Publication Date:
2014-08-27
Description:
The increasing need for traffic prediction systems has become an important issue in advanced traffic management and information systems. The forecast of traffic density reduces traffic congestion and improves transportation mobility. This study describes a novel methodology for traffic prediction by extracting important time-related association rules using an evolutionary algorithm named genetic network programming (GNP). The extracted rules provide a useful means for forecasting the future traffic density level of traffic networks. The proposed methodology is implemented and experimentally evaluated using a large-scale real-time traffic simulator named SOUND/4U. The routing algorithm combined with the traffic prediction was also studied using different environments.
Print ISSN:
0010-4620
Electronic ISSN:
1460-2067
Topics:
Computer Science
Permalink
