Using Information from Heterogeneous Sources and Machine Learning in Intelligent Transportation Systems

Abstract

Current estimates show that in Brazil traffic congestion has a huge impact in the economy. Although Intelligent Transportation Systems (ITS) techniques can contribute to reduce this figure, many of the proposed ITS-related techniques have not yet been fully developed and/or deployed. This is especially the case of techniques that use the potential of the Internet. Thus, this paper proposes methods for retrieving and using data from heterogeneous sources currently available in the Internet, in order to provide information for both authorities and for the citizens, using machine learning (ML) tools. It is important to stress that such Internet data goes beyond the traditional ones (e.g., traffic sensors), as it also refers to sources such as: social networks (e.g., Twitter); meteorological bulletins; sports and cultural events; images of traffic flow; videos (webcams); inter-vehicular communication and mobility Internet. This involves text and image processing, thus making the overall task not trivial. Underlying this effort, we propose a framework in which ML techniques play a key role in several tasks, from image and text processing to prediction. Specifically, our applications deal with named entities extraction in tweets, classification of event, pothole detection, and classification of traffic state from images.