.
Alhanai, Tuka
author_facet Wu, Chuheng
Atashzar, S. Farokh
Ghassemi, Mohammad M.
Alhanai, Tuka
contents Surface Electromyography (sEMG) is a non-invasive signal that is used in the recognition of hand movement patterns, the diagnosis of diseases, and the robust control of prostheses. Despite the remarkable success of recent end-to-end Deep Learning approaches, they are still limited by the need for large amounts of labeled data. To alleviate the requirement for big data, we propose utilizing a feature-imitating network (FIN) for closed-form temporal feature learning over a 300ms signal window on Ninapro DB2, and applying it to the task of 17 hand movement recognition. We implement a lightweight LSTM-FIN network to imitate four standard temporal features (entropy, root mean square, variance, simple square integral). We observed that the LSTM-FIN network can achieve up to 99\% R2 accuracy in feature reconstruction and 80\% accuracy in hand movement recognition. Our results also showed that the model can be robustly applied for both within- and cross-subject movement recognition, as well as simulated low-latency environments. Overall, our work demonstrates the potential of the FIN modeling paradigm in data-scarce scenarios for sEMG signal processing.
format Preprint
id arxiv_https___arxiv_org_abs_2405_19356
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle An LSTM Feature Imitation Network for Hand Movement Recognition from sEMG Signals
Wu, Chuheng
Atashzar, S. Farokh
Ghassemi, Mohammad M.
Alhanai, Tuka
Signal Processing
Artificial Intelligence
Machine Learning
Robotics
Surface Electromyography (sEMG) is a non-invasive signal that is used in the recognition of hand movement patterns, the diagnosis of diseases, and the robust control of prostheses. Despite the remarkable success of recent end-to-end Deep Learning approaches, they are still limited by the need for large amounts of labeled data. To alleviate the requirement for big data, we propose utilizing a feature-imitating network (FIN) for closed-form temporal feature learning over a 300ms signal window on Ninapro DB2, and applying it to the task of 17 hand movement recognition. We implement a lightweight LSTM-FIN network to imitate four standard temporal features (entropy, root mean square, variance, simple square integral). We observed that the LSTM-FIN network can achieve up to 99\% R2 accuracy in feature reconstruction and 80\% accuracy in hand movement recognition. Our results also showed that the model can be robustly applied for both within- and cross-subject movement recognition, as well as simulated low-latency environments. Overall, our work demonstrates the potential of the FIN modeling paradigm in data-scarce scenarios for sEMG signal processing.
title An LSTM Feature Imitation Network for Hand Movement Recognition from sEMG Signals
topic Signal Processing
Artificial Intelligence
Machine Learning
Robotics
url https://arxiv.org/abs/2405.19356