Study on Gesture Recognition Method with Two-Stream Residual Network Fusing sEMG Signals and Acceleration Signals
Sensors · 2024
DOI: 10.3390/s24092702 ↗Kurz gefasst
Fachartikel in der Zeitschrift Sensors, 2024. Verfasst von Zhigang Hu und 4 weiteren Autor:innen. Beteiligte Einrichtung: School of Medical Technology and Engineering, Henan University of Science and Technology, Luoyang 471023, China. Hauptthemen laut MEDLINE: Gestures, Electromyography, Neural Networks, Computer. Die Arbeit wurde bisher 10-mal zitiert (Crossref) und nennt 49 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Henan Province Office of Education.
Abstract (Originalsprache)
Currently, surface EMG signals have a wide range of applications in human–computer interaction systems. However, selecting features for gesture recognition models based on traditional machine learning can be challenging and may not yield satisfactory results. Considering the strong nonlinear generalization ability of neural networks, this paper proposes a two-stream residual network model with an attention mechanism for gesture recognition. One branch processes surface EMG signals, while the other processes hand acceleration signals. Segmented networks are utilized to fully extract the physiological and kinematic features of the hand. To enhance the model’s capacity to learn crucial information, we introduce an attention mechanism after global average pooling. This mechanism strengthens relevant features and weakens irrelevant ones. Finally, the deep features obtained from the two branches of learning are fused to further improve the accuracy of multi-gesture recognition. The experiments conducted on the NinaPro DB2 public dataset resulted in a recognition accuracy of 88.25% for 49 gestures. This demonstrates that our network model can effectively capture gesture features, enhancing accuracy and robustness across various gestures. This approach to multi-source information fusion is expected to provide more accurate and real-time commands for exoskeleton robots and myoelectric prosthetic control systems, thereby enhancing the user experience and the naturalness of robot operation.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- School of Medical Technology and Engineering, Henan University of Science and Technology, Luoyang 471023, China.
- School of Mechanical and Electrical Engineering, Henan University of Science and Technology, Luoyang 471003, China.
Förderung
- Henan Province Office of Education
Zitieren
APA
Hu, Z., Wang, S., Ou, C., Ge, A., & Li, X. (2024). Study on Gesture Recognition Method with Two-Stream Residual Network Fusing sEMG Signals and Acceleration Signals. Sensors. https://doi.org/10.3390/s24092702
Vancouver
Hu Z, Wang S, Ou C, Ge A, Li X. Study on Gesture Recognition Method with Two-Stream Residual Network Fusing sEMG Signals and Acceleration Signals. Sensors. 2024. doi:10.3390/s24092702
BibTeX
@article{Hu2024,
author = {Hu, Zhigang and Wang, Shen and Ou, Cuisi and Ge, Aoru and Li, Xiangpan},
title = {Study on Gesture Recognition Method with Two-Stream Residual Network Fusing sEMG Signals and Acceleration Signals},
journal = {Sensors},
year = {2024},
doi = {10.3390/s24092702}
}
EUVIMED