By Topic

Traffic Flow Predicting of Chaos Time Series Using Support Vector Learning Mechanism for Fuzzy Rule-based Modeling

Sign In

Cookies must be enabled to login.After enabling cookies , please use refresh or reload or ctrl+f5 on the browser for the login options.

Formats Non-Member Member
$33 $13
Learn how you can qualify for the best price for this item!
Become an IEEE Member or Subscribe to
IEEE Xplore for exclusive pricing!
close button

puzzle piece

IEEE membership options for an individual and IEEE Xplore subscriptions for an organization offer the most affordable access to essential journal articles, conference papers, standards, eBooks, and eLearning courses.

Learn more about:

IEEE membership

IEEE Xplore subscriptions

2 Author(s)
Pang Ming-bao ; Institute of System Engineering, Tianjin University, Hebei University of Technology, Tianjin City, China. ; He Guo-guang

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.

Published in:

2007 IEEE International Conference on Automation and Logistics

Date of Conference:

18-21 Aug. 2007