DEVELOPMENT OF AN INCIDENT DETECTION ALGORITHM USING DISCRETE CHOICE MODEL

In this research, a detector-based incident detection algorithm for urban streets is developed. Incidents, temporary events which reduce the capacity of roadway segments and cause delays, are a major cause of urban roadway congestion. The rapid and automatic detection of incidents will be a key part of ATIS. The algorithm developed in this research attempts to recognize incident patterns by using incident index that represents the probability of occurring incident. The incident index is estimated by binomial logit model. The algorithm was tested in terms of performance measures such as detection rate, false alarm rate, and time to detection. The algorithm performance was superior to those of the California algorithm. For the covering abstract see IRRD E102946.

• Availability:
  • Find a library where document is available. Order URL: http://worldcat.org/isbn/899500732X
• Corporate Authors:

  ORGANIZING COMMITTEE 5TH WORLD CONGRESS

  KUSANG BLDG, 4TH FLOOR, 1009-5, DAECHI-DONG KANGNAM-KU
  SEOUL, ZZ KOREA    135-283
• Authors:
  • LEE, Y-I HWANG
• Conference:
  • TOWARDS THE NEW HORIZON TOGETHER. PROCEEDINGS OF THE 5TH WORLD CONGRESS ON INTELLIGENT TRANSPORT SYSTEMS, HELD 12-16 OCTOBER 1998, SEOUL, KOREA. PAPER NO. 4094
• Publication Date: 1998

Language

• English

Subject/Index Terms

• TRT Terms: Calculation; Incident detection; Intelligent transportation systems; Methodology; Sensors
• ITRD Terms: 6464: Calculation; 8531: Case study; 1632: Incident detection; 9102: Method; 6120: Sensor
• Subject Areas: Operations and Traffic Management;

Filing Info

• Accession Number: 00781322
• Record Type: Publication
• Source Agency: Transport Research Laboratory
• ISBN: 89-950073-2-X
• Files: ITRD
• Created Date: Jan 7 2000 12:00AM