In this paper, we designed an experiment to observe changes for
different fatigue level in human brain when watching random dot
stereogram (RDS) using the method of EEG. The subjects were
asked to watch 3D content for 30 minutes and the disparity of RDS
changed every 10 seconds. During this watching task, subjects
should rate their extent of fatigue during the experiment on the
scale of one to five only when they felt worse or better. 30 channels
electroencephalogram (EEG) signals were recorded through the
experiment. Finally, the relationship between various fatigue levels
and disparities which revealed by EEG signals were investigated.
Our results show that the power of waveband, namely alpha
increased with the fatigue level increasing from one to four during
watching RDS, but decreased in level five. We have employed
logistic regression to model fatigue level and achieved classification
accuracy of 94.18%. Our research has important implications for
the continuous monitoring of user's fatigue in the future.