Nonparametric Regression Algorithm for Short-term Traffic Flow Forecasting Based on Data Reduction and Support Vector Machine
吴晋武1,4, 张海峰2, 冉旭东3
1. College of Intelligence and Computing, TianjinUniversity, TianJin 300072, China; 2. BeiJing Institute of Space Science and Technology Information, BeiJing 100094, China; 3. College of Management and Economics, TianjinUniversity, TianJin 300072, China; 4. ShenZhen e-Traffic Technology Co., LTD, ShenZhen Guangzhou 518057, China
Nonparametric Regression Algorithm for Short-term Traffic Flow Forecasting Based on Data Reduction and Support Vector Machine
WU Jin-wu1,4, ZHANG Hai-feng2, RAN Xu-dong3
1. College of Intelligence and Computing, TianjinUniversity, TianJin 300072, China; 2. BeiJing Institute of Space Science and Technology Information, BeiJing 100094, China; 3. College of Management and Economics, TianjinUniversity, TianJin 300072, China; 4. ShenZhen e-Traffic Technology Co., LTD, ShenZhen Guangzhou 518057, China
摘要Nonparametric regression is an important method for short-term traffic flow forecasting, but the traditional nonparametric regression method needs a large storage space and slow query speed when the data are large and the dimension is high. In this paper, an improved nonparametric regression traffic flow forecasting algorithm is proposed. Subtraction fuzzy clustering method is used to cluster historical data to reduce the amount of data in the pattern database. Principal component analysis (PCA) is used to reduce the dimension of the pattern to overcome the problems of slow matching speed and interference of irrelevant dimension caused by the high dimension of the pattern. The support vector machine method is used to estimate the value of the final predicted variables by searching the patterns. The operation efficiency and prediction accuracy of the algorithm are improved. An online simulation-based test shows that the algorithm exhibits better efficiency and accuracy compared with traditional methods.
Abstract：Nonparametric regression is an important method for short-term traffic flow forecasting, but the traditional nonparametric regression method needs a large storage space and slow query speed when the data are large and the dimension is high. In this paper, an improved nonparametric regression traffic flow forecasting algorithm is proposed. Subtraction fuzzy clustering method is used to cluster historical data to reduce the amount of data in the pattern database. Principal component analysis (PCA) is used to reduce the dimension of the pattern to overcome the problems of slow matching speed and interference of irrelevant dimension caused by the high dimension of the pattern. The support vector machine method is used to estimate the value of the final predicted variables by searching the patterns. The operation efficiency and prediction accuracy of the algorithm are improved. An online simulation-based test shows that the algorithm exhibits better efficiency and accuracy compared with traditional methods.
基金资助:Supported by the National Natural Science Foundation of China (No.71571132)
通讯作者:
WU Jin-wu
E-mail: wjwhh@qq.com
引用本文:
吴晋武, 张海峰, 冉旭东. Nonparametric Regression Algorithm for Short-term Traffic Flow Forecasting Based on Data Reduction and Support Vector Machine[J]. Journal of Highway and Transportation Research and Development, 2020, 14(3): 96-103.
WU Jin-wu, ZHANG Hai-feng, RAN Xu-dong. Nonparametric Regression Algorithm for Short-term Traffic Flow Forecasting Based on Data Reduction and Support Vector Machine. Journal of Highway and Transportation Research and Development, 2020, 14(3): 96-103.
[1] WAN Yu-long,LI Xin-chun,ZHOU Hong-biao. Prediction of Short-term Traffic Flow Based on WPD-PSO-ESN[J]. Journal of Highway and Transportation Research and Development,2019,36(8):144-151. (in Chinese) [2] TANG Zhi-hui,ZHENG Wei-hao,DONG Wei,et al. A Method for Predicting Short-term Traffic Flow Based on Interactive IMM-BP-UKF Model[J]. Journal of Highway and Transportation Research and Development,2019,36(4):117-124. (in Chinese) [3] CHEN M,YU X H,LIU Y. PCNN:Deep Convolutional Networks for Short-term Traffic Congestion Prediction[J]. IEEE Transactions on Intelligent Transportation Systems,2018,19(11):1-10. [4] SUN Jing-yi,MOU Ruo-jin,LIU Yong-hua. Study on Short-term Traffic State Forecasting Model of SVM Considering Proportion of Large Vehicles[J]. Journal of Highway and Transportation Research and Development,2018,35(10):126-132. (in Chinese) [5] HU R,CHIU Y C,HSIEH C W,et al. Mass Rapid Transit System Passenger Traffic Forecast Using a Re-sample Recurrent Neural Network[J]. Journal of Advanced Transportation,2019,2019:8943291. [6] ZHAO Z,CHEN W,WU X,et al. LSTM Network:A Deep Learning Approach for Short-term Traffic Forecast[J]. IET Intelligent Transport Systems,2017,11(2):68-75. [7] YU B,SONG X,GUAN F,et al. K-nearest Neighbor Model for Multiple-time-step Prediction of Short-term Traffic Condition[J]. Journal of Transportation Engineering,2016,142(6):04016018. [8] CLARK S. Traffic Prediction Using Multivariate Nonparametric Regression[J]. Journal of Transportation Engineering,2003,129(2):161-168. [9] KIM T,KIM H,LOVELL D J. Traffic Flow Forecasting:Overcoming Memoryless Property in Nearest Neighbor Non-parametric Regression[C]//Proceedings of 2005 Intelligent Transportation Systems. Vienna:IEEE,2005. [10] ZHANG X L. The Forecasting Approach for Short-term Traffic Flow Based on Wavelet Analysis and Neural Network[J]. Information and Control,2007,36(4):467-470,475. [11] TUROCHY R E. Enhancing Short-term Traffic Forecasting with Traffic Condition Information[J]. Journal of Transportation Engineering,2006,132(6):469-474. [12] ZHANG X L,HE G G. The Forecasting Approach for Short-term Traffic Flow Based on Principal Component Analysis and Combined Neural Network[J]. Systems Engineering-Theory & Practice,2007,27(8):167-171. [13] ZHENG Z D,SU D C. Short-term Traffic Volume Forecasting:A K-nearest Neighbor Approach Enhanced by Constrained Linearly Sewing Principle Component Algorithm[J]. Transportation Research Part C:Emerging Technologies,2014,43:143-157. [14] ZHANG X L,HE G G,LU H P. Short-term Traffic Flow Forecasting Based on K-nearest Neighbors Non-parametric Regression[J]. Journal of Systems Engineering,2009,24(2):178-183. [15] WOLD S,ESBENSEN K,GELADI P. Principal Component Analysis[J]. Chemometrics & Intelligent Laboratory Systems,1987,2(1/2/3):37-52. [16] ABDI H,WILLIAMS L J. Principal Component Analysis[J]. Wiley Interdisciplinary Reviews Computational Statistics,2010,2(4):433-459. [17] BEZDEK J C. Pattern Recognition with Fuzzy Objective Function Algorithms[M]. New York:Plenum Press,1981. [18] JIA Ning,MA Shou-feng,ZHONG Shi-quan. Non-parameter-regression Traffic Flow Forecast Method Based on KD-tree and Genetic Optimization[J]. Control and Decision,2012,27(7):991-996. (in Chinese)
2020, Vol. 14 
