As traffic conditions on arterial streets vary by day and month, fixed time signal control do not cope optimally with traffic demand. Especially megacities suffering from traffic congestions would need traffic responsive control systems. In this paper a low-cost real-time coordinated traffic signal control system is presented which is suited in particular for megacities in developing or newly industrializing countries. The proposed system is based on a pattern recognition method using feed forward artificial neural networks. The system recognizes the traffic state by system detectors and selects suitable settings out of a set of previously optimized timing plans. Real-time software in the loop simulation technique is used to compare the proposed system with optimized fixed time signal control. Although this study is based on experiments with microscopic traffic flow simulation, the algorithm itself is ready for real world implementations.
Pattern recognition method for simplified coordinated traffic signal control
2011-06-01
436416 byte
Conference paper
Electronic Resource
English
Transition scheme of traffic signal coordinated control
British Library Conference Proceedings | 2022
|Adaptive & Coordinated Traffic Signal System
IEEE | 2020
|Traffic jam coordinated control method and traffic jam coordinated control system
European Patent Office | 2015
|TRAFFIC SIGNAL RECOGNITION DEVICE, TRAFFIC SIGNAL RECOGNITION METHOD, AND VEHICLE CONTROL PROGRAM
European Patent Office | 2022
|Research on the Model of Traffic Signal Control and Signal Coordinated Control
Springer Verlag | 2017
|