ALS Detection Framework Based on Automatic Singular Spectrum Analysis and Quantum Convolutional Neural Network From EMG Signals

Abstract

Electromyogram (EMG) signals are recordings of the electrical activity in muscles, which are studied due to their informative nature regarding neuromuscular disorders. Analysis of EMG signals is invaluable for identifying various neuromuscular conditions. In this letter, an automatic singular spectrum analysis (Auto-SSA) and quantum convolutional neural network (QCNN)-based framework is proposed for the detection of amyotrophic lateral sclerosis (ALS) using EMG signals. The Auto-SSA effectively decomposes the EMG signals into reconstructed components, from which the particle swarm optimization extracts the most significant features. The QCNN classifies the extracted features for efficient ALS detection. The proposed framework outperforms the compared state-of-the-art ALS detection frameworks, achieving a testing accuracy of 98.50%. With the obtained performance, the proposed framework could be a valuable diagnostic tool for ALS neuromuscular conditions.