IoT-Based Monitoring of Students’ Brain Activity Using an Ensemble Method in E-Learning Classes

Perceiving the attentiveness of students in online classes has become critical after the pandemic situation due to a larger number of students involved in a single class, which becomes complex in improving the education quality in online mode. However, each student's participation has a different degree of proficiency, but the main goal of the online education is to improve their standard of teaching methodology. Hence, this research study introduced the Internet of Things (IoT) based online platform and evaluated the engagement level of students through online lessons. These technologies empower devices physically embedded for connecting to the internet are integrated extensively into human action by supporting several activities. In real time, Peripheral neurophysiological signals are less responsive to changes in affective states than the Electroencephalogram (EEG) signal. Thus, the student’s brain activity during online classes has been monitored through various frequencies of the brain obtained from Electroencephalography (EEG) devices. Moreover, the Machine Learning (ML) method with lazy predict classification library through an ensemble predictive system by soft voting concept for assisting the staff to identify student attitude in listening the online classes and justify the student’s potential in their academic. Thus, the proposed ensemble ML prediction system with IoT-based EEG has helped in determining the exact prediction of students’ brain activity for providing them a set of interesting classes from the online teaching staff.