关键词: 出租车轨迹数据, Canopy-K-means算法, 公交车站, 公交车的发车频率

Abstract:

It is fairly hard to plan the path of public traffic and to determine the traffic site via traditional way. Additionally, by appropriately mining the useful GPS data of taxi, the human activity hotspot can be identified. Thus, mining the GPS data of taxi is helpful for planning bus station. For this reason, A Canopy-K-means method is proposed to predict public traffic stations. Firstly, the hot spots of the tourist destination can be got by applying the Canopy K-means algorithm. Further, comparing the hot spots with the existing bus stations, we analyze the rationality of the existence of the bus station. Then, the temporal and spatial distribution characteristics of passenger flow is studied by mathematical statistics. The GPS trajectory data of 2064 taxis in Wuhan from July 31, 2014 to August 12, 2014 are employing for experimental study and the results show that the proposed method can effectively distinguish the rationality of bus station location and provide auxiliary decision for the departure frequency of buses.

Key words: taxi track data, Canopy-K-means algorithm, bus stations prediction, departure frequency of buses