A classification method for urban functional regions based on the transfer rate of empty cars

Abstract

Predicting the nature of each urban functional region based on the transfer rate of empty cars plays a crucial role in constructing smart cities and urban planning. The transfer rate of empty cars describes the probability of a taxi driving from one region to another without any passengers. It can reflect the main driving directions of taxies and the main flow directions of people among different urban functional regions. Although current researches have focused on the functional regions divided by remote sensing satellite images, there is almost no discussion on determining the nature of the region through taxi behaviour. The authors consider using taxi behaviour to classify urban functional regions. Besides, the attentional spatio-temporal model (Attentional Gated Recurrent Unit, AGRU) is introduced in the work. The AGRU consists of three modules, which are the spatial feature extraction module, the temporal feature extraction module, and the attentional pooling mechanism. The model has been evaluated on the data set provided by Didi Chuxing and it has been compared with some typical models. The experimental results show that the AGRU can reflect spatio-temporal information, and its attentional pooling mechanism can distinguish whether a region is the place of departure or the destination.