A Hybrid Short-term Traffic Flow Forecasting Method Based on Neural Networks Combined with K-Nearest Neighbor

  • Zhao Liu Southeast University
  • Jianhua Guo Southeast University
  • Jinde Cao Southeast University
  • Yun Wei Beijing Urban Construction Design and Development Group Co., Ltd
  • Wei Huang Southeast University
Keywords: short-term traffic flow forecasting, neural networks, K-nearest neighbor, traffic pattern

Abstract

It is critical to implement accurate short-term traffic forecasting in traffic management and control applications. This paper proposes a hybrid forecasting method based on neural networks combined with the K-nearest neighbor (K-NN) method for short-term traffic flow forecasting. The procedure of training a neural network model using existing traffic input-output data, i.e., training data, is indispensable for fine-tuning the prediction model. Based on this point, the K-NN method was employed to reconstruct the training data for neural network models while considering the similarity of traffic flow patterns. This was done through collecting the specific state vectors that were closest to the current state vectors from the historical database to enhance the relationship between the inputs and outputs for the neural network models. In this study, we selected four different neural network models, i.e., back-propagation (BP) neural network, radial basis function (RBF) neural network, generalized regression (GR) neural network, and Elman neural network, all of which have been widely applied for short-term traffic forecasting. Using real world traffic data, the  experimental results primarily show that the BP and GR neural networks combined with the K-NN method have better prediction performance, and both are sensitive to the size of the training data. Secondly, the forecast accuracies of the RBF and Elman neural networks combined with the K-NN method both remain fairly stable with the increasing size of the training data. In summary, the proposed hybrid forecasting  approach outperforms the conventional forecasting models, facilitating the implementation of short-term  traffic forecasting in traffic management and control applications.

Author Biographies

Zhao Liu, Southeast University
Zhao Liu is a PhD.student in the School of Transportation, Southeast University.
Jianhua Guo, Southeast University
Dr. Guo, Jianhua is a professor in Transportation Engineering at the Intelligent Transportation System Research Center of the Southeast University. His major research fields include intelligent transportation system applications, traffic management and control, statistical time series analysis, and discrete choice modeling.
Jinde Cao, Southeast University
Jinde Cao (M’07-SM’07-F’16) is a Distinguished Professor, the Dean of School of Mathematics and the Director of the Research Center for Complex Systems and Network Sciences at Southeast University.
Yun Wei, Beijing Urban Construction Design and Development Group Co., Ltd
He is the vice director of the Urban Railway Green and Safe Construction National Engineering Laboratory.  He is majoring in traffic information engineering and control and his research field includes intelligent vision analysis and pattern recognition.
Wei Huang, Southeast University
Wei Huang is a distinguished professor in Civil Engineer at the Intelligent Transportation System Research Center of the Southeast University.  He is a member of Chinese Academy of Engineering.  He enjoys the State Council special allowance and receives supports from the New Century Talent Program, the National Outstanding Mid-aged Experts Program, the National Talents Engineering Program, and the Yangtze Scholar Program from various agencies and organizations.

