A3 Refereed book chapter or chapter in a compilation book
Surface EMG-based gesture recognition using wavelet transform and ensemble learning
Authors: Subasi, Abdulhamit; Qaisar, Saeed Mian
Editors: Subasi, Abdulhamit; Qaisar, Saeed Mian, Nisar, Humaira
Publisher: Elsevier
Publication year: 2025
Book title : Artificial Intelligence and Multimodal Signal Processing in Human-Machine Interaction
Journal name in source: Artificial Intelligence and Multimodal Signal Processing in Human-Machine Interaction
Series title: Artificial Intelligence Applications in Healthcare and Medicine
First page : 263
Last page: 282
ISBN: 978-0-443-29150-0
eISBN: 978-0-443-29151-7
DOI: https://doi.org/10.1016/B978-0-443-29150-0.00013-5
Web address : https://doi.org/10.1016/B978-0-443-29150-0.00013-5
There are several uses for surface electromyography (sEMG), but one crucial application is in human-machine interaction (HMI). HMI systems can benefit from the integration of the sEMG to provide more flexible and responsive user interfaces. By adjusting their muscular activity, users can operate machines, computers, virtual reality platforms, and other electronic devices, providing an alternative to conventional input methods. The hands are essential for gripping and working with various objects. Human activity is impacted when even one hand is lost. For the subjects who lost their hands, a prosthetic hand is an enticing remedy in this regard. When designing prosthetic hands for industrial and assistive uses, the sEMG is a crucial component. By combining many classifier models in a weighted manner, the ensemble classifiers outperform other methods. Therefore utilizing sEMG signals that were captured during the grabbing actions with different objects for each of the six hand motions, the viability of the bagging and boosting ensemble classifiers is evaluated for the fundamental hand movement recognition in this research. There are three stages in the suggested procedure. Denoising is done using the Multiscale Principal Component Analysis (MSPCA) in the first stage. The second stage involves extracting features from the sEMG signals using a novel feature extraction technique called the Tunable Q-factor wavelet transform (TQWT), after which the statistical values of the TQWT subbands are mined to attain a dimension reduction. The final stage involves feeding the acquired feature set into an ensemble classifier to identify the desired hand movements. Different performance indicators are used to compare the Random Subspace and Rotation Forest algorithm-based ensemble classifiers’ performances. A 98.9% classification accuracy is obtained by using the TQWT-derived features in conjunction with the Rotation Forest plus SVM/Random Forest/REP Tree/LDA Tree. As a result, the findings indicate that the suggested approach is a strong contender for the realization of modern HMI systems.
