Linguistic reporting of driver behavior: Summary and event description

There is a clear need for computational systems able to produce automatic linguistic descriptions of data about phenomena. Linguistic summarization represents an attempt to describe by means of linguistic expressions patterns emerging in data. Generating data summaries can be seen as a very complex and non-trivial data mining task. Language is the unique meta-language to describe and understand various complex phenomena and humans use it for multi-modal data fusion in their brains. Our work is devoted to advance towards the development of a framework for the fusion of heterogenous information using linguistic descriptions based on NL. This application paper deals with the development of a computational system capable of automatically generating linguistic descriptions of driving activity from vehicle simulator data. Based on Fuzzy Logic, and as a contribution towards the development of Computational Theory of Perceptions, the proposed solution is part of our research on granular linguistic models of phenomena. We will generate a set of valid sentences describing a phenomenon through a granular linguistic model of a phenomenon. Then a relevancy analysis will be performed, in order to choose the most suitable sequence of clauses to each specific input data. We have used real time-series data from a vehicle simulator to evaluate the performance of our approach.