English

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

Machine Learning 2026-04-14 v1 Artificial Intelligence Signal Processing

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.

Keywords

Cite

@article{arxiv.2601.23011,
  title  = {Leveraging Convolutional Sparse Autoencoders for Robust Movement Classification from Low-Density sEMG},
  author = {Blagoj Hristov and Zoran Hadzi-Velkov and Katerina Hadzi-Velkova Saneva and Gorjan Nadzinski and Vesna Ojleska Latkoska},
  journal= {arXiv preprint arXiv:2601.23011},
  year   = {2026}
}
R2 v1 2026-07-01T09:27:50.177Z