Cognitive Validation of BYOD-Supported Traditional Classroom Using Single Channel EEG

Abstract

It is a challenging task to model the cognitive activity of the brain from electroencephalogram (EEG) data to find the learning interaction of the students in Bring Your Own Device (BYOD)-based traditional classroom. This study proposes a novel machine learning-based approach to represent the interaction in terms of EEG signal from a single channel device, and then, the research analyzes the collected data to find the novelty of mobile technology inside the classroom. The EEG signal from the student’s brain is captured, pre-processed, classified, and then analyzed to validate the learning interaction with and without mobile technology. Also, some statistical analysis such as Bayesian paired sample t-test along with some descriptive analysis was conducted to test the correctness of the objective and to support the research. Classroom is validated in terms of learning with and without BYOD-based smart devices by analyzing the attention, meditation, and other EEG states. The study investigates the use of smart technologies inside the traditional classroom by using single channel EEG device. Later, the study recommends the use of mobile technology inside the classroom for the betterment of quality education.