Prediction of Urban Expressway Travel Time through Matching Similar Spatiotemporal Traffic Patterns

Travel time is an effective measure of roadway traffic conditions. The provision of accurate travel time information enables travelers to make smart decisions such as route choice and departure time. Based on huge amounts of probe vehicle data, this study proposes a simple and fast data-driven method for travel time prediction on urban expressway. Unlike previous approaches that directly use travel time as the input variable, the proposed approach uses spatiotemporal traffic states evolution to match similar traffic patterns and predict travel times. First, Gray-Level Co-occurrence Matrix (GLCM) is employed to extract spatiotemporal traffic features. The Normalized Squared Differences (NSD) between GLCMs of current and historical datasets serves as a basis for distance measurement of similar traffic patterns. Then, a screening process with a time constraint window is implemented for weight assignment in selecting best matched candidates. Moreover, Box-and-Whisker Plot technique is adopted to suppress the influence of extreme candidates. Last, the future travel time is predicted as a combination of each candidate’s experienced travel time for a given departure. The proposed approach is investigated on Ring 2, a 33km urban expressway of Beijing, China. The results demonstrate the advantage of the proposed method, as well as its feasibility and effectiveness under varying traffic conditions.

• Supplemental Notes:
  • This paper was sponsored by TRB committee ABJ30 Standing Committee on Urban Transportation Data and Information Systems.
• Corporate Authors:

  Transportation Research Board

  500 Fifth Street, NW
  Washington, DC  United States  20001
• Authors:
  • Zhang, Zhihao
  • Wang, Yunpeng
  • Chen, Peng
  • 0000-0002-3201-7339
  • He, Zhengbing
  • Yu, Guizhen
• Conference:
  • Transportation Research Board 96th Annual Meeting
  • Location: Washington DC, United States
  • Date: 2017-1-8 to 2017-1-12
• Date: 2017

Language

• English

Media Info

• Media Type: Digital/other
• Features: Figures; References; Tables;
• Pagination: 30p
• Monograph Title: TRB 96th Annual Meeting Compendium of Papers

Subject/Index Terms

• TRT Terms: Beltways; Classification; Forecasting; Machine learning; Traffic distribution; Travel time
• Uncontrolled Terms: Spatiotemporal traffic dynamics
• Geographic Terms: Beijing (China)
• Subject Areas: Highways; Operations and Traffic Management;

Filing Info

• Accession Number: 01632158
• Record Type: Publication
• Report/Paper Numbers: 17-02434
• Files: TRIS, TRB, ATRI
• Created Date: Apr 5 2017 9:57AM