Recognition Method Of Driver’s Propensity Based On Deduction Through Mobile Sensing Data

With the rapid development of the economy and the increasing number of car owner,especially private cars.The problem among driver-vehicle-environment is serious in road traffic system.Driver’s physiological and psychological characteristics are related closely to traffic safety and its influences on traffic safety are represented mainly as driver’s propensity,which means driver’s psychology experience for real traffic situation,and the corresponding preference of driver’s decisions and behaviors under the influence of all dynamic factors.Because of the practicability of mobile sensor data,more and more traffic researchers focus on them.At the same time,the problem of privacy protection is paied more and more attention by people,along with data collected and processed.How to combine the sensor data with privacy protection safely and effectively for scientific research,has become a hot research at home and abroad.In order to recognize driver’s propensity,it can be divided into three types:conservative type,common type,and radical type.It can be further divided into five types:conservative type,common-conservative type,common type,common-radical type and radical type.using the minimum entropy discretization continuous attributes based on Rough Set to discretely processed for the sample information,and using the heuristic greedy algorithm for attribute reduction,and the feature dataes are extracted for the driver’s propensity;To focus on considering situational factors of driver’s emotion affected directly for the situation of three lanes.Dynamic Bayesian network is used to establish the driving propensity recognition model that adapt to the environmental evolution;the research perspective is based on the vehicle safety controlled technology,respecting and protecting the driver privacy as a precondition.The experiment roads travel time is taken as the characteristic parameters obtained through GPS.The dynamic recognition model of driver’s propensity is established based on support vector machine.Results show that the established recognition model of driver’s propensity is reasonable and feasible,which can achieve the dynamic recognition of driver’s propensity to some extent.The recognition model provides reference and theoretical basis for personalized vehicle active safety systems taking people as center especially for the vehicle safety technology based on the networking.