Authors: Wang Jian long, Wuhan University, Li Yi cong, Wuhan University, Duan Xiao qi, Wuhan University, Cui Chen rong, Wuhan University, Zhang Tong*, Wuhan University
Topics: Transportation Geography
Keywords: Public transit services,mobility patterns,smart card data,transit community,visualization
Session Type: Paper
Start / End Time: 5:00 PM / 6:40 PM
Room: 8228, Park Tower Suites, Marriott, Lobby Level
Presentation File: No File Uploaded
Monitoring human movement is of fundamental importance in transportation planning and management. Being deployed on public transit vehicles, smart card automated fare payment systems provide an efficient manner to collect large volumes of travel data at individual level.
We propose to examine complex public transit travel patterns over a large-scale transit network, which is challenging since it involves thousands of transit passengers and massive data from heterogeneous sources. Secondly, efficient representation and visualization of discovered travel patterns is needed given a large quantities of transit trips.
To address these challenges, this study leverages data-driven machine learning methods to identify time-varying mobility patterns based on smart card data. We also devise compact multi-scale visualization forms to represent the discovered travel behavior dynamics.
The proposed approach delivers a comprehensive solution to pre-process, analyze, and visualize complex public transit travel patterns. This approach first fuses smart card data with other urban data to reconstruct original transit trips. It then segments the study region into hierarchical areal units according to their mobility features. Based on these mobility areal units (i.e., transit community), we further extract inter-community corridors to represent mobility links between different regions. An interactive mapping prototype is also developed to enable the visual exploration of mobility structures over space and time.
The proposed approach is evaluated using smart card data collected in Shenzhen City, China. Our prototype demonstrates that the proposed visual analytics approach can offer a scalable and effective solution for discovering meaningful travel patterns across a big metropolitan area.