Combined Bayesian Networks and Rough-Granular Approaches for Discovery of Process Models Based on Vehicular Traffic Simulation

Abstract

The aim of this paper is to summarize our experiments for discovering process of creation of traffic jams. These experiments were conducted during work on our master theses. We obtained data sets from the vehicular traffic simulator which were used to create a proper ontology based on the domain knowledge. The ontology was used as a schema for hierarchical classifier, which used Bayesian network created by genetic algorithm and rough sets based methods. © Springer-Verlag Berlin Heidelberg 2010.