| Summary: | Amyotrophic Lateral Sclerosis (ALS) and Myopathy are the most well-known neuromuscular diseases. Electromyography (EMG) signal is hugely used in the diagnosis of these neuromuscular disorders. The study presented in this paper aims to develop a Computer-Aider-Diagnosis (CAD) system to identify ALS and Myopathic patients from Normal subjects through the EMG signal. The system employs the Mel Frequency Cepstral Coefficients (MFCC) as a feature extraction technique to produce discriminant features. Then, the MFCC vectors dimension is reduced using statistical values. Since features constitute a crucial factor in characterizing several phenomena and reaching good performances by CAD systems, the Relief feature selection algorithm was applied to the previously obtained outputs to select the most meaningful and significant attributes. The main contribution of this work is to build a robust model for the classification of EMG signals to identify the previously mentioned neuromuscular disorders. Hence, the last stage of the proposed scheme deals with machine learning classification algorithms. Support Vector Machine (SVM) and k-Nearest Neighbors (k-NN) were chosen in this work. Experimental results showed that k-NN with two nearest neighbors (k=2) and the 10-folds cross-validation method yielded higher classification results than SVM. According to the accuracy, sensitivity, specificity, and F-measure evaluation metrics, the classifiers' performances were evaluated. In Normal-ALS and Normal-Myopathy binary issues, we obtained 99.34% and 99.07% accuracy, respectively. The proposed system performed well also in a multi-class task with a classification accuracy of 98.69%.
|
|---|
