Searching Activity Trajectories by Exemplar

The rapid explosion of urban cities has modernized the residents’ lives and generated a large amount of data (e.g., human mobility data, traffic data, and geographical data), especially the activity trajectory data that contains spatial and temporal as well as activity information. With these data, urban computing enables to provide better services such as location-based applications for smart cities. Recently, a novel exemplar query paradigm becomes popular that considers a user query as an example of the data of interest, which plays an important role in dealing with the information deluge. In this article, we propose a novel query, called searching activity trajectory by exemplar, where, given an exemplar trajectory τ_q, the goal is to find the top-k trajectories with the smallest distances to τ_q. We first introduce an inverted-index-based algorithm (ILA) using threshold ranking strategy. To further improve the efficiency, we propose a gridtree threshold approach (GTA) to quickly locate candidates and prune unnecessary trajectories. In addition, we extend GTA to support parallel processing. Finally, extensive experiments verify the high efficiency and scalability of the proposed algorithms.