Paper Title
Topology Change Detection Fromtaxis�gps Traces Big Data

Abstract
the conventional methods of road change detection extract the differences by comparing two road network data before and after the change, which have disadvantages in the data acquisition period, data cost, algorithmic complexity, calculation difficulty and the update period. In this paper, we propose a new road network topology change detection method based on vehicles� GPS spatiotemporal trajectories. In this method, the similarity between the GPS trajectory vector and the regional topological vector is first measured using the vector similarity measurement model. Then we detect the topological changes of the road network by comparing the road changes of the addition, the deletion and the modification. Experimental results showed that the proposed method can not only detect the changes of the addition, the deletion and the modification of road network, but also realize the real-time change detection of urban road network. Index Terms- GPS trajectories, similarity, road network, change detection.