Spatio-temporal graph attention network for rehabilitation movement classification
Medical & Biological Engineering & Computing · 2026-07 · 64 (7) · 2435-2451
DOI: 10.1007/s11517-026-03599-9 ↗Kurz gefasst
Fachartikel in der Zeitschrift Medical & Biological Engineering & Computing, online erschienen am 25.05.2026. Verfasst von Qiyu Yang und 3 weiteren Autor:innen. Beteiligte Einrichtung: School of Automation, Guangdong University of Technology, Guangzhou, China. Hauptthemen laut MEDLINE: Rehabilitation. Die Arbeit nennt 43 Literaturangaben.
Abstract (Originalsprache)
The automated assessment of home-based rehabilitation benefits from skeleton-based methods, which provide a robust and privacy-preserving means of monitoring patient movements. While such approaches effectively capture local body pose and spatial joint configurations, they often fall short in modeling the complete temporal coherence of an entire exercise sequence. To address this limitation, we construct a novel cascaded framework that combines a Spatio-Temporal Graph Convolutional Network (ST-GCN) for capturing local joint dynamics with a Transformer-based attention mechanism to model global, long-range dependencies. Evaluated on the UI-PRMD and KIMORE datasets under a rigorous 5-fold cross-validation protocol with independent test sets, STGA-Net achieved mean accuracies of 92.71% and 95.24%, respectively, surpassing existing state-of-the-art methods. These results demonstrate its strong potential as a quantitative and privacy-preserving tool for personalized rehabilitation assessment in both clinical and home settings.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- School of Automation, Guangdong University of Technology, Guangzhou, China.
- School of Physical Education, Guangdong University of Technology, Guangzhou, China. Huangyi@gdut.edu.cn.
- Sun Yat-sen Memorial Hospital, Sun Yat-sen University, Guangzhou, China. yangzhengfei@vip.163.com.
Zitieren
APA
Yang, Q., Zhang, Z., Huang, Y., & Yang, Z. (2026). Spatio-temporal graph attention network for rehabilitation movement classification. Medical & Biological Engineering & Computing, 64(7), 2435-2451. https://doi.org/10.1007/s11517-026-03599-9
Vancouver
Yang Q, Zhang Z, Huang Y, Yang Z. Spatio-temporal graph attention network for rehabilitation movement classification. Medical & Biological Engineering & Computing. 2026;64(7):2435-2451. doi:10.1007/s11517-026-03599-9
BibTeX
@article{Yang2026,
author = {Yang, Qiyu and Zhang, Zehui and Huang, Yi and Yang, Zhengfei},
title = {Spatio-temporal graph attention network for rehabilitation movement classification},
journal = {Medical & Biological Engineering & Computing},
year = {2026},
volume = {64},
number = {7},
pages = {2435--2451},
doi = {10.1007/s11517-026-03599-9}
}
EUVIMED