EEG-based mental fatigue detection by spectral non-negative matrix factorization.

After long time cognitive work, most of people confronted with the mental fatigue, which can decrease the classification accuracy of cognitive, or even cause the traffic accidents for drivers. Therefore, the detection of the fatigue state is very essential. The study aims to explore an effective and novel approach based on electroencephalogram. All participants were instructed to implement the spelling experiments. Data were recorded on the awake condition, on sleep deprivation condition and after two hour spelling experiment. To comprehensively quantify the state of mental fatigue, spectral non-negative matrix factorization and a quantification fatigue index were proposed in the data analysis. The results indicated that the quantification fatigue index significantly increased with the greater level of fatigue (p <; 0.05), and this method we proposed can discriminate the different state of fatigue. Thus this method is promising in detecting the state of mental fatigue with electroencephalogram.