Search

To create and maintain a well-functioning transportation system is a very complex task, that requires knowledge from different domains. As the number of different means of transportation grows new dependencies and dynamic behavior patterns emerge. In this paper we analyze different options for modelling transportation systems with the use of heterogeneous data inputs and sources. Our study builds on use of machine learning and big data analysis for extracting information on characteristics of transportation systems and reducing the number of incidents. We aim at developing a flexible and extensible approach, that can be adapted to transportation problems of different complexity. [ABSTRACT FROM AUTHOR]