Dynamic traffic signal control using a self-learning fuzzy-neural intelligent system.

This paper introduces an adaptive and self-learning intelligent traffic signal control system for networks or corridor applications. It is aimed at meeting the requirements of dynamic traffic optimal control. The system is developed based on intelligent fuzzy modeling, fuzzy-neural algorithms and traffic delay minimization algorithms. It consists of two major parts: off-line and on-line. In the off-line part, traffic flow patterns are identified using a fuzzy clustering algorithm. In the on-line part, real time traffic data is acquired through field traffic controllers. (A)