Journal article
Off-Deployment Traffic Estimation --- A Traffic Generative Adversarial Networks Approach
IEEE transactions on big data, Vol.8(4), pp.1084-1095
07/09/2022
DOI: 10.1109/TBDATA.2020.3014511
Abstract
The rapid progress of urbanization has expedited the process of urban planning, e.g., new residential, commercial areas, which in turn boosts the local travel demand. We propose a novel "off-deployment traffic estimation problem", namely, to foresee the traffic condition changes of a region prior to the deployment of a construction plan. This problem is important to city planners to evaluate and develop urban deployment plans. However, this task is challenging. Traditional traffic estimation approaches lack the ability to solve this problem, since no data about the impact can be collected before the deployment and old data fails to capture the traffic pattern changes. In this paper, we define the off-deployment traffic estimation problem as a traffic generation problem, and develop a novel deep generative model TrafficGAN that captures the shared patterns across spatial regions of how traffic conditions evolve according to travel demand changes and underlying road network structures. In particular, TrafficGAN captures the road network structures through a dynamic filter in the dynamic convolutional layer. We evaluate our TrafficGAN using a large-scale traffic data collected from Shenzhen, China. Results show that TrafficGAN can more accurately estimate the traffic conditions compared with all baselines.
Details
- Title: Subtitle
- Off-Deployment Traffic Estimation --- A Traffic Generative Adversarial Networks Approach
- Creators
- Yingxue Zhang - Worcester Polytechnic Institute, 8718 Worcester, Massachusetts United States (e-mail: yzhang31@wpi.edu)Yanhua Li - Computer Science Department, Worcester Polytechnic Institute (WPI), Worcester, Massachusetts United States (e-mail: yli15@wpi.edu)Xun Zhou - Management Sciences, The University of Iowa, iowa city, Iowa United States 52242 (e-mail: xun-zhou@uiowa.edu)Xiangnan Kong - WPI, Worcester, Massachusetts United States (e-mail: xkong@wpi.edu)Jun Luo - Machine Intelligence Center, Lenovo Group Limted, Telegraph Bay, Hong Kong Hong Kong (e-mail: jluo1@lenovo.com)
- Resource Type
- Journal article
- Publication Details
- IEEE transactions on big data, Vol.8(4), pp.1084-1095
- Publisher
- IEEE
- DOI
- 10.1109/TBDATA.2020.3014511
- ISSN
- 2332-7790
- eISSN
- 2332-7790
- Grant note
- 1831140 / Division of Civil Mechanical and Manufacturing Innovation (10.13039/100000147) 1566386; 1718310 / Division of Information and Intelligent Systems (10.13039/100000145) 1657350 / Division of Computer and Network Systems (10.13039/100000144)
- Language
- English
- Electronic publication date
- 08/05/2020
- Date published
- 07/09/2022
- Academic Unit
- Business Analytics
- Record Identifier
- 9984066101802771
Metrics
18 Record Views