DBH-CLUS: A Hierarchal Clustering Method to Identify Pick-up/Drop-off Hotspots

Travelling by taxi is more convenient and effective. With an overcrowding population and a much terrible traffic, the traditional way of hailing a taxi encounters many challenges like where to pick-up/drop-off passengers reasonably and where to find potential passengers quickly. More cities have established taxi stands to advocate and to guide passengers to hail a taxi. However, most of them have low rate of usage. The reason lies in that to determine where to establish reasonably is a big problem. In this paper, we are the first to propose a DFA to identify data signifying pick-up/drop-off events. We propose a DBH-CLUS method to identify pick-up/drop-off hotspots. The method applies hierarchal clustering based on agglomerative clustering analysis method. We have conducted three experiments to verify the DFA, to analyze the region agglomeration and to analyze the accuracy. The experimental results manifest that our method can precisely identify hotspots from the original GPS data and provide an excellent tool to facilitate taxi stand planning.