基于<i>K</i>近邻算法和支持向量回归组合的短时交通流预测

摘要
图/表
参考文献
相关文章 (15)

全文: PDF (625 KB) HTML ()
输出: BibTeX | EndNote (RIS)

摘要 To improve the forecasting accuracy of short-term traffic flow and provide precise and reliable traffic information for traffic management units and travelers, this study proposes a hybrid prediction model that is based on the characteristics of K-nearest neighbor (KNN) method and support vector regression (SVR). The proposed hybrid model, i.e. KNN-SVR, mimics the search mechanism of the KNN method to reconstruct a time series of historical traffic flow that is similar to the current traffic flow. Then, the SVR is used for short-term traffic flow forecasting. Using actual traffic flow data, we study the effect of the traffic flows on target and adjacent section roads and analyze the forecasting accuracy of the proposed model. Results show that the KNN-SVR model that considers the target and adjacent section roads has the best performance, having a mean absolute percentage error (MAPE) of 8.29%. The forecasting error of the KNN-SVR model that considers only the target section road is slightly large, having an average MAPE of 9.16%. Furthermore, the forecasting accuracy of the KNN-SVR model is better than that of traditional prediction models, such as the KNN method, SVR, and neural networks.

	服务

	把本文推荐给朋友
	加入我的书架
	加入引用管理器
	E-mail Alert
	RSS
	作者相关文章
	刘钊
	杜威
	闫冬梅
	柴干
	郭建华

关键词 ： traffic engineering, prediction model, K-nearest neighbor, support vector regression, short-term traffic flow

Abstract：To improve the forecasting accuracy of short-term traffic flow and provide precise and reliable traffic information for traffic management units and travelers, this study proposes a hybrid prediction model that is based on the characteristics of K-nearest neighbor (KNN) method and support vector regression (SVR). The proposed hybrid model, i.e. KNN-SVR, mimics the search mechanism of the KNN method to reconstruct a time series of historical traffic flow that is similar to the current traffic flow. Then, the SVR is used for short-term traffic flow forecasting. Using actual traffic flow data, we study the effect of the traffic flows on target and adjacent section roads and analyze the forecasting accuracy of the proposed model. Results show that the KNN-SVR model that considers the target and adjacent section roads has the best performance, having a mean absolute percentage error (MAPE) of 8.29%. The forecasting error of the KNN-SVR model that considers only the target section road is slightly large, having an average MAPE of 9.16%. Furthermore, the forecasting accuracy of the KNN-SVR model is better than that of traditional prediction models, such as the KNN method, SVR, and neural networks.

Key words： traffic engineering prediction model K-nearest neighbor support vector regression short-term traffic flow

收稿日期: 2017-05-15

基金资助:Supported by the National Natural Science Foundation of China (No.61573106); The Scientific Innovation Research of College Graduates in Jiangsu Province (No.KYLX_0168)

通讯作者: LIU Zhao E-mail: liuzhao_xy@sina.com

引用本文:

刘钊, 杜威, 闫冬梅, 柴干, 郭建华. 基于K近邻算法和支持向量回归组合的短时交通流预测[J]. Journal of Highway and Transportation Research and Development, 2018, 12(1): 89-96.
LIU Zhao, DU Wei, YAN Dong-mei, CHAI Gan, GUO Jian-hua. Short-term Traffic Flow Forecasting Based on Combination of K-nearest Neighbor and Support Vector Regression. Journal of Highway and Transportation Research and Development, 2018, 12(1): 89-96.

链接本文:

http://manu27.magtech.com.cn/Jwk_gljtkj_en/CN/ 或 http://manu27.magtech.com.cn/Jwk_gljtkj_en/CN/Y2018/V12/I1/89

