Application of new neural network technology in traffic volume prediction

HU Sheng-neng

Abstract


In view of the disadvantages of traditional neural network technology application, neural network integration technology is applied to traffic forecast for the first time. Neural network integration is used to study the same problem with a finite number of neural networks, and the output of each network is synthesized, which significantly improves the generalization ability of the learning system.Based on Boosting and Bagging integration method, the neural network integration method is proposed based on divide and conquer strategy, and discussed the network weights allocation algorithm. Using these three kinds of neural network integration prediction model, the real-time traffic volume of a certain intersection in Zhengzhou city is predicted, and the result is better than that of single neural network forecasting method. The experiments show that the neural network integration is better used in traffic forecasting.


Full Text:

PDF

References


BibikY.V. (2007).The second Hamiltonian structure for a special case of the Lotka-Volterra equations. Computational Mathematics and Mathematical Physics,47(8): 1285−1294

Breiman L. (2012).Bagging predictors. Machine Learning, 24(2):123-140

Chen H.Y. (2015). Research on the combination forecasting model based on forecasting effectiveness. Forecast, 20(3): 72-73

Corinne Ledoux. (2015).An urban traffic flow model integrating neural networks. Transportation Research Part C: Emerging Technologies, 13(1): 21-31

Despotovic V., Goertz N., Peric Z. (2012).Nonlinear long-term prediction of speech based on truncated Volterra series. IEEE Transactions on Audio, Speech, and Language Processing,20(3): 1069−1073

DoughetryM.S., CobbettM.R. (2012). Short-term inter-urban traffic forecasts using neural networks. International Journal of Forecasting, 13(1): 21-31

Ghasemi M., TavassoliK.M., Babolian E. (2010).Numerical solutions of the nonlinear VolterraFredholm integral equations by using homotopy perturbation method. Applied Mathematics and Computation, 188(1): 446−449

Hansen L.K., Salamon P. (2010).Neural Network integration. IEEE Trans Pattern Analysis and Machine Intelligence, 12(10):993 -1001

HornikK.M., Stinchcombe M., White H.(2015).Multilayer Feedforward Networks are Universal Approximators. Neural Networks, 2(2):259-366

Kennedy, R.E. (2013).Particle swarm optimization proc. IEEE International Conference on Neural Networks (Perth, Australia). IEEE Service Center, Piscataway, NJ, 5: 1942-1948

Kirby H., Watson S., Dougherty M. (2014).Should we use neural networks or statistical models for short-term motorway traffic forecasting. International Journal of Forecasting, Elsevier, 13: 43-50

Kobayakawa S, Yokoi H. (2009).Evaluation of prediction capability of Non-recursion type 2nd-order Volterra neuron network for electrocardiogram. In: Proceedings of the 15th International Conference on Neuro-Information Processing of the Asia Pacific Neural Network Assembly, Lecture Notes in Computer Science. Berlin, Heidelberg: Springer, 5507: 679−686

Lelitha V., Laurence R.R. (2014).A comparison of the performance of artificial neural networks and support vector machines for the prediction of traffic speed. 2004 IEEE Intelligent Vehicles Symposium. Parma, Italy: Institute of Electrical and Electronics Engineers,194-199

Liu L.L., Li K.K., Lu F.(2016).Dynamic Simulation Modeling of Inking System Based on Elastohydrodynamic Lubrication, International Journal of Heat and Technology,34(3),124-128

Park B. (2012).Hybrid neural-fuzzy application in short-term freeway traffic volume forecasting. Transportation Research Record 1802, 190-196

SilveiraD.D., GilabertP.L., Dos-Santos A.B., Gadringer M.(2013).Analysis of variations of volterra series models for RF power am pliers. IEEE Microwave and Wireless Components Letters, 23(8): 442−444

Smith B.L., DemetskyM.J. (2013).Short-term traffic flow prediction: neural network approach. Transportation Research Record 1453, 98-104

Wang M.T. (2014).Research on the method of determining the optimal solution of the combined forecasting weight coefficient. System engineering theory and practice, (3): 104-109

Wu J.X., Zhou Z.H., Shen X.H. (2010).A selective neural network integration construction method. Computer research and development, 37(9): 1039-1044

YakubovY.A.(2009). On nonlinear Volterra equations of convolution type. Deferential Equations, 45(9): 1326−1336

Yin H.B., Xu J.M.(2013).Huang Huang. Research on intersection traffic volume prediction method based on fuzzy neural network. China Journal of highway and transport, 13(3): 78-81

Zhu Z., Yang Z.S. (2015).Prediction model of real time traffic flow artificial neural network. China Journal of highway and transport, 11(4): 89-92

Zhou Z.H., Chen S.F. (2012).Neural network integration. Chinese Journal of computers, 25(1): 1-8


Refbacks

  • There are currently no refbacks.


Revista de la Facultad de Ingeniería,

ISSN: 2443-4477; ISSN-L:0798-4065

Edif. del Decanato de la Facultad de Ingeniería,

3º piso, Ciudad Universitaria,

Apartado 50.361, Caracas 1050-A,

Venezuela.

© Universidad Central de Venezuela