سال انتشار: ۱۳۸۶

محل انتشار: چهاردهمین کنفرانس مهندسی پزشکی ایران

تعداد صفحات: ۶

نویسنده(ها):

Mohammadreza Asghari Oskoei – Department of Computing and Electronic Systems University of Essex Wivenhoe Park, Colchester CO4 3SQ, U.K.
Huosheng Hu – Department of Computing and Electronic Systems University of Essex Wivenhoe Park, Colchester CO4 3SQ, U.K.

چکیده:

This paper evaluates the Support Vector Machine (SVM) applied to upper limb motion classification using myoelectric signals. The main purpose of this paper is to compare SVM-based classifiers with LDA and MLP. SVM demonstrates exceptional classification accuracy and results in a
robust way of limb motion classification with low computational cost. The validity of entropy, as an index to measure correctness of classification, is also examined. Experimental results show that entropy is a reliable measure for online training in myoelectric control systems.