DocumentCode :
3020295
Title :
Rules Self-Adaptive Control System for Urban Traffic Signal Based on Genetic Study Classification Algorithm
Author :
Wang, Anlin ; Wu, Xiaofeng ; Ma, Bo ; Zhou, Chenglin
Author_Institution :
Mech. Eng. Coll., Tongji Univ., Shanghai, China
Volume :
1
fYear :
2009
fDate :
7-8 Nov. 2009
Firstpage :
429
Lastpage :
433
Abstract :
In this paper rules adaptive control system based on genetic study classification algorithm is put forward in order to solve the traffic signal´s separated, complex, non-linear features and prevent failure of the control rules in urban regional coordination traffic signal control system. In this study, we build the self-organization model by fluid dynamics, and get the control parameters and environment news to genetic classifier. Then, the system can classify and acquire good rules because of its powerful search capabilities in genetic algorithm and advantage in finding regulation from numerous data. Finally, aiming at the rules failure caused by urban construction or road alteration, a traffic platform is built by VC++ to simulate the actual traffic control. From the results, the system shows rules adaptive effect for environmental changes.
Keywords :
C++ language; genetic algorithms; road traffic; self-adjusting systems; VC++ simulation; fluid dynamics; genetic algorithm; genetic study classification algorithm; rules self-adaptive control system; self-organization model; urban traffic signal control; Adaptive control; Adaptive systems; Classification algorithms; Control systems; Fluid dynamics; Genetic algorithms; Nonlinear control systems; Power system modeling; Roads; Traffic control; Genetic study and classification; Self-Adaptive; Self-Organization; rules;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Artificial Intelligence and Computational Intelligence, 2009. AICI '09. International Conference on
Conference_Location :
Shanghai
Print_ISBN :
978-1-4244-3835-8
Electronic_ISBN :
978-0-7695-3816-7
Type :
conf
DOI :
10.1109/AICI.2009.233
Filename :
5376255
Link To Document :
بازگشت