Application of fuzzy logic for detecting incidents at signalized highway intersections

S. Lee, John Yen, R. A. Krammes

Research output: Contribution to conferencePaperpeer-review

1 Scopus citations

Abstract

Traffic incidents - i.e., accidents, cargo spills, and vehicles stalled - are a major cause of urban congestion. Research in incident detection for signalized arterial streets is at a very initial stage. Existing algorithms are far from being robust in dealing with the difficulties related to data availability and the multi-dimensional nature of the incident detection problem. This paper discusses a fuzzy-logic based incident detection model for real-time implementation at signalized diamond interchanges. The model overcomes the boundary condition problem inherent in conventional threshold-based methods. The model captures system-wide incident effects utilizing multiple measures for more accurate and reliable detection, and is incorporated into a real-time traffic adaptive diamond interchange control system. The model is scaleable and expandable for larger systems of arterial streets. Simulation results suggest that the fuzzy-logic based approach to incident detection at signalized diamond interchanges is promising.

Original languageEnglish (US)
Pages867-872
Number of pages6
StatePublished - Dec 1 1996
EventProceedings of the 1996 5th IEEE International Conference on Fuzzy Systems. Part 3 (of 3) - New Orleans, LA, USA
Duration: Sep 8 1996Sep 11 1996

Other

OtherProceedings of the 1996 5th IEEE International Conference on Fuzzy Systems. Part 3 (of 3)
CityNew Orleans, LA, USA
Period9/8/969/11/96

All Science Journal Classification (ASJC) codes

  • Software
  • Theoretical Computer Science
  • Artificial Intelligence
  • Applied Mathematics

Fingerprint Dive into the research topics of 'Application of fuzzy logic for detecting incidents at signalized highway intersections'. Together they form a unique fingerprint.

Cite this