Abstract
In this paper, a hybrid genetic algorithm (GA) based online support vector machine (OSVM) prediction model for short-term traffic flow forecasting is proposed, according to the data collected sequentially by the probe vehicle or the loop detectors, which can update the forecasting function in real time via online learning way, and the parameters used in the OSVM were optimized by GA. As a result, it is fitter for the real engineering application. The GA based OSVM model was tested by using the I-880 database, the result shows that this model is superior to the back-propagation neural network (BPNN) model.
Access provided by Autonomous University of Puebla. Download to read the full chapter text
Chapter PDF
Similar content being viewed by others
Keywords
- Genetic Algorithm
- Support Vector Machine
- Traffic Flow
- Hybrid Genetic Algorithm
- Intelligent Transportation System
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.
References
Zhu, Z., Yang, Z.S.: Real time traffic flow prediction model based on ANN. China Journal of Highway and Transport 11(4), 89–92 (1998)
Yang, Z.S., Gu, Y.: Real time and dynamic traffic flow forecast research. Journal of Highway and Transportation Research and Development 15(3), 4–7 (1998)
Yang, Z.S.: Theories and models of urban traffic guidance system. China Communications Press, Beijing (2000)
Li, C.J., Yang, R.G., Zhang, J.S.: Traffic flow forecasts based on wavelet analysis. Journal of Computer Applications 23(12), 7–8 (2003)
He, G.J., Li, Y., Ma, S.F.: Short-term traffic flow prediction based on mathematic models. Systems engineering-theory & practice 12, 51–56 (2000)
He, G.Q.: Introduction to ITS systems engineering. China railway publishing house, Beijing (2004)
Yang, Z.S., Jiang, G.Y.: Theories and models of urban traffic guidance system based on high-order neural networks. Journal of Highway and Transportation Research and Development 6, 16–19 (1998)
Vapnik, V.: The Nature of Statistical Learning Theory. Springer, New York (1995)
Cheng, H., Cheng, L.H., et al.: The Appliance of BP-Network and SVM in Approach of Non-linear Function. Aeronautical Computer Technique 34(3), 27–30 (2004)
Xu, Q.H., Shi, J.: Aero-Engine Fault Diagnosis Based on Support Vector Machine. Journal of Aerospace Power 2, 298–302 (2005)
Wang, J.S., Gao, B.C., Shi, L.P.: Application of support vector machines in traffic volume forecast. Information Technology 4, 8–10 (2004)
Zhang, C.Y., Hu, G.H., Xu, T.Z.: Traffic flow time series prediction based on LS-SVM. Journal of Yunnan University 26, 19–22 (2004)
Yin, Y., Zhang, C.Y., Hu, G.H., Xu, T.Z.: Design of Real-Time Traffic Flow Simulating and Forecasting System Based on SVM. Journal of Computer Engineering and Applications 10, 197–199 (2005)
Xu, Q.H., Yang, R.: Traffic Flow Prediction Using Support Vector Machine Based Method. Journal of Highway and Transportation Research and Development 22(12), 131–134 (2005)
Jiang, G., Xiao, J.: Real-time Forecast of Urban Traffic Flow Based on Kernel Machine Method. Computer Engineering 32(17), 48–51 (2006)
Yang, Z.S., Wang, Y., Guan, Q.: Short-term traffic flow prediction method based on SVM. Journal of Jilin University 36(6), 881–884 (2006)
Qin, P.P.: Comparison of SVM and Neural Network Model for Incident Detection. Journal of Computer Engineering and Applications 34, 214–232 (2006)
Holland, J.H.: Adaptation in natural and artificial system. MIT Press, Cambridge, MA (1975)
Joine, J., Houck, C.: On the use of non-stationary penalty functions to solve nonlinear constrained optimization problems with GAs. In: Proceedings of the First IEEE Conference on Evolutionary Compution, pp. 548–579. IEEE Press, Los Alamitos (1994)
Kirpatrick, S., Gelatt, C.D., Vecchi, M.P.: Optimization by simulated annealing. Science 220(4598), 671–680 (1983)
Kovac, A., Glavic, P.: Retrofit of complex and energy intensive processes-I. Computers & Chemical Engineering 19, 1255–1270 (1995)
Kralj, A.K., Glavic, P.: Retrofit of complex and energy intensive processes. Computers & Chemical Engineering 21(Suppl.), 517–522 (1997)
Suykens, J.A.K., Vandewalle, J.: Least Squares Support Vector Machine Classifiers. Neural Process Letter 9, 293–300 (1999)
Zhang, C.B., Yang, X.G., Yan, X.P.: Traffic Data Collection System Based on Floating Cars. Computer and Communications 5(24), 31–34 (2006)
Petty, K.: The analysis software for the FSP project, http://ipa.eecs.berkeley.edu/~pettyk/FSP
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 2007 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Su, H., Yu, S. (2007). Hybrid GA Based Online Support Vector Machine Model for Short-Term Traffic Flow Forecasting. In: Xu, M., Zhan, Y., Cao, J., Liu, Y. (eds) Advanced Parallel Processing Technologies. APPT 2007. Lecture Notes in Computer Science, vol 4847. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-76837-1_80
Download citation
DOI: https://doi.org/10.1007/978-3-540-76837-1_80
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-76836-4
Online ISBN: 978-3-540-76837-1
eBook Packages: Computer ScienceComputer Science (R0)