Traffic State Identification Based on Phase Transition

A new method for state identification is proposed based on traffic phase transition. An interval is used as a threshold instead of a single value in order to improve the discrimination precision. Traffic parameters are divided into two categories: traffic parameters at a point and traffic parameters over a section. A traffic index is extracted by using principal component analysis under location traffic parameters. Based on the data of the Oakland Bay Bridge and Chongqing Yellow Garden Bridge, the statistical distribution law of traffic index is studied, finding the phase change process between traffic states. The detection of traffic states is realized by detecting the transition period and the corresponding rules are proposed. By using the new method and cluster analysis, the traffic states of Yellow Garden Bridge for one day are identified. By comparing the results, the method proposed in this paper is more consistent with the actual situation.

• Record URL:
  • https://doi.org/10.1061/9780784482292.255
• Availability:
  • Find a library where document is available. Order URL: http://worldcat.org/isbn/9780784482292
• Supplemental Notes:
  • © 2019 American Society of Civil Engineers.
• Corporate Authors:

  American Society of Civil Engineers

  1801 Alexander Bell Drive
  Reston, VA  United States  20191-4400
• Authors:
  • Feng, Shumin
  • Xin, Mengwei
  • Han, Xishuang
  • Sun, Yali
• Conference:
  • 19th COTA International Conference of Transportation Professionals
  • Location: Nanjing , China
  • Date: 2019-7-6 to 2019-7-8
• Publication Date: 2019-7

Language

• English

Media Info

• Media Type: Web
• Monograph Title: CICTP 2019: Transportation in China—Connecting the World

Subject/Index Terms

• TRT Terms: Automatic vehicle detection and identification systems; Case studies; Distributions (Statistics); Traffic characteristics; Traffic flow
• Identifier Terms: Chongqing Yellow Garden Bridge (China); San Francisco-Oakland Bay Bridge
• Subject Areas: Highways; Operations and Traffic Management;

Filing Info

• Accession Number: 01713699
• Record Type: Publication
• ISBN: 9780784482292
• Files: TRIS, ASCE
• Created Date: Aug 13 2019 9:26AM