Towards open-set myoelectric gesture recognition via dual-perspective inconsistency learning
Computer Methods and Programs in Biomedicine · 2026
DOI: 10.1016/j.cmpb.2026.109258 ↗Kurz gefasst
Fachartikel in der Zeitschrift Computer Methods and Programs in Biomedicine, 2026. Verfasst von Chen Liu und 5 weiteren Autor:innen. Beteiligte Einrichtung: School of Biomedical Engineering, Shanghai Jiao Tong University, Shanghai, China. Electronic address: lchen1206@sjtu.edu.cn. Hauptthemen laut MEDLINE: Gestures, Electromyography, Pattern Recognition, Automated, Machine Learning. Die Arbeit nennt 54 Literaturangaben.
Abstract (Originalsprache)
BACKGROUND AND OBJECTIVE: Gesture recognition based on surface electromyography (sEMG) has achieved significant progress in human-machine interaction (HMI), especially in prosthetic control and movement rehabilitation. However, accurately recognizing predefined gestures within a closed set is still inadequate in practice; a robust open-set system needs to effectively reject unknown gestures while correctly classifying known ones, which is rarely explored in the field of myoelectric gesture recognition. METHODS: To handle this challenge, we first report a significant distinction in prediction inconsistency discovered for unknown classes, which arises from perspective differences and can substantially enhance open-set recognition performance. Based on this insight, we propose a novel dual-perspective inconsistency learning approach, PredIN, to explicitly magnify the prediction inconsistency by enhancing the inconsistency of class feature distribution within different perspectives. Specifically, PredIN maximizes the class feature distribution inconsistency among the dual perspectives to enhance their differences. Meanwhile, it optimizes inter-class separability within an individual perspective to maintain individual performance. RESULTS: We evaluate our method on four public benchmark sEMG datasets. Comprehensive experiments demonstrate that the PredIN outperforms state-of-the-art methods by a clear margin. CONCLUSION: Our proposed method simultaneously achieves accurate closed-set classification for predefined gestures and effective rejection for unknown gestures, exhibiting its efficacy and superiority in open-set gesture recognition based on sEMG.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- School of Biomedical Engineering, Shanghai Jiao Tong University, Shanghai, China. Electronic address: lchen1206@sjtu.edu.cn.
- School of Biomedical Engineering, Shanghai Jiao Tong University, Shanghai, China.
- College of Media Engineering, Communication University of Zhejiang, Hangzhou, China.
- School of Biomedical Engineering, Shanghai Jiao Tong University, Shanghai, China. Electronic address: dahong.qian@sjtu.edu.cn.
Zitieren
APA
Liu, C., Han, C., Zhou, C., Wang, Y., Cai, C., & Qian, D. (2026). Towards open-set myoelectric gesture recognition via dual-perspective inconsistency learning. Computer Methods and Programs in Biomedicine. https://doi.org/10.1016/j.cmpb.2026.109258
Vancouver
Liu C, Han C, Zhou C, Wang Y, Cai C, Qian D. Towards open-set myoelectric gesture recognition via dual-perspective inconsistency learning. Computer Methods and Programs in Biomedicine. 2026. doi:10.1016/j.cmpb.2026.109258
BibTeX
@article{Liu2026,
author = {Liu, Chen and Han, Can and Zhou, Chengfeng and Wang, Yaqi and Cai, Crystal and Qian, Dahong},
title = {Towards open-set myoelectric gesture recognition via dual-perspective inconsistency learning},
journal = {Computer Methods and Programs in Biomedicine},
year = {2026},
doi = {10.1016/j.cmpb.2026.109258}
}
EUVIMED