Skip to main navigation Skip to search Skip to main content

Spatiotemporal multi-Task learning for citywide passenger flow prediction

  • Runxing Zhong
  • , Weifeng Lv
  • , Bowen Du*
  • , Shuo Lei
  • , Runhe Huang
  • *Corresponding author for this work
  • Beihang University
  • Hosei University

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

Massive data collected by automated fare collection (AFC) systems provides unprecedented opportunities for studying and predicting citywide passenger flow, which can be beneficial for travel planning, traffic management, and public safety. However, it is very challenging to model and predict citywide passenger flow because there are a variety of factors potentially influencing it, such as the dynamic change of passenger flow and spatiotemporal correlations. To this end, in this paper, we first investigate multiple types of heterogeneous data that are related to the citywide passenger flow, and extract different features from each type of the data, including mobility related features, connectivity and traffic capacity, regional characteristics, event and weather, and temporal view features. Then, upon these features, we develop a spatiotemporal multi-Task learning based regression approach for predicting the citywide passenger flow. Finally, we leverage real-world data sets from multiple sources for model training and validation. Experimental results on real-world data demonstrate the effectiveness of our proposed approach in predicting citywide passenger flow.

Original languageEnglish
Title of host publication2017 IEEE SmartWorld Ubiquitous Intelligence and Computing, Advanced and Trusted Computed, Scalable Computing and Communications, Cloud and Big Data Computing, Internet of People and Smart City Innovation, SmartWorld/SCALCOM/UIC/ATC/CBDCom/IOP/SCI 2017 - Conference Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages1-8
Number of pages8
ISBN (Electronic)9781538604342
DOIs
StatePublished - 26 Jun 2018
Event2017 IEEE SmartWorld Ubiquitous Intelligence and Computing, Advanced and Trusted Computed, Scalable Computing and Communications, Cloud and Big Data Computing, Internet of People and Smart City Innovation, SmartWorld/SCALCOM/UIC/ATC/CBDCom/IOP/SCI 2017 - San Francisco, United States
Duration: 4 Apr 20178 Apr 2017

Publication series

Name2017 IEEE SmartWorld Ubiquitous Intelligence and Computing, Advanced and Trusted Computed, Scalable Computing and Communications, Cloud and Big Data Computing, Internet of People and Smart City Innovation, SmartWorld/SCALCOM/UIC/ATC/CBDCom/IOP/SCI 2017 - Conference Proceedings

Conference

Conference2017 IEEE SmartWorld Ubiquitous Intelligence and Computing, Advanced and Trusted Computed, Scalable Computing and Communications, Cloud and Big Data Computing, Internet of People and Smart City Innovation, SmartWorld/SCALCOM/UIC/ATC/CBDCom/IOP/SCI 2017
Country/TerritoryUnited States
CitySan Francisco
Period4/04/178/04/17

Fingerprint

Dive into the research topics of 'Spatiotemporal multi-Task learning for citywide passenger flow prediction'. Together they form a unique fingerprint.

Cite this