Vehicle Trajectory Analysis Based On Optimized Association Rules

With the development of economy,the living standard of people has been constantly improved,and the construction of smart cities has gradually increased in various regions,which is one of the key contents of new infrastructure construction.Meanwhile,vehicle control is the primary content of smart city construction.On the one hand,it is necessary to detect and identify the urban vehicle target comprehensively.On the other hand,it is significant to analyze and depict the trajectory of specific vehicles,so as to grasp the relevant information of important vehicles,such as finding accompanying vehicles,analyzing landing point of the vehicle,and predicting vehicle trajectory.These information will provide a huge auxiliary role for traffic management and other relevant departments,and provide a strong data support for the construction of smart city.However,with the increase of urban vehicles,it is increasingly difficult to analyze,manage and mine vehicle information.In order to better serve the society,the relevant departments urgently need new methods to analyze and use these data efficiently.Therefore,it is of great significance to analyze vehicle trajectory by association rule algorithm.Firstly,this paper introduces the basic development of smart city,the types of vehicle trajectory,and the generation and development of association rules.This paper focuses on the analysis of Apriori algorithm in association rules,and summarizes its advantages and disadvantages.In view of the shortcomings of the track analysis of the bayonet vehicle,the following improvements are made:1.In view of the performance bottleneck of the classic Apriori algorithm,the common association rule Apriori algorithm is improved to T-Apriori algorithm,so that it can be suitable for the analysis of the vehicle trajectory of the intelligent bayonet system.The algorithm uses the Boolean matrix to associate the data,only needs to scan the database once to get frequent itemsets,which greatly reduces the waste of I/O resources.In the process of operation,we make full use of the properties of association rules to prune,so that the data is compressed and the efficiency of operation is improved.Therefore,T-Apriori algorithm has the advantages of less memory space,fast running speed,and suitable for vehicle trajectory analysis.2.T-Apriori algorithm is used to analyze the association of vehicles.By setting the threshold,the frequent item set group that meets the threshold is found to determine the accompanying vehicles.This method can mine the accompanying vehicle group in the large-scale data set,which solves the problem of the deficiency of the traditional method in the process of accompanying vehicle mining.This method not only makes full use of resources,but also obtains more abundant information,which greatly improves the efficiency.3.According to the frequency of vehicles occurrence in a certain area,the prediction of vehicle foothold is divided into two parts:high frequency vehicle and low frequency vehicle.Using T-Apriori association rules,by associating the license plate number and the corresponding historical foothold,then the possible foothold of the vehicle can be analyzed and predicted.Next,Combined with the actual situation of the road network,the prediction of the vehicle trajectory can be completed.The experimental results show that the method can accurately predict the real-time landing point of the vehicle,and relatively accurately predict the trajectory of the vehicle,which has a certain practicality.