A Lightweight Frozen Multi-Convolution Dual-Branch Network for Efficient sEMG-Based Gesture Recognition
Sensors · 2026
DOI: 10.3390/s26020580 ↗Kurz gefasst
Fachartikel in der Zeitschrift Sensors, 2026. Verfasst von Shengbiao Wu und 5 weiteren Autor:innen. Beteiligte Einrichtung: School of Electronics and Electrical Engineering, East China University of Technology, Nanchang 330013, China. Hauptthemen laut MEDLINE: Electromyography, Gestures. Die Arbeit nennt 49 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, Jiangxi Provincial Major Science and Technology Research and Development Foundation.
Abstract (Originalsprache)
Gesture recognition is important for rehabilitation assistance and intelligent prosthetic control. However, surface electromyography (sEMG) signals exhibit strong non-stationarity, and conventional deep-learning models require long training time and high computational cost, limiting their use on resource-constrained devices. This study proposes a Frozen Multi-Convolution Dual-Branch Network (FMC-DBNet) to address these challenges. The model employs randomly initialized and fixed convolutional kernels for training-free multi-scale feature extraction, substantially reducing computational overhead. A dual-branch architecture is adopted to capture complementary temporal and physiological patterns from raw sEMG signals and intrinsic mode functions (IMFs) obtained through variational mode decomposition (VMD). In addition, positive-proportion (PPV) and global-average-pooling (GAP) statistics enhance lightweight multi-resolution representation. Experiments on the Ninapro DB1 dataset show that FMC-DBNet achieves an average accuracy of 96.4% ± 1.9% across 27 subjects and reduces training time by approximately 90% compared with a conventional trainable CNN baseline. These results demonstrate that frozen random-convolution structures provide an efficient and robust alternative to fully trained deep networks, offering a promising solution for low-power and computationally efficient sEMG gesture recognition.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- School of Electronics and Electrical Engineering, East China University of Technology, Nanchang 330013, China.
- Jiangxi Industry Technology Research Institute of Rehabilitation Assistance, Nanchang 330013, China.
Förderung
- National Natural Science Foundation of China
- Jiangxi Provincial Major Science and Technology Research and Development Foundation
Zitieren
APA
Wu, S., Lv, Z., Li, Y., Fang, C., You, T., & Gui, J. (2026). A Lightweight Frozen Multi-Convolution Dual-Branch Network for Efficient sEMG-Based Gesture Recognition. Sensors. https://doi.org/10.3390/s26020580
Vancouver
Wu S, Lv Z, Li Y, Fang C, You T, Gui J. A Lightweight Frozen Multi-Convolution Dual-Branch Network for Efficient sEMG-Based Gesture Recognition. Sensors. 2026. doi:10.3390/s26020580
BibTeX
@article{Wu2026,
author = {Wu, Shengbiao and Lv, Zhezhe and Li, Yuehong and Fang, Chengmin and You, Tao and Gui, Jiazheng},
title = {A Lightweight Frozen Multi-Convolution Dual-Branch Network for Efficient sEMG-Based Gesture Recognition},
journal = {Sensors},
year = {2026},
doi = {10.3390/s26020580}
}
EUVIMED