Classification Of Surface EMG Signals Through Machine Learning

Abstract

The Classification Of Surface EMG Signals Through Machine Learning project aims to develop an accurate and efficient system for the classification of surface electromyography (EMG) signals to validate the treatment of chiropractic interventions and spinal manipulations for lower back pain. Surface EMG is widely used in clinical environments to diagnose and monitor neuromuscular disorders, such as muscular dystrophy and neuropathy. Various machine learning techniques, including Long-Short Term Memory (LSTM), Light Gradient Boosting Machine (LGBM), Extreme Gradient Boosting (XGBoost), and Adaptive Boosting (AdaBoost), are utilized in the proposed system to classify surface EMG signals based on their patterns and features. The project involves preprocessing the surface EMG signals to remove noise and artifacts, feature extraction using empirical mode decomposition (EMD) and wavelet decomposition, and classification using the selected machine learning algorithms. The system’s performance is evaluated based on several metrics, such as accuracy, F1-score, precision, recall, ROC curve, sensitivity, and specificity. The results show that the proposed system achieved accuracy in classifying surface EMG signals, which indicates its potential to aid in the diagnosis and treatment of pain management of lower back muscle.