적응적 수업자료의 개발을 위한 머신러닝의 활용: 학습자의 뇌파를 활용한 인지부하 판별모형 개발

Abstract

The purpose of this study was to develop an artificial intelligence-based model that determines the degree of cognitive load using learner’s neurophysiological data. The participants were two undergraduate students of a flagship university. Their EEG response data were collected during the experimental tasks. Machine learning models including random forest, support vector machine, and artificial neural network techniques were applied for the data. Results showed that the machine learning model that employed artificial neural network technique produced the highest predictive power at 95.17%. In addition, the machine learning model that employed random forest technique showed more than 94% prediction accuracy. The results of the study suggested that the models can be used to develop a personalized adaptive learning system that actively responds by measuring the cognitive load of learners in real time.