A multi-label deep residual shrinkage network for high-density surface electromyography decomposition in real-time

Background The swift and accurate identification of motor unit spike trains (MUSTs) from surface electromyography (sEMG) is essential for enabling real-time control in neural interfaces. However, the existing sEMG decomposition methods, including blind source separation (BSS) and deep learning, have...

Full description

Saved in:

Bibliographic Details
Published in:	Journal of neuroengineering and rehabilitation Vol. 22; no. 1; pp. 106 - 19
Main Authors:	Ma, Jinting, Wang, Lifen, Wu, Renxiang, Zhang, Naiwen, Wei, Jing, Li, Jianjun, Li, Qiuyuan, Tan, Lihai, Li, Guanglin, Jiang, Naifu, Dan, Guo
Format:	Journal Article
Language:	English
Published:	London BioMed Central 08.05.2025 BioMed Central Ltd BMC
Subjects:	Algorithms Biomedical and Life Sciences Biomedical Engineering and Bioengineering Biomedicine Deep Learning Deep residual shrinkage network Electromyography Electromyography - methods High-definition television High-density surface electromyography Humans Machine learning Methods Motor unit spike trains Multi-label learning Muscle, Skeletal - physiology Neural Networks, Computer Neurology Neurophysiology Neurosciences Real-time decomposition Rehabilitation Medicine Signal processing Signal Processing, Computer-Assisted Specific gravity Massachusetts China Motor unit spike trains Multi-label learning Real-time decomposition High-density surface electromyography Deep residual shrinkage network
ISSN:	1743-0003, 1743-0003
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!

Description
Summary:	Background The swift and accurate identification of motor unit spike trains (MUSTs) from surface electromyography (sEMG) is essential for enabling real-time control in neural interfaces. However, the existing sEMG decomposition methods, including blind source separation (BSS) and deep learning, have not yet achieved satisfactory performance, due to high latency or low accuracy. Methods This study introduces a novel real-time high-density sEMG (HD-sEMG) decomposition algorithm named ML-DRSNet, which combines multi-label learning with a deep residual shrinkage network (DRSNet) to improve accuracy and reduce latency. ML-DRSNet was evaluated on a public sEMG dataset and the corresponding MUSTs extracted via the convolutional BSS algorithm. An improved multi-label deep convolutional neural network (ML-DCNN) was also evaluated and compared against a conventional multi-task DCNN (MT-DCNN). These networks were trained and tested on various window sizes and step sizes. Results With the shortest window size (20 data points) and step size (10 data points), ML-DRSNet significantly outperformed both ML-DCNN (0.86 ± 0.18 vs. 0.71 ± 0.24, P < 0.001) and MT-DCNN (0.86 ± 0.18 vs. 0.66 ± 0.16, P < 0.001) in decomposition precision. Moreover, ML-DRSNet demonstrated a notably lower latency (15.15 ms) compared to ML-DCNN (69.36 ms) and MT-DCNN (76.96 ms), both of which demonstrated reduced latency relative to BSS-based decomposition methods. Conclusions The proposed ML-DRSNet and the improved ML-DCNN algorithms substantially enhance both the accuracy and real-time performance in decomposing MUSTs, establishing a technical foundation for neuro-information-driven motor intention recognition and disease assessment.
Bibliography:	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 23
ISSN:	1743-0003 1743-0003
DOI:	10.1186/s12984-025-01639-3