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

TL;DR

This paper introduces a lightweight LSTM-based feature imitation network for hand movement recognition from sEMG signals, achieving high accuracy with limited labeled data and demonstrating robustness across subjects and environments.

Contribution

The study presents a novel LSTM-based feature imitation network that effectively learns temporal features for hand movement recognition in data-scarce scenarios.

Findings

Achieved up to 99% R2 accuracy in feature reconstruction

Reached 80% accuracy in hand movement recognition

Demonstrated robustness in cross-subject and low-latency environments

Abstract

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.