Leveraging Convolutional Sparse Autoencoders for Robust Movement Classification from Low-Density sEMG

TL;DR

This paper introduces a deep learning framework using convolutional sparse autoencoders for accurate, low-density sEMG-based gesture recognition, with transfer and incremental learning for adaptability across subjects.

Contribution

It presents a novel deep learning approach that achieves high accuracy with minimal sensors and introduces transfer and incremental learning protocols for practical prosthetic control.

Findings

Achieved 94.3% F1-score on a 6-class gesture set across multiple subjects.

Significantly improved unseen subject performance from 35.1% to 92.3% with few-shot transfer learning.

Enabled expansion to 10 classes with 90.0% F1-score using incremental learning without full retraining.

Abstract

Reliable control of myoelectric prostheses is often hindered by high inter-subject variability and the clinical impracticality of high-density sensor arrays. This study proposes a deep learning framework for accurate gesture recognition using only two surface electromyography (sEMG) channels. The method employs a Convolutional Sparse Autoencoder (CSAE) to extract temporal feature representations directly from raw signals, eliminating the need for heuristic feature engineering. On a 6-class gesture set, our model achieved a multi-subject F1-score of 94.3% $\pm$ 0.3%. To address subject-specific differences, we present a few-shot transfer learning protocol that improved performance on unseen subjects from a baseline of 35.1% $\pm$ 3.1% to 92.3% $\pm$ 0.9% with minimal calibration data. Furthermore, the system supports functional extensibility through an incremental learning strategy, allowing for expansion to a 10-class set with a 90.0% $\pm$ 0.2% F1-score without full model retraining. By combining high precision with minimal computational and sensor overhead, this framework provides a scalable and efficient approach for the next generation of affordable and adaptive prosthetic systems.