Research on the Combination Model of Short-Term Traffic Flow Forecasting

Abstract:

Short-term traffic flow is difficult to predict accurately and real-time, owing to the characteristics of very complexity, randomness, nonlinearity and uncertainty, etc.. In this paper, the method of combining multiple linear regression with back propagation (BP) neural network was proposed, using BP neural network to compensate the model error of multiple linear regression. The combination model and the corresponding algorithm program was made, and used to pedict the short-term traffic flow. Two different methods of selecting the input layer parameters were used and compared, while the new method has higher accuracy and stability.

• Periodical: Applied Mechanics and Materials (Volumes 178-181)
• Pages: 2668-2672
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.178-181.2668
• Online since: May 2012
• Authors: Yuan Lin Liu*, Wu Sheng Hu, Su Lan Li, Hong Wei Li
• Keywords: BP Neural Network (BPNN), Input Layer Elements, Model, Multiple Linear Regression, Short-Term Traffic Flow

References

[1] Y.L. Liu, W.S. Hu, S.J. Xin. The Short-Term Traffic Flow Prediction Based on Genetic BP Neural Network [C]. The 10th International Conference of Chinese Transportation Professionals, 1835-1843. (2010)

DOI: 10.1061/41127(382)198

[2] B.L. Smith, M.J. Demetsky. Traffic Flow Forecasting: Comparison of Modeling Approaches [J]. Journal of Transportation Engineering, vol. 123, 261-266. (1997)

DOI: 10.1061/(asce)0733-947x(1997)123:4(261)

[3] Z. Zhu, Z.S. Yang, A real-time traffic flow prediction model based on artificial neural network [J]. China Journal of Highway and Transport, vol. 11, 89-92. (1998)(in Chinese)

[4] Z.S. Yang, Y.L. Gu, A study on the model for real-time dynamic traffic flow forecasting [J]. Journal of Highway and Transportation Research and Development, vol. 15, 4-7. (1998) (in Chinese)

[5] Y.L. Pei, Y. Zhang, Research on short-term traffic flow forecasting model of nodes in urban road network [J]. China Civil Engineering Journal, vol. 36, 11-15. (2003) (in Chinese)

[6] M.S. Dougherty, H.R. Kirby, R.D. Boyle, The use of neural networks to recognise and predict traffic congestion [J]. Traffic Engineering Control, vol. 34, 311-314. (1993)

[7] B. Park, C.J. Messer, T.II. Urbanik, Short-term freeway traffic volume forecasting using radial basis function neural network [J]. Transportation Research Record, Washington, D.C., vol. 1651, 39-47. (1998)

DOI: 10.3141/1651-06

[8] W.S. Hu, Y.L. Liu, S.J. Xin. The Short-Term Traffic Flow Prediction Based on Neural Network [C]. The 2010 International Conference on Future Computer and Communication, 293-296. (2010)

DOI: 10.1109/icfcc.2010.5497785

[9] W.S. Hu. The theory of neural network and its applications in engineering [M]. Sino Maps Press, Beijing, 63-67. (2006) (in Chinese)