Wavelet domain feature extraction scheme based on dominant motor unit action potential of EMG signal for neuromuscular disease classification.

In this paper, two schemes for neuromuscular disease classification from electromyography (EMG) signals are proposed based on discrete wavelet transform (DWT) features. In the first scheme, a few high energy DWT coefficients along with the maximum value are extracted in a frame by frame manner from the given EMG data. Instead of considering only such local information obtained from a single frame, we propose to utilize global statistics which is obtained based on information collected from some consecutive frames. In the second scheme, motor unit action potentials (MUAPs) are first extracted from the EMG data via template matching based decomposition technique. It is well known that not all MUAPs obtained via decomposition are capable of uniquely representing a class. Thus, a novel idea of selecting a dominant MUAP, based on energy criterion, is proposed and instead of all MUAPs, only the dominant MUAP is used for the classification. A feature extraction scheme based on some statistical properties of the DWT coefficients of dominant MUAPs is proposed. For the purpose of classification, the K-nearest neighborhood (KNN) classifier is employed. Extensive analysis is performed on clinical EMG database for the classification of neuromuscular diseases and it is found that the proposed methods provide a very satisfactory performance in terms of specificity, sensitivity, and overall classification accuracy.