CLASSIFICATION OF AMYOTROPHIC LATERAL SCLEROSIS AND HEALTHY ELECTROMYOGRAPHY SIGNALS BASED ON TRANSFER LEARNING

Abstract

This paper investigates the usage of transfer learning in amyotrophic lateralsclerosis (ALS) disease detection. ALS is a dangerous disease which affectsthe nerve cells in brain and spinal cord. Electromyogram (EMG) is animportant measure for analysing of the electrical level of the muscles. EMGbased early ALS disease detection system helps the physicians and patients.The proposed work uses EMG signals in discrimination of the ALS and healthypersons. The EMG signals are initially segmented with a overlapped windowand each segment is converted to the spectrogram images. The obtainedspectrogram images are resized and fed into the pre-trained convolutionalneural networks model. The pre-trained model is fine-tuned with the problemat hand. The R002 dataset which is obtained from www.emglab.net is usedduring the experimental works. Accuracy, sensitivity and specificity measuresare used to evaluate the obtained achievement. According to these measures,97.70% accuracy, 97.97% sensitivity, and 97.29% specificity values arerecorded. We further compare the obtained results with some of the existingresults that were obtained on the same dataset. The comparisons show thatproposed method is outperformed.