References

[1] Smith BL, Williams BM, Oswald RK. Comparison of parametric and nonparametric models for traffic flow forecasting. Transportation Research Part C: Emerging Technologies. 2002 Aug;10(4): 303-321.
[2] Yoon B, Chang H. Potentialities of data-driven nonparametric regression in urban signalized traffic flow forecasting. Journal of Transportation Engineering. 2014 Apr;140(7): 04014027.
[3] Smith BL, Ulmer JM. Freeway traffic flow rate measurement: Investigation into impact of measurement time interval. Journal of Transportation Engineering. 2003 May-June;129(3): 223-229.
[4] Guo J, Williams BM, Smith B. Data collection time intervals for stochastic short-term traffic flow forecasting. Transportation Research Record: Journal of the Transportation Research Board. 2008 Jan;2024: 18-26.
[5] Transportation Research Board (TRB). Highway capacity manual. Transportation Research circular-Special Rep. 209, National Research Council, Washington, D.C., p. 110-118.
[6] Smith BL, Demetsky MJ. Short-term traffic flow prediction: neural network approach. Transportation Research Record: Journal of the Transportation Research Board. 1994; 1453.
[7] Dougherty MS, Cobbett MR. Short-term inter-urban traffic forecasts using neural networks. International Journal of Forecasting. 1997 Mar;13(1): 21-31.
[8] Dia H. An object-oriented neural network approach to short-term traffic forecasting. European Journal of Operational Research. 2001 June;131(2): 253-261.
[9] Vlahogianni EI, Karlaftis MG, Golias JC. Optimized and meta-optimized neural networks for short-term traffic flow prediction: a genetic approach. Transportation Research Part C: Emerging Technologies. 2005 Jun;13(3): 211-234.
[10] Williams B, Durvasula P, Brown D. Urban freeway traffic flow prediction: application of seasonal autoregressive integrated moving average and exponential smoothing models. Transportation Research Record: Journal of the Transportation Research Board. 1998 Jan;1644: 132-141.
[11] Hamed MM, Al-Masaeid HR, Said ZMB. Short-term prediction of traffic volume in urban arterials. Journal of Transportation Engineering. 1995 Jun;121(3): 249-254.
[12] Williams BM, Hoel LA. Modeling and forecasting vehicular traffic flow as a seasonal ARIMA process: Theoretical basis and empirical results. Journal of Transportation Engineering. 2003 Nov;129(6): 664-672.
[13] Okutani I, Stephanedes, YJ. Dynamic prediction of traffic volume through Kalman filtering theory. Transportation Research Part B: Methodological. 1984 Feb;18(1): 1-11.
[14] Guo J, Williams BM. Real-time short-term traffic speed level forecasting and uncertainty quantification using layered Kalman filters. Transportation Research Record: Journal of the Transportation Research Board. 2010 Jan;2175: 28-37.
[15] Yasin Çodur M, Tortum A. An artificial neural network model for highway accident prediction: A case study of Erzurum, Turkey. Promet – Traffic & Transportation. 2015 May;27(3): 217-225.
[16] Marković H, Dalbelo Bašić B, Gold H, Dong F, Hirota K. GPS Data-based Non-parametric Regression for redicting
Travel Times in Urban Traffic Networks. Promet – Traffic & Transportation. 2010 Feb;22(1): 1-13.
[17] Clark S. Traffic prediction using multivariate nonparametric regression. Journal of Transportation Engineering. 2003 Apr;129(2): 161-168.
[18] Cai P, Wang Y, Lu G, Chen P, Ding C, Sun J. A spatiotemporal correlative k-nearest neighbor model for short-term traffic multistep forecasting. Transportation Research Part C: Emerging Technologies. 2016 Jan;62: 21-34.
[19] Zheng Z, Su D. Short-term traffic volume forecasting: a k-nearest neighbor approach enhanced by constrained linearly sewing principle component algorithm. Transportation Research Part C: Emerging Technologies. 2014 Jun;43: 143-157.
[20] Habtemichael FG, Cetin M. Short-term traffic flow rate forecasting based on identifying similar traffic patterns. Transportation Research Part C: Emerging Technologies. 2016 May;66: 61-78.
[21] Zhang Y, Xie Y. Forecasting of short-term freeway volume with v-support vector machines. Transportation Research Record: Journal of the Transportation Research Board. 2008 Jan;2024: 92-99.
[22] Peng T, Tang Z. A small scale forecasting algorithm for network traffic based on relevant local least squares support vector machine regression model. Applied Mathematics & Information Sciences. 2015 Apr;9(2L): 653-659.
