Eeg Based Brain Computer Interface BCI Deep Learning Model For e Learning Knowledge Tracing and Recommendations

Abstract

The COVID19 pandemic has accelerated the proliferation of online e learning platforms, offering a diverse array of subjects to learners of all ages. Despite this rapid growth, a significant number of these platforms still lack a learner centric approach and often fall short in effectively validating user learning progress. The current scenario highlights the importance of implementing effective e learning monitoring systems and individualized guidance for e learning materials. This doctoral dissertation tackles these significant issues by employing a pioneering methodology that leverages live electroencephalogram EEG data obtained from individuals who utilize EEG headsets during their participation in Massive Open Online Courses MOOCs. These EEG data are subject to categorization through sophisticated deep learning architectures, such as Convolutional Neural Networks CNN and Long Short Term Memory LSTM networks, with the primary objective of evaluating the effectiveness of the learning experience. newlineThe advent of the COVID19 pandemic has ushered in an unprecedented era of online learning platforms. These platforms offer a diverse range of subjects and cater to learners of all ages, providing unprecedented access to educational resources. However, this rapid growth in e learning platforms has also revealed some critical limitations. A significant proportion of these platforms often fail to adopt a learner centric approach and, more importantly, lack effective mechanisms to validate user learning progress. This deficiency has highlighted the pressing need for innovative solutions that can enhance e learning validation and provide personalized learning recommendations. To address mentioned challenges, this PhD thesis introduces a pioneering approach based on the collection of EEG signals collected in real time from subjects who wear EEG headsets during attending e learning sessions. EEG signals, as direct indicators of brain activity, offer a unique window into the cognitive processes underlying learning.