An EEG Signals based model for student attention prediction in Online Education System

The COVID-19 pandemic promotes online learning. However, a significant challenge with online education is assessing and maintaining student attention, which are critical for effective learning. The electroencephalography (EEG) signals and Support Vector Machine (SVM) are used to predict and monitor student attention during online educational videos. Numerous researchers have used the benchmark EEG dataset to explore this problem in the literature and provide real-time feedback on student attention to instructors. However, there is still a research need to enhance the performance of the models that are already available in the literature. Therefore, to address this research gap, we have proposed an efficient model which optimizes SVM to address this problem. Our proposed model results demonstrate that EEG-based attention classifier achieves high accuracy compared to the other contemporary models.