Fast automatic detection of amyotrophic lateral sclerosis disease based on Euclidean distance metric

Abstract

This paper proposes an efficient method for the fast detection of amyotrophic lateral sclerosis (ALS) disease. Electromyography (EMG) signal is the most often used in the processing of neuromuscular disorders such as ALS and myopathy. EMG provides helpful information which can be extracted using different advanced signal processing tools. In this work, discrete wavelet transform (DWT) is used for the feature extraction. Our challenge is not only to detect ALS but also to reduce the computing time of automated system of neuromuscular disorder. To achieve our goals a new combined method is involved to quickly diagnosis the ALS based on the Euclidean distance (ED) metric and DWT method. Two Euclidean distance metrics are calculated, namely absolute Euclidean distance (AED) and relative Euclidean distance (RED). These two metrics gave excellent results and made a quick and correct decision in the identification of EMG signals.