Neural network-based classification of electromyographic (EMG) signal during dynamic muscle contraction

Abstract

A neural-network-based decision making tool was developed for online classification of various neuromuscular diseases. The problem was to design an automatic classification system based on signal processing techniques such as autoregressive modeling, the short-time Fourier transform, the Wigner-Ville distribution, and chaos analysis, by defining the region of normal, and various abnormalities such as neuropathy and myopathy. Using any one method, the probability density function of the features of the various patient groups often overlap and were difficult to classify based on the features of a single method. It was therefore necessary to develop a tool which would use all the quantitative features from each signal processing method and combine the human expertise to provide an expert decision to classify different pathologies. An attempt has been made to solve this problem using an artificial neural network. The results are discussed.<>