Title: Exploring traffic condition based on massive taxi trajectories

Authors: Dongjin Yu; Jiaojiao Wang; Ruiting Wang

Addresses: School of Computer Science and Technology, Hangzhou Dianzi University, Hangzhou, China; Key Laboratory of Complex Systems Modelling and Simulation, Ministry of Education, Hangzhou, China ' School of Computer Science and Technology, Hangzhou Dianzi University, Hangzhou, China; Key Laboratory of Complex Systems Modelling and Simulation, Ministry of Education, Hangzhou, China ' School of Computer Science and Technology, Hangzhou Dianzi University, Hangzhou, China; Key Laboratory of Complex Systems Modelling and Simulation, Ministry of Education, Hangzhou, China

Abstract: As the increasing volumes of urban traffic data become available, more and more opportunities arise for the data-driven analysis that can lead to the improvements of traffic conditions. In this paper, we focus on a particularly important type of urban traffic dataset: taxi trajectories. With GPS devices installed, moving taxis become the valuable sensors for the traffic conditions. However, analysing these GPS data presents many challenges due to their complex nature. We propose a new approach to the exploration of traffic conditions based on massive taxi trajectories. First, we match the locations of moving taxis with the road network according to the recorded GPS data. Afterwards, we transform the trajectory of each moving taxi as a document, and identify traffic topics through textual topic modelling techniques. Finally, we cluster trajectories based on these traffic topics to explore the traffic conditions. The effectiveness of our approach is illustrated by the case with a large taxi trajectory dataset acquired from 3,743 taxis in a city.

Keywords: vehicle trajectory; map matching; traffic regions; latent Dirichlet allocation; LDA; trajectory clustering; visualisation.

DOI: 10.1504/IJHPCN.2019.099743

International Journal of High Performance Computing and Networking, 2019 Vol.14 No.1, pp.30 - 41

Received: 22 May 2016
Accepted: 18 Dec 2016

Published online: 08 May 2019 *

Full-text access for editors Access for subscribers Purchase this article Comment on this article