Physical Action Categorization using Signal Analysis and Machine Learning
This work addresses assistive technology needs for individuals with limb movement disabilities by improving action classification, though it appears incremental with standard methods applied to sEMG data.
The paper tackles physical action classification from surface electromyography signals by developing a machine learning framework that extracts features from multiple domains and compares classifiers, achieving 95.21% accuracy with SVM and 95.83% with 1-NN on a subset of features.
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 signals for classification and use in applications. In this paper, we propose a machine learning based framework for classification of 4 physical actions. The framework looks into the various features from different modalities which contribution from time domain, frequency domain, higher order statistics and inter channel statistics. Next, we conducted a comparative analysis of k-NN, SVM and ELM classifier using the feature set. Effect of different combinations of feature set has also been recorded. Finally, the classifier accuracy with SVM and 1-NN based classifier for a subset of features gives an accuracy of 95.21 and 95.83 respectively. Additionally, we have also proposed that dimensionality reduction by use of PCA leads to only a minor drop of less than 5.55% in accuracy while using only 9.22% of the original feature set. These finding are useful for algorithm designer to choose the best approach keeping in mind the resources available for execution of algorithm.