Classification of Myopathy and Normal Electromyogram (EMG) Data with a New Deep Learning Architecture

Electromyograms (EMG) are recorded movements of nerves and muscles that help diagnose nerve-related disorders. It is frequently used in the diagnosis neuromuscular diseases such as myopathy, which causes many changes EMG signal properties. The most useful auxiliary test myopathy EMG. Therefore, it has become imperative to identify computer-assisted anomalies with full accuracy develop an efficient classifier. In this study, a new machine learning method deep architecture can score normal from EMGLAB database proposed. Using discrete wavelet transform Coiflets 5 (Coif 5) wavelet, signals decomposed into subbands various statistical features obtained coefficients. success rates decision tree C4.5 algorithm, one traditional architectures, Long Short-term Memory (LSTM) were compared. Unlike studies literature, LSTM 100% rate was achieved proposed model. addition, real-time approach presented by analyzing data classification time