Machine Learning and Signal Processing Based Analysis of EMG Signals for Daily Action Classification

Abstract

Daily life of thousands of individuals around the globe suffers due to physical or mental disability related to limb movement. The quality of life for such individuals can be made better by use of assistive applications and systems. In such scenario, mapping of physical actions from movement to a computer aided application can lead the way for solution. Surface Electromyography (sEMG) presents a non-invasive mechanism through which we can translate the physical movement to signalsfor classification and use in applications. Keeping this in view, this study propose a machine learning based framework for classification of 20 physical actions. The framework looks into the various features from different modalities which contribution from time domain, frequency domain and inter channel statistics. Next, we conducted a comparative analysis of k-NN and SVM classifier using the feature set for multiple normal and aggressive activities. Effect of different combinations of feature set has also been recorded. Finally, the SVM classifier gives an accuracy of 100% for 10 normal actions and 1- NN for a subset of features gives an accuracy of 98.91% for 10 aggressive actions respectively. Additionally, we use both SVM and 1-NN to propose a hybrid approach to classify 20 physical actions. The hybrid classifier gives an accuracy of 98.97% respectively. These finding are useful for algorithm designer to choose the best approach keeping in mind the resources available for execution of an algorithm.