Traffic State Classification Under Operational Constraints of Condition-Responsive Traffic Control Systems

The performance of any condition responsive traffic control systems depends on the appropriateness of the selection mechanism for picking the right traffic control scheme for any traffic state observed in the field. The right traffic control plan is typically selected by comparing actual traffic conditions with pre-defined thresholds for a few distinctive traffic states. A supervised linear discriminant analysis (SLDA) technique to classify observed traffic states under the operational constraints of condition responsive traffic control systems, such as the Traffic Responsive Plan Selection (TRPS) mode for closed-loop systems, was developed. A step-by-step description for determining TRPS thresholds is given, and application of the method is illustrated using hardware in the loop simulations and field studies. The field study results indicated statistically significant improvement in traffic operations after the implementation of the TRPS mode. The reduction in travel times and improvement in average travel speeds was found statistically significant. Although the method was primarily developed to TRPS mode, with slight modifications it can be used to other classification problems with similar constraints. The application of the system was illustrated using field data and hardware in the loop simulation.


  • English

Media Info

  • Media Type: CD-ROM
  • Features: Figures; References; Tables;
  • Pagination: 15p
  • Monograph Title: TRB 86th Annual Meeting Compendium of Papers CD-ROM

Subject/Index Terms

Filing Info

  • Accession Number: 01049641
  • Record Type: Publication
  • Report/Paper Numbers: 07-3478
  • Files: TRIS, TRB
  • Created Date: Feb 8 2007 8:09PM