Automatic Mental Fatigue Detection in Real-Scene Classroom Learning

This work analyzed students’ mental fatigue states in real classroom situation by using machine learning method. First, we acquired electrocardiogram (ECG) data from 45 college students during their classes of circuit analysis and calculated the peaks of two consecutive R waves (RR) from the ECG data. Second, RR interval features, which revealed the autonomic nervous activities, were extracted from the samples, and critical feature subsets highly influenced by mental fatigue were selected through forward feature selection. Third, we constructed the binary classification model for the recognition of mental fatigue and non-fatigue states. The model achieved 63.16% F1 score on the validation data set independent of the model training and feature selection. The results show that it is feasible to monitor students’ classroom-learning fatigue through machine learning method.