Hybrid feature selection for myoelectric signal classification using MICA

Publication Type:
Journal Article
Journal of Electrical Engineering, 2010, 61 (2), pp. 93 - 99
Issue Date:
Filename Description Size
Thumbnail2012007334OK.pdf814.17 kB
Adobe PDF
Full metadata record
This paper presents a novel method to enhance the performance of Independent Component Analysis (ICA) of myoelectric signal by decomposing the signal into components originating from different muscles. First, we use Multi run ICA (MICA) algorithm to separate the muscle activities. Pattern classification of the separated signal is performed in the second step with a back propagation neural network. The focus of this work is to establish a simple, yet robust system that can be used to identify subtle complex hand actions and gestures for control of prosthesis and other computer assisted devices. Testing was conducted using several single shot experiments conducted with five subjects. The results indicate that the system is able to classify four different wrist actions with near 100 % accuracy. © 2010 FEI STU.
Please use this identifier to cite or link to this item: