EVALUATION OF EXISTING INCIDENT DETECTION ALGORITHMS

The report describes results of the first of two years of research on computer algorithms that make use of freeway surveillance data to detect incidents. Extensive data base is obtained from loop detectors on freeways in the Los Angeles area. Results are presented in three parts: Part I--Background and Evaluation Criteria; Part II--Evaluation of Existing Incident Detection Algorithms; Part III--Preliminary Results in the Development of New Incident Detection Algorithms. Part II represents the major portion of the report and describes the evaluation of a set of 24 algorithms which includes nearly all algorithms that had been proposed at the time this study was initiated. Among these algorithms are the California algorithm, an algorithm based on the method of standard normal deviates and 15 algorithms based on the double exponential smoothing technique.

  • Corporate Authors:

    Technology Service Corporation

    3811 Wilshire Boulevard
    Santa Monica, CA  USA  90403

    Federal Highway Administration

    Office of Research, 1200 New Jersey Avenue, SE
    Washington, DC  USA  20590
  • Authors:
    • Payne, H J
    • Goodwin, D N
    • Teener, M D
  • Publication Date: 1975-2

Media Info

  • Pagination: 244 p.

Subject/Index Terms

Filing Info

  • Accession Number: 00091427
  • Record Type: Publication
  • Source Agency: National Technical Information Service
  • Report/Paper Numbers: FHWA-RD-75- 39 Intrm Rpt.
  • Contract Numbers: DOT-FH-11-8278
  • Files: NTIS, TRIS, USDOT
  • Created Date: Jul 15 1976 12:00AM