Discovering Expert Drivers from Trajectories
Jiabao Sun, Jiajie Xu, Rui Hong Zhou, Kai Zheng, Chengfei Liu · 2018
Discovering expert drivers is highly important for a broad range of location based services, but this issue is largely untouched in previous trajectory mining and search studies. In this paper, we study the problem of trajectory data driven expert driver discovery. It aims to find out top-k expert drivers about a region of interest, based on the understanding of their historical trajectories. To this end, we first investigate the construction of reference system, which collectively describes exemplar routes among important junctions, so that the driving behaviors embedded in each trajectory can be evaluated. To discover expert drivers accurately, a novel tf-idf concept based measure is proposed afterwards, such that the rationality of their trajectories are not only precisely evaluated by the match to reference system, but also properly aggregated for modelling expert drivers. Extensive experimental evaluation using real trajectory datasets demonstrates the effectiveness and efficiency of our proposed solutions.