Study on traffic flow prediction using RBF neural network

Author(s):  
Jun-mei Xiao ◽  
Xi-huai Wang
2011 ◽  
Vol 255-260 ◽  
pp. 4128-4132
Author(s):  
Hong Chen ◽  
Yu Wei Yuan ◽  
Juan Sun ◽  
Na Bao

In order to study the short-time traffic flow prediction on high-grade highway, the article proposed a model based on wavelet analysis and RBF neural network. Aiming to the traffic flow’s characteristic of highway, the study focus on three facet: network topology, the difference of continuous flow and discontinuous flow , the flow of lanes’ uplink and downlink are not equal. Thus the article use the wavelet analysis to do data preprocessing, then structure the model of short-term traffic flow prediction based on RBF neural network. The experiment result shows that the new hybrid model adapt to high-grade highway, and model considering traffic flow characteristic is better than the model which is not. Meanwhile the model has the higher precision of prediction.


Sign in / Sign up

Export Citation Format

Share Document