Genetic Gradient Algorithm Based RBF Neural Network and Its Applications to Traffic Information Prediction
GUO Lin1,2,3, FANG TingJian1,2,3, YE JiaSheng3
1.Hefei Institute of Intelligent Machines, Chinese Academy of Sciences, Hefei 230031 2.Department of Automation, University of Science and Technology of China, Hefei 230027 3.The Research Center for Software Engineering of Anhui Province, Hefei 230088
Abstract The realtime and accurate predicted traffic information is critical to the intelligent traffic inducement and the traffic management. A twostep learning algorithm GGA (Genetic Gradient Algorithm) for radial basis function (RBF) neural network is proposed in this paper. A genetic algorithm (GA) initially determines the parameters of the RBF network including the number and locations of the selected centers and the widths of Gaussian kernel functions in the hidden layer. Then a gradient descent algorithm is adopted to further adjust these parameters of the RBF network. A smaller network with better generalization capability can thus be obtained. The experimental results of the realtime traffic information prediction in Ningbo city show good performance of the proposed method.
GUO Lin,FANG TingJian,YE JiaSheng. Genetic Gradient Algorithm Based RBF Neural Network and Its Applications to Traffic Information Prediction[J]. , 2006, 19(6): 831-835.
[1] Yang Zhaosheng. The Inducing System of Urban Traffic Flow. Beijing, China: Chinese Railway Publishing House, 2004 (in Chinese) (杨兆升.城市交通流诱导系统.北京:中国铁道出版社, 2004) [2] Smith B L, Demetsky M J. Traffic Flow Forecasting: Comparison of Modelling Approaches. Journal of Transportaion Engineering, 1997, 123(4): 261-266 [3] Okotani I, Stephanedes Y J. Dynamic Prediction of Traffic Volumn through Kalman Filtering Theory. Transportation Reasearch: Part B, 1984, 18(1): 1-11 [4] Hobeika A G, Chang K K. Traffic-Flow-Prediction Systems Based on Upstream Traffic // Proc of the Vehicle Navigation and Information System Conference. Berlin, Germany, 1994: 456-462 [5] Hussein D. An Object-Oriented Neural Network Approach to Short-Term Traffic Forecasting. European Journal of Operations Research, 2001,131(2): 253-261 [6] Wu C H, Ho J M, Lee D T. Travel-Time Prediction with Support Vector Regression. IEEE Trans on Intelligent Transportation Systems, 2004, 5(4): 276-281 [7] Zhao W B, Huang D S. The Structure Optimization of Radial Basis Probabilistic Neural Networks Based on Genetic Algorithms // Proc of the International Joint Conference on Neural Networks. Honolulu, USA, 2002: 1086-1091 [8] Gomm J B, Yu D L. Selecting Radial Basis Function Network Centers with Recursive Orthogonal Least Squares Training. IEEE Trans on Neural Networks, 2000, 11(2): 306-314 [9] Fastentrath D U. Floating Car Data on a Larger Scale [EB/OL]. [1997-05-01]. http://www.ddg.de/pdf_dat/ddgfcd.pdf [10] Wang Jiajie, Fang Tingjian, Jchfer R P. China First FCD Application at NingBo City // Proc of 12th World Congress on Intelligent Transport Systems and Services. San Francisco, USA, 2005: 1250-1256
2006, Vol. 19 
