Evaluation of probabilistic queries in moving objects databases

Abstract

The representation of moving objects in spatial database systems has become an important research topic in recent years. As it is not realistic to track and store the location of objects at every time instant, one of the issues in this domain has to do with handling uncertainty in the location of moving objects. In this paper, we propose three statistical methods for computing probabilistic estimates about the location of a moving object at a certain time and show how to use them for evaluating probabilistic range queries. The focus is on applications dealing with the spatiotemporal behavior of non-network constrained moving objects, for monitoring or data-mining purposes, for instance.