EEG based confused mental state detection and analysis

The state of confusion while learning can reduce the performance of students in their studies. Monitoring the engagement of students in online courses is a tedious job. This paper aims to detect the state of confusion state among students watching MOOC videos based on EEG signals. EEG (Electroencephalography) signals are the brain’s electrical signals that can be used to detect activities like engagement, happiness, stress and many other emotions. Machine learning is an easy and efficient method to deal with complex EEG data and analyze it. The dataset used is a combination of two datasets from Kaggle. The first one is EEG data recorded from 10 students and the other consists of demographic information of the students. Various machine learning algorithms such as gradient boosting, decision tree, random forest, KNN and Naïve Bayes are used to classify the data as confused or not confused. Random forest classifiers proved to be the best algorithms for classification from the comparative analysis of all the implemented algorithms with an accuracy of 96%.