[1] VLAHOGIANNI E I, GOLIAS J C, KARLAFTIS M G. Short-term Traffic Forecasting:Overview of Objectives and Methods[J]. Transport Reviews, 2004,24(5):533-557.
[2] SMITH B L, WILLIAMS B M, OSWALD R K. Comparison of Parametric and Nonparametric Models for Traffic Flow Forecasting[J]. Transportation Research Part C:Emerging Technologies, 2002,10(4):303-321.
[3] KARLAFTIS M G, VLAHOGIANNI E I. Memory Properties and Fractional Integration in Transportation Time Series[J]. Transportation Research Part C:Emerging Technologies, 2009,17(4):444-453.
[4] GUO J H, WILLIAMS B M. Real Time Short Term Traffic Speed Level Forecasting and Uncertainty Quantification Using Layered Kalman Filters[J]. Transportation Research Record:Journal of the Transportation Research Board, 2010,2175:28-37.
[5] SONG Guo-jie, HU Cheng, XIE Kun-qing, et al. Process Neural Network Modeling for Real Time Short-term Traffic Flow Prediction[J]. Journal of Traffic and Transportation Engineering, 2009,9(5):73-77. (in Chinese)
[6] YANG Chun-xia,FU Yi-qin,BAO Tie-nan. Short-term Traffic Flow Prediction Based on Similarity[J]. Journal of Highway and Transportation Research and Development, 20015,32(10):124-128. (in Chinese)
[7] ZHANG Tao, CHEN Xian, XIE Mei-ping, el al. K-NN Based on Nonparametric Regression Method for Short Term Traffic Flow Forecasting[J]. System Engineering-Theory & Practice, 2010,30(2):376-384. (in Chinese)
[8] WU Q. A Hybrid-Forecasting Model Based on Gaussian Support Vector Machine and Chaotic Particle Swarm Optimization[J]. Expert Systems with Applications, 2010,37(3):2388-2394.
[9] GUO Jian-hua, WILLIAMS B, SMITH B. Data Collection Time Intervals for Stochastic Short-term Traffic Flow Forecasting[J]. Transportation Research Record, 2008,2024:18-26.
[10] SUN Zhan-quan, PAN Jing-shan, ZHANG Zan-jun, et al. Traffic Flow Forecast Based on Combining Principal Component Analysis with Support Vector Machine[J]. Journal of Highway and Transportation Research and Development, 2009,26(5):127-131. (in Chinese)
[11] FAN Na, ZHAO Xiang-mo, DAI Ming, et al. Short-term Traffic Flow Prediction Model[J]. Journal of Traffic and Transportation Engineering, 2012(4):114-119. (in Chinese)
[12] SHEN Guo-jiang, WANG Xiao-hu, KONG Xiang-jie. Short-term Traffic Volume Intelligent Hybrid Forecasting Model and Its Application[J]. System Engineering-Theory & Practice, 2011,31(3):561-568. (in Chinese)
[13] HUANG Ling, LIN Pei-qun, XU Jian-min. Urban Road Network Traffic Congestion Prediction Model Based on Probe Vehicle Technology[J]. Journal of Highway and Transportation Research and Development, 2009,26(10):121-125. (in Chinese)
[14] WANG J, Shi Q. Short-term Traffic Speed Forecasting Hybrid Model Based on Chaos-wavelet Analysis-support Vector Machine Theory[J]. Transportation Research Part C:Emerging Technologies, 2013,27:219-232.
[15] XIANG Xiao-dong. Research on Forecast of Nonlinear Time Series Based on Neural Networks and Chaotic Theory[D]. Chengdu:Southeast Jiaotong University, 2002.
[16] YANG Zhao-sheng, WANG Yuan, GUAN Qing. Short-term Traffic Flow Prediction Method Based on SVM[J]. Journal of Jilin University Engineering and Technology Edition, 2006,36(6):881-884. (in Chinese)
[17] ZHANG Xiao-li, LU Hua-pu. Non-parametric Regression for Short-term Traffic Flow Forecasting[J]. Journal of Tsinghua University:Science and Technology, 2009,5(9):1471-1475. (in Chinese)
[18] SMOLA A J, SCHÖLKOPF B. A Tutorial on Support Vector Regression[J]. Statistics and Computing, 2004, 14(3):199-222.
[19] YUAN F, CHEU R L. Incident Detection Using Support Vector Machines[J]. Transportation Research Part C:Emerging Technologies, 2003, 11(3):309-328.
[20] TAN M C, WONG S C, XU J M, et al. An Aggregation Approach to Short-term Traffic Flow Prediction[J]. IEEE Transactions on Intelligent Transportation Systems, 2009,10(1):60-69.