Dynamic Traffic Information Research Based On Data Mining Of Floating Cars

The research about vehicle data based on floating point in real-time traffic information has just started in China in the last two years, navigation products with dynamic real-time traffic information have appeared on the market w in China, but some products with dynamic real-time traffic information is not accurate , and traffic information didn't timely update and the information on a low coverage. In response to solve the issues above, we build traffic analysis model based on the floating car datas and achieve dynamic real-time traffic information update and provide owners for dynamic real-time traffic information service at Shenzhen.The purpose of this research project is to increase the accuracy of traditional judge road traffic information based on floating-point and reduce the requriements for amount of data. Real-timely read the GPS data uploaded by vehicles, analysis road traffic information , then put the traffic information into a database for convenient inquiries and timely release.In addition, in order to make full use of single vehicle for provide road traffic information, we install traffic analyzer (Mobile Navigation Assistance, MNA) in vehiche terminal, once there is a event of congestion, congestion information was reported initiativly so achieved distributed computing. There is not only reduce the center system compute pressure, but also reduces the amount of data requirements ,the data which for judge road traffic information. In finally integration of two kinds of information and release it in Web site form. This paper mainly include the following aspects:Firstly, in order to overcome the phenomenon that the large-scale floating point data spent a lot of time to local position, we divide the map into grid. First,local longitude and latitude data into grid, then locate the road section within the grid, so reduce the local time for latitude and longitude at exponential level.Secondly, large-scale floating-point vehicle data filter, sort and determine the model calculations.Once again, by a single vehicle data collection, analysis features, the establishment of traffic models to determine the road traffic conditon, and then the actual verification model changes through repeated verification model, and finally to determine the model, then model algorithm transplanted to vehicle, realize vehicle platform real-time communication with the central.Finally, integration variety of traffic information and establish the priority standards, put traffic information into the database, using the Web site to read real-time database data, realiz dynamic traffic information broadcast in real time.In this paper, the real state of traffic congestion detection and simulation to verify the two kinds of traffic models to determine the correct rate and real-time; break the traditional centralized computing, achieve applicaton for vehicle terminal real-time detection traffic information with GPS module.