부산대학교 도서관

In this demo, we present a system for managing location uncertainty in moving objects’ data and refining their uncertain trajectories. Therefore, users are able to query objects’ past, present, and predicted location more precisely. In the absence of precise location data, i.e. exact lat and long, the uncertain location is defined by an uncertainty region that overlaps multiple nodes in the underlying road network graph. Imprecise location comes from various causes such as inaccurate GPS readings, cloaked region for privacy, or communication issues. The main idea is to find a maximum likelihood connected path of nodes across consecutive regions of uncertainty. By doing so, we narrow down the possible paths and hence prune out a considerable number of nodes in the uncertain regions which in turn leads to a smaller and more precise region. Finally, using the latest location data received from a given object, following refinements, we predict its future movements. Due to the uncertain nature of the problem, there are always multiple possible locations for a moving object. This is only amplified when we try to predict future movements. The refinement steps narrow down possible locations significantly and hence reduces the computation cost. During the demo, the audience will be able to interact with the system to define the size of the uncertainty region, examine the refinement process, and visually experience how the system narrows down the possible locations of the objects’ past, current, and future trajectory segments.