Discrete wavelet transform and k-nn classification in EMG signals for diagnosis of neuromuscular disorders

Electromyography (EMG) is a technique for evaluating and recording the electrical activity produced by skeletal muscles, during voluntary or involuntary muscle activities. An electromyography detects the electrical potential generated by muscle cells when these cells are electrically or neurologically activated. The signals can be analyzed to detect medical abnormalities in the muscles. The EMG signal is a complicated biomedical signal due to anatomical/physiological properties of the muscles and its noisy environment. An accurate and computationally efficient means of classifying electromyographic (EMG) signal patterns has been the subject of considerable research effort in recent years. The analysis of EMG signals provides an important source of information for the diagnosis of neuromuscular disorders. Different methodologies in the time domain and frequency domain have been followed for the analysis of EMG signals. In this study, the usefulness of the Discrete Wavelet Transform, besides, statistical features are presented for the classification of intramuscular EMG signals. The proposed method automatically classifies the EMG signals into normal, Amyotrophic lateral sclerosis, or myopathy. The k-nn classifier is used to give the recognition result. The experimental results show the high accuracy of the proposed method.