Dynamic Origin-Destination Travel Demand Estimation Using Location Based Social Networking Data

The Location-based Social Networking (LBSN) data have emerged as new data sources for studying travel demand. This paper investigates the feasibility of using LBSN data to estimate dynamic Origin-Destination (OD) travel demand for general trips. A combined non-parametric cluster and regression model is used to establish the relationship between LBSN data and the trip production and attraction. A modified gravity model based trip distribution method with three friction function variations is proposed to estimate the OD matrix. The proposed methods are calibrated and evaluated against the ground truth OD data from CMAP (Chicago Metropolitan Agency for Planning). The results demonstrate the promising potential of using LBSN data for dynamic OD estimation.

• Supplemental Notes:
  • This paper was sponsored by TRB committee ADB40(1) Emerging Methods.
• Corporate Authors:

  Transportation Research Board

  500 Fifth Street, NW
  Washington, DC  United States  20001
• Authors:
  • Yang, Fan
  • Jin, Peter J
  • Wan, Xia
  • Li, Rui
  • Ran, Bin
• Conference:
  • Transportation Research Board 93rd Annual Meeting
  • Location: Washington DC
  • Date: 2014-1-12 to 2014-1-16
• Date: 2014

Language

• English

Media Info

• Media Type: Digital/other
• Features: Figures; Maps; References; Tables;
• Pagination: 15p
• Monograph Title: TRB 93rd Annual Meeting Compendium of Papers

Subject/Index Terms

• TRT Terms: Cluster analysis; Location based services; Origin and destination; Regression analysis; Travel demand; Trip distribution
• Candidate Terms: Social networking
• Identifier Terms: Chicago Metropolitan Agency for Planning
• Subject Areas: Highways; Planning and Forecasting; Public Transportation; I72: Traffic and Transport Planning;

Filing Info

• Accession Number: 01519220
• Record Type: Publication
• Report/Paper Numbers: 14-5509
• Files: TRIS, TRB, ATRI
• Created Date: Mar 24 2014 12:01PM