ABSTRACT
Cities worldwide face rapid growth and huge transportation challenges. By monitoring traffic performance and patterns over time, cities can ensure they operate at full capacity. The prediction of traffic characteristics such as traffic flow and travel time stands for an important feature in Advanced Traveler Information Systems (ATIS). In the era of data availability, the dissemination of accurate traffic information to travelers could have a huge impact on their trip choices and thus in systems’ performance. The scope of this paper is traffic modeling and prediction based on artificial neural networks namely deep learning mechanisms. The proposed framework enables the estimation of traffic characteristics between a predefined set of Origin-Destinations (O-D) locations, by taking into account available disaggregate traffic data. The proposed application is tested on a realistic road system, namely that of Cyprus. The aim of the study is to provide reliable travel information to users in order to improve significantly the use of the existing transportation networks.
