Artificial neural net algorithms in classifying electromyographic signals
Christos N. Schizas, Constantinos S. Pattichis, Ian S. Schofield, Peter R.W. Fawcett, Lefkos T. Middleton · International Conference on Artificial Neural Networks · 1989
Examines how artificial neural nets (ANN) can be used as a computerized method for electromyographic diagnosis. For this reason, a number of well defined neuromuscular disorders have been selected: the Becker's muscular dystrophy; the spinal muscular atrophy; and the motor neuron disease. In this study the macro motor unit potential shape descriptors form continuous valued inputs, which are used to excite a multilayer perceptron net. Learning is carried out under supervision by providing to the net the desired output. >