Abstract:

This paper presents for an isolated four-approach intersection a traffic signal control method based on adaptive neural-fuzzy inference system. Which could make adjustments to signal timing in response to traffic changes. The “urgency degree”, “stop degree” term, which can describe the different users’ demands for green time are used in decision-making by which strategy of signal timing can be determined. Using three levels module based on adaptive neural-fuzzy inference system (ANFIS), it could be determined whether to extend or terminate the current signal phase and select the sequences of phases. Simulation results show that the fuzzy controller has the ability to adjust its signal timing in response to changing traffic conditions on a real-time basis, and the proposed controller produces lower vehicle delays than the traffic-actuated controller.

Keywords: Traffic Signal Control, Adaptive Neural-fuzzy, Inference system, Isolated Intersection

 (Full paper, 676KB )

Biographie:

Wei cheng, Doctor of Jilin University, major in traffic information and control, take part in two provincial research subjects, and publish more than 20 articles in academic journal and compile the book "traffic engineering" which win the Jilin University outstanding teaching awards. From June 2004 teach in faulty of Traffic engineering, Kunming University of science and technology. and act as deputy director of traffic engineering, take charge six scientific research program . now I am assessment team leader of the Yunnan Province "urban traffic project", the middle-aged academic and technology leaders of reserve personnel in Yunnan province, china.

BibTex:

 (Full paper, 676KB )