Short Term Prediction of Freeway Exiting Volume Based on SVM and KNN

作     者：Xiang Wang Kang An Liang Tang Xiaohong Chen 

作者机构：Ph.D.CandidateKey Laboratory of Road and Traffic Engineering of the Ministry of EducationTongji University 4800 Cao’an RoadShanghai201804P.R.of China Graduate Research AssistantDepartment of Civil and Environmental Engineering Transportation Systems Research Laboratory3109 Jeong H.Kim Engineering BuildingUniversity of MarylandCollege ParkMD 20740 ProfessorKey Laboratory of Road and Traffic Engineering of the Ministry of EducationTongji University 4800 Cao’an RoadShanghai201804P.R.of China 

出 版 物：《International Journal of Transportation Science and Technology》 (交通科学与技术(英文))

年 卷 期：2015年第4卷第3期

页      面：337-351页

学科分类：08[工学] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

主　　题：Freeway Exiting Flow Short-term Prediction KNN SVM Hybrid Model 

摘      要：In order to better predict the traffic states on freeways and make management decisions,a hybrid model of support vector machine(SVM)and K-nearest neighbor(KNN)is proposed for shortterm freeway exiting volume ***,a historical data set is built by using the freeway toll *** abnormal toll records,such as records that have same entry and exit station,illogical time record and abnormal travel speed,are excluded by data quality *** on the historical dataset,it is found that the exiting volume has periodical variation over time which provides the basis of the short-term ***,the historical data set is cross-classified into twelves groups based on the day of week and time of *** prediction has been done for each ***,the prediction is accomplished by the hybrid-model of SVM and *** exiting volumes of previous time periods are used as the feature vector for KNN and ***,a dynamic weight is adopted for the prediction of current time period based on the latest prediction accuracy of KNN and *** model results indicate that the proposed algorithm is feasible and *** Mean Absolute Percentage Error is under 10%.When comparing with the results of single KNN or SVM method,the results show that the combination of KNN and SVM can improve the reliability of the prediction *** proposed method can be implemented in the on-line application of exiting volume prediction,which is able to consider different vehicle types.