ResEMGNet: A Lightweight Residual Deep Learning Architecture for Neuromuscular Disorder Detection from Raw EMG Signals

TL;DR

ResEMGNet is a lightweight deep learning model that directly classifies raw EMG signals to detect neuromuscular disorders like ALS and Myopathy with high accuracy, eliminating the need for feature extraction.

Contribution

The paper introduces ResEMGNet, a novel residual CNN architecture that classifies raw EMG signals for neuromuscular disorder detection, simplifying the diagnostic process.

Findings

Achieved 94.43% three-class accuracy on subject-independent data.

Outperformed traditional feature-based methods in classification accuracy.

Reduced computational complexity by eliminating handcrafted feature extraction.

Abstract

Amyotrophic Lateral Sclerosis (ALS) and Myopathy are debilitating neuromuscular disorders that demand accurate and efficient diagnostic approaches. In this study, we harness the power of deep learning techniques to detect ALS and Myopathy. Convolutional Neural Networks (CNNs) have emerged as powerful tools in this context. We present ResEMGNet, designed to identify ALS and Myopathy directly from raw electromyography (EMG) signals. Unlike traditional methods that require intricate handcrafted feature extraction, ResEMGNet takes raw EMG data as input, reducing computational complexity and enhancing practicality. Our approach was rigorously evaluated using various metrics in comparison to existing methods. ResEMGNet exhibited exceptional subject-independent performance, achieving an impressive overall three-class accuracy of 94.43\%.