A Bayesian Network Approach to Traffic Flow Forecasting

In this paper, the authors present a new approach to traffic flow forecasting using Bayesian networks. A Bayesian network involves a directed graphical model to represent conditional independencies between a set of random variables. This approach is different from many existing traffic flow forecasting models in that it explicitly includes information from adjacent road links. The approach also considers the issue of traffic flow forecasting when incomplete data exists. Experiments on urban traffic flow data from Beijing, along with comparisons with other methods, reveal that the Bayesian network is a promising and effective approach for traffic flow modeling and forecasting.

• Availability:
  • Find a library where document is available. Order URL: http://worldcat.org/oclc/41297384
• Authors:
  • Sun, Shiliang
  • Zhang, Changshui
  • Yu, Guoqiang
• Publication Date: 2006-3

Language

• English

Media Info

• Media Type: Print
• Features: Figures; References; Tables;
• Pagination: pp 124-132
• Serial:
  • IEEE Transactions on Intelligent Transportation Systems
  • Volume: 7
  • Issue Number: 1
  • Publisher: Institute of Electrical and Electronics Engineers (IEEE)
  • ISSN: 1524-9050
  • Serial URL: http://ieeexplore.ieee.org/xpl/RecentIssue.jsp?punumber=6979

Subject/Index Terms

• TRT Terms: Algorithms; Forecasting; Mathematical models; Traffic flow; Variable speed limits
• Subject Areas: Highways; Operations and Traffic Management; I71: Traffic Theory;

Filing Info

• Accession Number: 01020945
• Record Type: Publication
• Source Agency: UC Berkeley Transportation Library
• Files: BTRIS, TRIS
• Created Date: Apr 3 2006 7:35AM