Research On Driving Alertness Recognition Based On Multiple Physiological Signals

With the increasing of car ownership,road traffic safety problem has become more serious.As the operator of a car,its mental state is often the dominant reason for car accidents.In the long driving,the driver's driving alertness will continue to decrease with the degree of mental fatigue.Numerous studies have found that physiological signals are sensitive to the driver's mental state.Therefore,a driving vigilance recognition method based on EEG and ECG signals is proposed.The main research contents of this paper include the following points:(1)In this paper,the relationship between electroencephalogram(EEG)and electrocardiogram(ECG)signals and alertness was studied.According to previous studies,there were differences in the key indexes of electroencephalogram(EEG)before and after driving.(2)The difference between the before and after driving behavior data such as speed deviation,average speed,lane offset,and response accuracy was tested by T.The effectiveness of the split of the upper and lower alertness was verified.(3)The time domain and frequency analysis of heart rate variability of ECG signal were carried out,and the difference between the two time periods was verified.The characteristics of EEG signal were analyzed by wavelet transform,the components of EEG were extracted,and the key indexes were compared between the two phases.(4)The driving awareness recognition model was constructed by using the theory of T-S fuzzy neural network model.It was found that the recognition rate of the dual signal of the integrated ECG and EEG was slightly improved than that of the single signal,and the recognition rate of low driving alertness has been significantly improved.