A Comparative Examination of Bagging Techniques for EEG-Based Hand Gesture Classification
N Priyadharshini Jayadurga, M. Chandralekha, Kashif Saleem · 2024
This study delves into the transformative potential of EEG-based hand gesture recognition for enhancing human-computer interaction. Through sophisticated classification techniques, specifically ensemble methods, EEG signals are analyzed to accurately identify hand gestures. The research highlights the Bagged SVM classifier’s remarkable efficiency, reaching an accuracy rate of 96.8%. This achievement emphasizes the practicality and reliability of EEG signals for creating intuitive user interfaces, with promising applications in virtual reality and assistive technology. By effectively linking neural signals to computational interpretations, the study marks a significant leap in neurotechnology and human-computer interfaces, setting new standards for future research and development in EEG-based gesture recognition systems.