Traffic Flow Predicting of Chaos Time Series Using Support Vector Learning Mechanism for Fuzzy Rule- based Modeling
The method was studied about traffic flow prediction using least squares support vector machine regression for fuzzy rule-based model of phase-space reconstruction.The prediction model of traffic flow must be established to satisfy the intelligent need of high precision through the problems analysis of the exiting predicting methods in chaos traffic flow time series and the demand of uncertain traffic system.Based on the powerful nonlinear mapping ability of support vectors and the characteristics of fuzzy logic which can combine the prior knowledge into fuzzy rules,the traffic flow predicting model of chaotic time series was established by support vector machine regression for fuzzy rule-based model.The support vector learning mechanism extracts support vectors and generates fuzzy rules.The function was realized which extracts the typical samples as the final learning samples from the large-scale samples.The fuzzy basis function was chosen as the kernel function of the support vector machine to fuse the two mechanisms into a new fuzzy inference system.The predictive model could be updated online.The simulation result shows that the method is feasible and the predicting result have more precision than that using other methods.
traffic flow least squares support vector machine (LS-SVM) phase-space reconstruction fuzzy rule- based modelling intelligent transportation system(ITS)
PANG Ming-bao HE Guo-guang
PANG Ming-bao Institute of System Engineering Tianjin University, Hebei University of Technology Tia Institute of System Engineering, School of Management Tianjin University No 72, WEI Jin Road, Tianji
国际会议
2007 IEEE International Conference on Automation and Lofistics
山东济南
英文
2007-08-18（万方平台首次上网日期，不代表论文的发表时间）