Firstly, to improve the effectiveness of real-time fatigue detection, a locomotive driver fatigue monitoring mechanism based on bayesian network information fusion is proposed.

A lot of methods for evaluating driver fatigue are presented.

According to the comparisons among those commonly used detecting and evaluating techniques for motor driver fatigue,the PERCLOS(percentage of eyelid closure over the pupil over time) is the most closely correlated with driver fatigue in the study of simulating driving instrument.

So,research of driver fatigue characteristic in two-lane highway on mountain area can give reference for highway traffic safety design and management,further to prevent accident happening and assure men and vehicles safe.

Research situation and development trend of pre-warning system of fatigue driving;

Eyes states recognition algorithm for fatigue driving based on ICA and HMM;

To investigate the characters of the electroencephalogram(EEG) for fatigued drivers,the situation of fatigue driving was simulated using a car simulator,the EEG for the driver was recorded by an EEG recording instrument,and the EEG data and waves obtained.