Review of EMG Signal Classification for Diagnosis of Neuromuscular Disorders

Electromyographic (EMG) signal provide a significant source of information for diagnosis, treatment and management of neuromuscular disorders.Neuromuscular diseases changes, the shape and characteristics of the motor unit action potentials (MUAPs). The MUAPs detected from myopathic patients are characterized by high frequency contents, low peak-to-peak amplitude and MUAPs neuropathic patients are poly-phasic, low frequency, high peak-to-peak amplitude than the normal MUAPs. This paper gives a review of different techniques used for decomposition of EMG signal, extraction of time domain and time-frequency domain features of motor unit action potentials (MUAPs) . Different classification strategies including single classifier, multi-classifier fusion classifier trainable and non-trainable are investigated. The performance of Support Vector Machine (SVM), Distance weighted K-nearest neighborhood (DWKNN) classifier and neural network are meticulously studied. The essence of this paper is to review the most recent developments and research studies related to the issues mentioned above. Keywords— Support Vector Machine, EMG; Discrete wavelet Transform; K-nearest neighborhood (KNN).