Comparison of Methods for Electromyography Diagnosis using Time Domain Features

V.K. Jain, G. Kaur, and A.S. Arora (India)


Electromyography, motor unit action potentials, artificial neural network, support vector machine.


Electromyographic examination studies the electrical activity of the muscles and forms a valuable neurophysiological test for the assessment of neuromuscular disorders. The shapes and firing rates of motor unit action potentials (MUAPs) in an electromyogram (EMG) signal provide an important source of information for the diagnosis of neuromuscular disorders. In order to extract this information from the EMG signals recorded at low to moderate force levels, we examined the performance of Artificial Neural Network (ANN) and Binary Support Vector Machine (BSVM) classifier by using time domain parameters. Our results show that BSVM outer performed ANN. The classification accuracy of ANN and BSVM was 66.72% and 75.06% respectively.

Important Links:

Go Back