Title: A METHOD OF TRAFFIC VARIABLE ESTIMATION BASED ON NEURO-FUZZY ON URBAN ROAD
Abstract: This paper examines traffic variable estimation, and presents a method of estimation for the number of vehicles waiting for queue (NVWQ) at urban intersections and based on neuro fuzzy logic. Results of training the neural network (NN) are presented for a detectorized intersection in Changsha city, China. The accuracy of NVWQ estimation using the fuzzy NN approach is above 90%. The fuzzy NNs have the advantages of both fuzzy expert systems and artificial NNs. The fuzzy NNs can be trained successfully to estimate NVWQ for different traffic flow patterns and conditions at intersections, thus greatly reducing much the effort of extracting traffic experts' knowledge of fuzzy if-then rules. All that remains is to present training data to the network which then determines its own rules through internal representation. In traffic signal control systems, detection of traffic variables at intersections, such as NVWQ, is very important and is the basic input data for determining signal timing.
Publication Year: 2003
Publication Date: 2003-01-01
Language: en
Type: article
Access and Citation
Cited By Count: 4
AI Researcher Chatbot
Get quick answers to your questions about the article from our AI researcher chatbot