Movement recognition via channel-activation-wise sEMG attention
Methods · 2023-10 · 218 · 39-47
DOI: 10.1016/j.ymeth.2023.06.011 ↗Kurz gefasst
Fachartikel in der Zeitschrift Methods, 2023-10. Verfasst von Jiaxuan Zhang und 4 weiteren Autor:innen. Beteiligte Einrichtung: Nara Institute of Science and Technology (NAIST), Ikoma, Nara 630-0192, Japan. Electronic address: zhang.jiaxuan.ze4@is.naist.jp. Hauptthemen laut MEDLINE: Algorithms, Gestures. Die Arbeit wurde bisher 21-mal zitiert (Crossref) und nennt 48 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Japan Society for the Promotion of Science.
Abstract (Originalsprache)
CONTEXT: Surface electromyography (sEMG) signals contain rich information recorded from muscle movements and therefore reflect the user's intention. sEMG has seen dominant applications in rehabilitation, clinical diagnosis as well as human engineering, etc. However, current feature extraction methods for sEMG signals have been seriously limited by their stochasticity, transiency, and non-stationarity. OBJECTIVE: Our objective is to combat the difficulties induced by the aforementioned downsides of sEMG and thereby extract representative features for various downstream movement recognition. METHOD: We propose a novel 3-axis view of sEMG features composed of temporal, spatial, and channel-wise summary. We leverage the state-of-the-art architecture Transformer to enforce efficient parallel search and to get rid of limitations imposed by previous work in gesture classification. The transformer model is designed on top of an attention-based module, which allows for the extraction of global contextual relevance among channels and the use of this relevance for sEMG recognition. RESULTS: We compared the proposed method against existing methods on two Ninapro datasets consisting of data from both healthy people and amputees. Experimental results show the proposed method attains the state-of-the-art (SOTA) accuracy on both datasets. We further show that the proposed method enjoys strong generalization ability: a new SOTA is achieved by pretraining the model on a different dataset followed by fine-tuning it on the target dataset.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Nara Institute of Science and Technology (NAIST), Ikoma, Nara 630-0192, Japan. Electronic address: zhang.jiaxuan.ze4@is.naist.jp.
- Nara Institute of Science and Technology (NAIST), Ikoma, Nara 630-0192, Japan.
- Osaka Metropolitan University, Osaka, Osaka 558-8585, Japan.
Förderung
- Japan Society for the Promotion of Science
Zitieren
APA
Zhang, J., Matsuda, Y., Fujimoto, M., Suwa, H., & Yasumoto, K. (2023). Movement recognition via channel-activation-wise sEMG attention. Methods, 218, 39-47. https://doi.org/10.1016/j.ymeth.2023.06.011
Vancouver
Zhang J, Matsuda Y, Fujimoto M, Suwa H, Yasumoto K. Movement recognition via channel-activation-wise sEMG attention. Methods. 2023;218:39-47. doi:10.1016/j.ymeth.2023.06.011
BibTeX
@article{Zhang2023,
author = {Zhang, Jiaxuan and Matsuda, Yuki and Fujimoto, Manato and Suwa, Hirohiko and Yasumoto, Keiichi},
title = {Movement recognition via channel-activation-wise sEMG attention},
journal = {Methods},
year = {2023},
volume = {218},
pages = {39--47},
doi = {10.1016/j.ymeth.2023.06.011}
}
EUVIMED