The Study Of Driving Distraction Behavior Based On Using The Mobile Taxi APP

With the rapid development of road transportation, the number of motor vehicles in various countries has increased rapidly, and the number of road traffic accidents has increased day by day. According to the figure, ninety percent of the road traffic accidents are related to human factors, and the driving distractions are the main cause of traffic accidents. In recent years, with the rapid increasing number of people using the mobile taxi App, the phenomenon of operating the mobile taxi App while driving is more and more common, thus the driving safety issues become more concerned. Therefore, it is very important to improve road traffic safety and reduce the accidents by studying the driving distraction behavior which is induced by using the mobile taxi App while driving and establishing the driving distraction monitoring model.This paper first introduces the relationship between driving safety and driving distraction behavior, and clarifies that driving distraction behavior is an important cause of accidents.Then the article sorts out the feature of using the mobile taxi App. Based on the Regulations of the People ’s Republic of China on the Implementation of Road Traffic Safety Law and the actual situation of the driving simulator, this paper concludes four types of distracting operation: having a Bluetooth calling, talking with passengers, viewing information, inputting information. Besides, the mobile phone holder is chosen to put on the dashboard.Subsequently, the paper details that the author finishes the driving simulation experiments based on using the mobile taxi App in the large-scale driving simulator which is researched and developed independently by the Southwest Jiaotong University.Through the conclusion of the experiment, we can see that in the conventional scene, the standard deviation of six types of data, such as throttle opening, longitudinal velocity, longitudinal acceleration, steering wheel angle, steering wheel angular velocity and lateral acceleration have significant differences.And the driver’s individual differences have no significant effect on the outcome of the six index data; In the unconventional scene, when the driver is distracting while driving, the driver’s response time to a dangerous stimulus increases significantly, and the individual differences in the driver will also have a significant impact on the outcome of response time.The change in the reaction time of the driver will directly lead to the changes in the way of avoiding collision , but the compensation behavior can’t reduce the traffic accident rate.we can see that the accident rate is significantly improved when the driver is distracting while driving.Finally, we divided the driving states into three categories, including normal driving state,cognitive distraction driving state, and visual distraction driving state. Based on the difference analysis result of longitudinal controlling indexes and vertical controlling indexes , the driving distraction monitoring parameter set is constructed . By the use of the support vector machine theory, the driving distraction monitoring model is constructed . Then the training sample set and the test sample set are randomly selected to train and verify the model. The results show that the average correct monitoring rate of normal driving state, cognitive distraction driving state, visual distraction driving state can be very high, respectively for 85%, 82.5%, 92.5%;The probability of the model mistaking the visual distraction driving state and cognitive distraction driving state for the normal driving state is less than 8%; The overall monitoring effect of the model is good, and the model can be used for monitoring the driving distracting.