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

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Hristov, Blagoj, Hadzi-Velkov, Zoran, Saneva, Katerina Hadzi-Velkova, Nadzinski, Gorjan, Latkoska, Vesna Ojleska
Natura: Preprint
Pubblicazione: 2026
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866910121767993344
author Hristov, Blagoj
Hadzi-Velkov, Zoran
Saneva, Katerina Hadzi-Velkova
Nadzinski, Gorjan
Latkoska, Vesna Ojleska
author_facet Hristov, Blagoj
Hadzi-Velkov, Zoran
Saneva, Katerina Hadzi-Velkova
Nadzinski, Gorjan
Latkoska, Vesna Ojleska
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2601_23011
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Leveraging Convolutional Sparse Autoencoders for Robust Movement Classification from Low-Density sEMG
Hristov, Blagoj
Hadzi-Velkov, Zoran
Saneva, Katerina Hadzi-Velkova
Nadzinski, Gorjan
Latkoska, Vesna Ojleska
Machine Learning
Artificial Intelligence
Signal Processing
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.
title Leveraging Convolutional Sparse Autoencoders for Robust Movement Classification from Low-Density sEMG
topic Machine Learning
Artificial Intelligence
Signal Processing
url https://arxiv.org/abs/2601.23011