A user centric mobility prediction approach based on spatial conceptual maps

This paper presents a novel framework for user mobility prediction that can accurately predict the traveling trajectory and destination using knowledge of user´s preferences, goals, and analyzed spatial information without imposing any assumptions about the availability of users´ movements history. Using concepts of evidential reasoning of Dempster-Shafer´s theory, the user´s navigation behavior is captured by gathering pieces of evidence concerning different groups of candidate future locations. These groups are then refined to predict the user´s future location when evidence accumulate using Dempster rule of combination. Simulation results are presented to demonstrate the performance of the proposed framework.