A Hierarchical Three-Stage Feature Selection Strategy for Efficient and Generalizable sEMG-Based Joint Torque Estimation in Athletic Training and Rehabilitation
Sensors · 2026
DOI: 10.3390/s26185768 ↗Kurz gefasst
Fachartikel in der Zeitschrift Sensors, 2026. Verfasst von Yufeng Zheng und 5 weiteren Autor:innen. Beteiligte Einrichtung: The Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen 518055, China. Hauptthemen laut MEDLINE: Electromyography, Joints. Die Arbeit nennt 42 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Shenzhen Science and Technology Program, Shenzhen Medical Research Fund, National Natural Science Foundation of China.
Abstract (Originalsprache)
Estimating joint torque in athletes provides important information for understanding neuromuscular performance and optimizing high-intensity training. While surface electromyography (sEMG) offers a non-invasive measure of muscle activation, existing methods often struggle to balance prediction accuracy, computational efficiency, and generalizability across different movement conditions. This study proposes a Hierarchical Three-Stage Feature Selection (H3FS) strategy for efficient and stable sEMG-based joint torque estimation. H3FS integrates domain knowledge, statistical and model-driven screening to generate compact, physiologically meaningful feature sets tailored to various application contexts. Using isokinetic movement data from the shoulder, elbow, and knee joints of 39 young athletes, H3FS identified the optimal configuration, ELATE-3, comprising logarithmic mean absolute value (LMAV), waveform length (WL), and Teager–Kaiser energy operator (TKEO). The study also introduces an Integrated Performance Index (IPI) to evaluate prediction accuracy and computational cost. Results indicate that XGBoost with ELATE-3 achieves the best balance between accuracy and real-time performance (average R2 = 0.85, RMSE = 16.2, IPI = 0.013). It outperforms both traditional and data-driven feature sets, demonstrating strong generalization and low latency across joints, making it highly suitable for low-latency estimation on the adopted computational platform. The proposed strategy offers a systematic, scalable solution for joint torque estimation, supporting athletic training optimization and neuromuscular assessment, with potential future applications in rehabilitation monitoring.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- The Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen 518055, China.
- The School of Electronic Engineering and Automation, Guilin University of Electronic Technology, Guilin 541004, China.
- The College of Integrated Circuits, Shenzhen Polytechnic University, Shenzhen 518055, China.
- The Guizhou Institute of Sport Science (Guizhou Anti-Doping Agency), Guiyang 550025, China.
ORCID-Profile: Yufeng Zheng, Pingao Huang, Hongqiang Wang, Yongxue Wang, Chunlong Gan, Hui Wang
Förderung
- Shenzhen Science and Technology Program
- Shenzhen Medical Research Fund
- National Natural Science Foundation of China
Zitieren
APA
Zheng, Y., Huang, P., Wang, H., Wang, Y., Gan, C., & Wang, H. (2026). A Hierarchical Three-Stage Feature Selection Strategy for Efficient and Generalizable sEMG-Based Joint Torque Estimation in Athletic Training and Rehabilitation. Sensors. https://doi.org/10.3390/s26185768
Vancouver
Zheng Y, Huang P, Wang H, Wang Y, Gan C, Wang H. A Hierarchical Three-Stage Feature Selection Strategy for Efficient and Generalizable sEMG-Based Joint Torque Estimation in Athletic Training and Rehabilitation. Sensors. 2026. doi:10.3390/s26185768
BibTeX
@article{Zheng2026,
author = {Zheng, Yufeng and Huang, Pingao and Wang, Hongqiang and Wang, Yongxue and Gan, Chunlong and Wang, Hui},
title = {A Hierarchical Three-Stage Feature Selection Strategy for Efficient and Generalizable sEMG-Based Joint Torque Estimation in Athletic Training and Rehabilitation},
journal = {Sensors},
year = {2026},
doi = {10.3390/s26185768}
}
EUVIMED