Research On Classification And Regression Of EEG Signals Based On Machine Learning For Fatigue Driving

According to statistics from the World Health Organization,China has always been among the countries with a high incidence of traffic accidents,for which the main reason is fatigue driving.In recent years,electroencephalogram(EEG)signals analysis is already a topic of interest within the field of fatigue driving research.In this paper,we conducted simulated driving experiments,and the classification and regression study were performed on the collected EEG signals.In the classification research of fatigue driving,there is a problem that a large amount of spatial orientation data will be generated by EEG signals in a short period of time.To solve this problem,we propose a feature reduction method based on weighted principal component analysis(WPCA)for EEG signals in this paper.Firstly,the EEG features were extracted by an autoregressive(AR)model.Secondly,we calculated the influence of different features on the classified performance of fatigue state.Then the accuracy reduction values of different features were normalized as the weights of the features.Finally,these weights were assigned to the WPCA to reduce the EEG features.In order to verify the effectiveness of the algorithm,we used the support vector machine(SVM)as a classifier to establish a fatigue driving classification experiment.The experimental results showed that the WPCA method could effectively reduce the feature dimension for different EEG feature extraction methods,accelerate the process of calculations,and achieve a much higher classification accuracy of fatigue driving.In the fatigue driving regression analysis study,in order to determine the driver’s fatigue level,we produced the data set label: which calculates the fatigue index of EEG signals to characterize the level of fatigue.In order to satisfy individual differences,the fatigue index curve was fitted by least square method.At the same time,we proposed an Ensemble Learning driver fatigue index regression analysis method based on Bayesian model combination(BMC-EL).And the support vector regression(SVR)algorithm was introduced as a base learner.By increasing the diversity and difference of the base learners,the performance of the regression analysis method during the process of driver fatigue index regression analysis could be improved.The experimental results showed that the proposed regression analysis method was reliable and could accurately and reliably characterize the driver’s fatigue index.