Paper Info
Title
Evaluation of decomposition parameters for high-density surface electromyogram using fast independent component analysis algorithm
Abstract
The surface electromyogram (sEMG) signal reveals the electrical neuromuscular activities and offers theoretical and clinical information. Recently, exploring motoneuron discharge events at the microscopic level through decomposition has been proposed as a promising analysis approach, which can surpass traditional global sEMG-based analysis method in some aspects. However, computational efficiency is an essential issue when discharge events of individual motor unit are decomposed using blind source separation algorithms. Therefore, choosing proper parameters of decomposition algorithms for different research purposes is important. Accordingly, we have systematically investigated the influences between computation time and decomposition performance for fast independent component analysis (FastICA)-based sEMG decomposition algorithm under different value selections of five decomposition parameters, namely the percentage of eliminated channels, extension factor, the number of decomposition iteration loops, the number of maximum inner loops in each iteration and sampling frequency. We employed high-density sEMG signals from 14 intact subjects during muscle contractions of four-digit extension and flexion at different force levels (20% and 50% maximum voluntary contraction) and a public dataset for sEMG decomposition. According to obtained results, we offer four preference suggestions (less computation time, more motor units, higher accuracy and trade-off). Results show that the trade-off values with consideration of decomposition performance and computation time are recommended as 25% of channels with minimal root mean square, extension factor of 4, 200 iteration loop numbers of decomposition, 20 maximum inner loop numbers and 2048 sampling frequency. Overall, this paper provides a guide for researchers to determine proper decomposition parameters for sEMG decomposition-related works.
Year
DOI
Venue
2022
10.1016/j.bspc.2022.103615
Biomedical Signal Processing and Control
Keywords
DocType
Volume
Biosignal processing,Surface electromyogram (sEMG),sEMG decomposition,Blind source separation,Independent component analysis
Journal
75
ISSN
Citations 
PageRank 
1746-8094
0
0.34
References 
Authors
0
7
Name
Order
Citations
PageRank
Long Meng100.34
Qiong Chen200.34
Xinyu Jiang388.27
Xiangyu Liu432.73
Jiahao Fan553.13
Chenyun Dai687.61
Wei Chen79639.08