Traffic prediction using time related association rules and vehicle routing

This paper describes a methodology and results of traffic prediction by extracting important time related association rules using an evolutionary algorithm named Genetic Network Programming(GNP). The extracted rules provides an useful mean to investigate the future traffic density of traffic networks and hence to develop traffic navigation systems. The proposed methodology is implemented and experimentally evaluated using a large scale real-time traffic simulator SOUND/4U. The routing algorithm combined with the traffic prediction results is studied using the environment of SOUND/4U.