[23] Wang J, Shi Q. Short-term traffic speed forecasting hybrid model based on chaos-wavelet analysis-support vector machine theory. Transportation Research Part C: Emerging Technologies. 2013 Feb;27: 219-232.
[24] Ma SF, He GG, Wang ST. A traffic flow forecast supported system based multi-agent. Intelligent Transportation Systems. IEEE Intelligent Transportation Systems Conference Proceedings, 25-29 Aug 2001, Oakland, CA, USA; 2001. p. 620-624.
[25] Vlahogianni EI, Karlaftis MG, Golias JC. Spatio-temporal short-term urban traffic volume forecasting using genetically optimized modular networks. Computer-Aided Civil and Infrastructure Engineering. 2007 May;22(5): 17-325.
[26] Vlahogianni, EI, Golias, JC, Karlaftis MG. Short-term traffic forecasting: overview of objectives and methods. Transport Reviews. 2004;24(5): 533-557.
[27] Karlaftis MG, Vlahogianni EI. Statistical methods versus neural networks in transportation research: Differences, similarities and some insights. Transportation Research Part C: Emerging Technologies. 2011 Jun;19(3): 387-399.
[28] Guo J, Huang W, Williams BM. Adaptive Kalman filter approach for stochastic short-term traffic flow rate prediction and uncertainty quantification. Transportation Research Part C: Emerging Technologies. 2014 Jun;43: 50-64.
[29] Zhang Y, Zhang Y, Haghani A. 2013. A hybrid shortterm traffic flow forecasting method based on spectral analysis and statistical volatility model. Transportation Research Part C: Emerging Technologies. 2013 Jun;43(Part 1): 65-78.
[30] Fei X, Lu C, Liu KA. Bayesian dynamic linear model approach for real-time short-term freeway travel time prediction. Transportation Research Part C: Emerging Technologies. 2011 Dec;19(6): 1306-1318.
[31] van Lint JWC, Hoogendoorn SP, van Zuylen HJ. Accurate travel time prediction with state-space neural networks under missing data. Transportation Research Part C: Emerging Technologies. 2005 Oct-Dec;13(5-6): 347-369.
[32] Yin H, Wong SC, Xu J, Wong CK. Urban traffic flow prediction using a fuzzy-neural approach. Transportation Research Part C: Emerging Technologies. 2002 Apr;10(2): 85-98.
[33] Quek C, Pasquier M, Lim BBS. POP-TRAFFIC: A novel fuzzy neural approach to road traffic analysis and prediction. IEEE Transactions on Intelligent Transportation Systems. 2006 May;7(2): 133-146.
[34] Ma X, Tao Z, Wang Y. Long short-term memory neural network for traffic speed prediction using remote microwave sensor data. Transportation Research Part C: Emerging Technologies. 2015 May;54: 187-197.
[35] Zheng W, Lee DH, Shi Q. Short-term freeway traffic flow prediction: Bayesian combined neural network approach. Journal of Transportation Engineering. 2006 Feb;132(2): 114-121.
[36] Kuchipudi C, Chien S. Development of a hybrid model for dynamic travel time prediction. Transportation Research Record: Journal of the Transportation Research Board. 2003 Jan;1855: 22-31.
[37] Stathopoulos A, Karlaftis MG. Spectral and cross spectral analysis of urban traffic flows. IEEE Intelligent Transportation Systems Conference Proceedings, 25-29 Aug 2001, Oakland, CA, USA; 2001. p. 820-825.
[38] Yu B, Song X, Guan F, Yang Z, Yao B. k-Nearest Neighbor Model for Multiple-Time-Step Prediction of Short-Term Traffic Condition. Journal of Transportation Engineering. 2016 Jun;142(6): 04016018.
[39] Han HG, Chen QL, Qiao JF. An efficient self-organizing RBF neural network for water quality prediction. Neural Networks. 2011 Sep;4(7): 717-725.
[40] Specht, DF. A general regression neural network. IEEE transactions on neural networks. 1991 Nov;2(6): 568-576.
[41] Shi XH, Liang YC, Lee HP, Lin WZ, Xu X, Lim SP. Improved Elman networks and applications for controlling ultrasonic motors. Applied Artificial Intelligence. 2004 Aug; 18(7): 603-629.
[42] Wilson DR, Martinez TR. The general inefficiency of batch training for gradient descent learning. Neural Networks. 2003 Dec;6(10): 1429-1451.
[43] Tan MC, Wong SC, Xu JM, Guan ZR, Zhang P. An aggregation approach to short-term traffic flow prediction. IEEE Transactions on Intelligent Transportation Systems. 2009 Mar;10(1): 60-69.
Published
2018-08-30
How to Cite
1.
Liu Z, Guo J, Cao J, Wei Y, Huang W. A Hybrid Short-term Traffic Flow Forecasting Method Based on Neural Networks Combined with K-Nearest Neighbor. Promet - Traffic & Transportation [Internet]. 30Aug.2018 [cited 17Oct.2018];30(4):445-56. Available from: http://www.fpz.unizg.hr/traffic/index.php/PROMTT/article/view/2651
Section
Articles