Title: A comparison of ICA algorithms in surface EMG signal processing

Authors: Ganesh R. Naik

Addresses: School of Electrical and Computer Engineering, RMIT University, GP.O. Box 2476V. Melbourne, Victoria, 3001, Australia

Abstract: Recent research has resulted in development of number of different Independent Component Analysis (ICA) technique. While there are some researchers who have compared their techniques with the existing methods for audio examples, there is no comparison of performance between ICA algorithms for biosignal applications. With ICA being the feasible method for source separation and decomposition of biosignals, it is important to compare the different techniques and determine the most suitable method for the applications. This paper presents the performance of five ICA algorithms (SOBI, TDSEP, FastICA, JADE and Infomax) for decomposition of surface electromyogram (sEMG) to identify subtle wrist actions.

Keywords: BSS; blind source separation; ICA; independent component analysis; sEMG; surface electromyograms; MES; myoelectric signals; source separation; EMG signal processing; biosignals; wrist actions.

DOI: 10.1504/IJBET.2011.041774

International Journal of Biomedical Engineering and Technology, 2011 Vol.6 No.4, pp.363 - 374

Published online: 21 Jan 2015 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article