A study of back-propagation and radial basis neural network on EMG signal classification

Neural networks are ubiquitous tool for classification. This paper presents a study of classifying EMG signal patterns using back-propagation and radial basis neural networks. Since the pattern of the EMG signal elicited may differ depending on the activity of the muscle movement. Therefore, the purpose of this study was to demonstrate the effectiveness of the neural networks on discriminating the patterns of certain activities to their respective category. Experiments were carried out on a selected muscle. Five subjects were asked to perform several series of voluntary movement with the respect to the muscle concerned. From the EMG data obtained, four statistical features are computed and are applied to the networks. Comparison is made based on the elements of the networks and the classification rate achieved. Generally, both networks are well performed in discriminating different EMG signal patterns with the successful rate of 88% and 89.33% respectively.