From zero- to few-shot: deep temporal learning of wrist EMG enables scalable cross-user gesture recognition
Journal of Neural Engineering · 01.10.2025 · 22 (5) · 056018
DOI: 10.1088/1741-2552/ae08eb ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Neural Engineering, online erschienen am 26.09.2025. Verfasst von Fady S Botros und 3 weiteren Autor:innen. Beteiligte Einrichtung: Department of Electrical and Computer Engineering, University of New Brunswick, Fredericton, NB E3B 5A3, Canada. Hauptthemen laut MEDLINE: Electromyography, Gestures, Wrist, Deep Learning. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 68 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Natural Sciences and Engineering Research Council of Canada.
Abstract (Originalsprache)
Objective. Wrist electromyography (EMG) is emerging as an enticing wearable input modality for human–machine interaction. Traditionally recorded from the forearm for use in transradial prostheses, wrist-based EMG sensors are now being integrated into devices such as watches and wristbands for hand gesture recognition (HGR). Consumer familiarity with wrist-worn devices makes wrist EMG a compelling option, but the need for individualized user calibration remains a challenge. Approach. This study therefore evaluated various cross-user models to reduce the calibration burden and compared wrist- and forearm-based models. Eight different machine learning architectures were evaluated across 33 users, using varying amounts of data from the end user. Main results. A temporal convolutional network-bidirectional long short-term memory architecture, applied for the first time to EMG classification, was found to significantly ( p < 0.05) outperform other tested machine learning architectures. An inter-day feature set combined with Z -score normalization achieved the best performance when classifying five gestures (plus a rest class) using either wrist or forearm EMG. Consistent with other recent results, wrist EMG consistently outperformed forearm EMG in all analyses, including within- and across-user comparisons ( p < 0.05). In cross-user models, wrist EMG demonstrated a zero-shot performance of 78.2%, compared to 71.6% for forearm EMG ( p < 0.05). Introducing one calibration repetition from the end user increased one-shot performance of wrist EMG to 91.6%, compared to 86.9% for forearm EMG ( p < 0.05). Adding further training repetitions boosted wrist EMG performance to 98.3%, compared to 97.4% for forearm EMG. Significance. These findings provide new evidence supporting the viability of wrist EMG for cross-user HGR models that generalize to new users with minimal calibration, suggesting promising potential for its broader adoption in wearable devices.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Electrical and Computer Engineering, University of New Brunswick, Fredericton, NB E3B 5A3, Canada.
- Institute of Biomedical Engineering, University of New Brunswick, Fredericton, NB E3B 5A3, Canada.
- MathWorks, Inc., Natick, MA 01760, United States of America.
ORCID-Profile: Fady S Botros, Heather E Williams, Angkoon Phinyomark, Erik J Scheme
Förderung
- Natural Sciences and Engineering Research Council of Canada
Zitieren
APA
Botros, F. S., Williams, H. E., Phinyomark, A., & Scheme, E. J. (2025). From zero- to few-shot: deep temporal learning of wrist EMG enables scalable cross-user gesture recognition. Journal of Neural Engineering, 22(5), 056018. https://doi.org/10.1088/1741-2552/ae08eb
Vancouver
Botros FS, Williams HE, Phinyomark A, Scheme EJ. From zero- to few-shot: deep temporal learning of wrist EMG enables scalable cross-user gesture recognition. Journal of Neural Engineering. 2025;22(5):056018. doi:10.1088/1741-2552/ae08eb
BibTeX
@article{Botros2025,
author = {Botros, Fady S and Williams, Heather E and Phinyomark, Angkoon and Scheme, Erik J},
title = {From zero- to few-shot: deep temporal learning of wrist EMG enables scalable cross-user gesture recognition},
journal = {Journal of Neural Engineering},
year = {2025},
volume = {22},
number = {5},
pages = {056018},
doi = {10.1088/1741-2552/ae08eb}
}
EUVIMED