Different activities in urban environment involve mobility and an efficient mobility is an important factor for a smooth running of these activities. Recent advances in sensing technology have made it possible to track moving objects (e.g. pedestrians and vehicles) especially in urban environment. While the analysis of these traces has mainly focused on discovering movement patterns, the interpretation of these patterns is still challenging due to ignoring the movement context.
This project aims at developing methods for integrating the spatio-temporal context into the analysis of urban mobility data. The methods developed cover the process running from the acquisition of context data, integrating them with the mobility data, and analysing the integrated data for mobility pattern interpretation. The interest in this project is particularly on identifying the interplay between the movement and its context; by discovering causal relationships for instance. The project applies different computational approaches designed for handling large datasets. Mobility data including scheduled public transportation, taxi, and private car traces are used to demonstrate the applicability of the methods developed. The results of this project can be useful in smart city applications where the detection of unusual mobility patterns and the exploration of the evolution of these patterns are of great importance.