EEG-based Confusion Recognition Using Different Machine Learning Methods

Massive Open Online Course (MOOC) has emerged as a key trend. As a way of teaching online, the main shortcoming of MOOC is lacking feedback because there is a distance in both time and space between teachers and students. This study proposes the confusion recognition system based on Electroencephalo...

Full description

Saved in:
Bibliographic Details
Published in2021 2nd International Conference on Artificial Intelligence and Computer Engineering (ICAICE) pp. 826 - 831
Main Authors He, Shuwei, Xu, Yanran, Zhong, Lanyi
Format Conference Proceeding
LanguageEnglish
Published IEEE 01.11.2021
Subjects
Brain-computer interface (BCI)
Classification
Computer aided instruction
Deep learning
Education
EEG
Electroencephalography
Electronic learning
Emotion recognition
LSTM
Machine learning
Random forests
Online AccessGet full text

Cover

More Information
Summary:Massive Open Online Course (MOOC) has emerged as a key trend. As a way of teaching online, the main shortcoming of MOOC is lacking feedback because there is a distance in both time and space between teachers and students. This study proposes the confusion recognition system based on Electroencephalography(EEG). We apply machine learning methods, including Naive Bayes, KNN, Random Forest, XGBoost, and also a deep learning method, LSTM, on the EEG data set respectively to detect whether a student feel confused. We find that LSTM shows better performance than any machine learning methods we use. The average accuracy of LSTM classifier is 78.1%. This study shows the significance of detecting confusion through EEG and helping students in improving learning efficiency.
DOI:10.1109/ICAICE54393.2021.00160