Paper Info
Title
New Channel Merging Methods for Multi-DoF Force Prediction of Finger Contractions
Abstract
Surface electromyography (sEMG) signal is one of the widely applied biological signals in the research field of the force intention prediction. However, due to the severe crosstalk issue of sEMG signals during fine hand contractions, few studies have related sEMG to multiple degree-of-freedom (DoF) force prediction of individual fingers. Accordingly, this pilot study proposed two methodsCommon Spatial Pattern (CSP) and Softmax function to solve the cross-talk issues for the estimation of EMG-force during multiple finger contractions through weighting the significance of each selected channel. High-density sEMG signals of forearm extensor muscles were obtained, and experimental data from two able-bodied subjects were analyzed. Subjects produced 1-DoF and 3-DoF forces up to 30% maximum voluntary contraction (MVC). Then, the root-mean-square values of sEMG were related to joint force. Linear EMG-force models were trained using 1-DoF trials, then tested on 3-DoF trials. Our results showed that the proposed two novel methods had lower RMS errors than the traditional methods for index, and ring with little fingers. The results suggest that 3-DoF control for individual fingers with minimal training procedure (1-DoF trials) may be feasible for practical use.
Year
DOI
Venue
2019
10.1109/BIOCAS.2019.8919012
2019 IEEE Biomedical Circuits and Systems Conference (BioCAS)
Keywords
Field
DocType
Common Spatial Pattern,Softmax function,EMG-force prediction,EMG signal processing
Computer vision,Weighting,Softmax function,Crosstalk,Computer science,Joint force,Communication channel,Electromyography,Artificial intelligence,Merge (version control),Maximum voluntary contraction
Conference
ISSN
ISBN
Citations 
2163-4025
978-1-5090-0618-2
0
PageRank 
References 
Authors
0.34
0
4
Name
Order
Citations
PageRank
Yuyang Chen135.78
Xinyu Jiang288.27
Chenyun Dai387.61
Wei Chen49639.08