ANALYSIS AND PROCESSING OF ELECTROMYOGRAM SIGNALS

K. A. Zimenko, A. S. Borgul, A. A. Margun


Read the full article 

Abstract

A method of electromyogram signals processing and identification for implementation in rehabilitation devices control is given. The method is based on the high-frequency components filtration which improves the signal/noise ratio; also it is based on the wavelet analysis for signal preprocessing and motion type classification by taught artificial neural network. Obtained accuracy of motion type classification is 94%.


Keywords: electromyogram, neural network, signal processing, wavelet transform
Copyright 2001-2017 ©
Scientific and Technical Journal
of Information Technologies, Mechanics and Optics.
All rights reserved.

Яндекс.Метрика