Data Driven Performance Measures for Effective Management of Complex Transportation Networks

This research aims to explore performance measures quantified based on different transportation data sources. It examined the major performance measures that can help describe both traffic operations and safety conditions. The available data sources that can be used to derive the performance measures were investigated. Particularly, performance measures related to travel time reliability, incident duration, and secondary crashes have been emphasized. Data-driven methodologies for performance quantification have been proposed for each category. Specifically, improved travel time estimation approaches based on probe vehicle data have been developed for traffic delays and travel time reliability analysis. Second, structure learning algorithms based on Bayesian Networks approach were proposed to mine incident records and predict incident durations that can be used for traffic incident management. Finally, both infrastructure sensor and virtual-sensor-based approaches have been developed to explore traffic sensor data as well as on-line traffic information for identifying secondary crashes. The results shown through the use of actual case studies illustrated that how key performance measures can be used to assess the performance of their systems. This research suggests that by mining existing traffic data sources, more performance measures can be more efficiently and accurately quantified without major expenditures in the deployment of new data collection technologies

• Record URL:
  http://www.utrc2.org/sites/default/files/pubs/Final-Data-Driven-Performance-Measures.pdf
• 
• Supplemental Notes:
  • This document was sponsored by the U.S. Department of Transportation, University Transportation Centers Program.
• Corporate Authors:

  Rutgers University, Piscataway

  Center for Advanced Information Processing (CAIP)
  Rutgers Infrastructure Monitoring and Evaluation (RIME) Group
  Piscataway, NJ  United States  08854

  University Transportation Research Center

  City College of New York
  Marshak Hall, Suite 910, 160 Convent Avenue
  New York, NY  United States  10031

  Research and Innovative Technology Administration

  1200 New Jersey Avenue, SE
  Washington, DC  United States  20590
• Authors:
  • Ozbay, Kaan
  • Yang, Hong
  • Demiroluk, Sami
  • Morgul, Ender
  • Bartin, Bekir
• Publication Date: 2014-2-1

Language

• English

Media Info

• Media Type: Digital/other
• Edition: Final Report
• Features: Figures; Maps; References; Tables;
• Pagination: 87p

Subject/Index Terms

• TRT Terms: Algorithms; Case studies; Crash data; Data collection; Information management; Methodology; Performance measurement; Probe vehicles; Reliability; Sensors; Traffic data; Travel time
• Subject Areas: Data and Information Technology; Highways; Operations and Traffic Management; Safety and Human Factors; I70: Traffic and Transport; I80: Accident Studies;

Filing Info

• Accession Number: 01519412
• Record Type: Publication
• Contract Numbers: 49111-25-23
• Files: UTC, TRIS, RITA, ATRI, USDOT
• Created Date: Mar 24 2014 4:19PM