Myoelectric Signal Classification Using Neural Networks

Abstract

A feed-forward neural network is used for diagnosis of spastic paralysis. It is a two-layer perceptron and it is able to classify two kinds of myoelectric signal recorded in surface electromyography: the normal EMG and the EMG in the case of spastic paralysis. The myoelectric signal was recorded with a surface electrode pair and sampled at 10 kHz. The EMG activity is stochastic and the instantaneous amplitude distribution for a fixed level of contraction is Gaussian. The signal variance is considered a measure of muscle force. We can describe any kind of this process by the AR model. For a precisely modeling of EMG there are necessary many AR model parameters. In the classification problem we have it is not necessary to use a high order AR model. We find a 4-th order AR model is good enough for this study. The Hopfield algorithm is used to calculate the parameters of the autoregressive model.