A multilevel graph approach for road accidents data interpretation

Nowadays, due to the massive low-cost technology and mobile devices spread, our society is increasingly projected towards data production. Often, we find ourselves surrounded by data that, however, does not always lead to the knowledge, or toward information that we need. This is liable to eclipse the desire to use this data trying to predict the future. So much has been done in literature in regard to the extraction of information and interpretation of these data. However, in this field does not seem to be present a universal methodology for solving the problem, leading us to research new approaches more customized on the available dataset. The aim of this paper is to introduce an approach for the interpretation of data from sensors located within a city using three graphical views: Context Dimension Tree, Ontologies and Bayesian Networks. Through the Ontologies and the Context Dimension Tree it is possible to analyze the scenario from a syntactic and semantic point of view, assisting the construction of the he Bayes network structure that allow to estimate the probability that some events happen. A first preliminary analysis conducted on a London borough seems to confirm the effectiveness of the proposed method.