ARTIFICIAL INTELLIGENCE TECHNIQUES IN THE DEVELOPMENT OF EXPRESSWAY INCIDENT DETECTION SYSTEMS

In this paper, the authors describe how genetic algorithms and probabilistic neural networks can be applied as freeway automatic incident detection (AID) models are developed. AID model development has been hampered by insufficient training data and a lack of model adaptability when site conditions change. The authors propose solutions to these two problems using artificial intelligence techniques. They use genetic algorithms to calibrate system parameters and neural networks to achieve site adaptation potential.

• Availability:
  • Find a library where document is available. Order URL: http://worldcat.org/oclc/42308110
• Supplemental Notes:
  • Publication Date: 1999 Civil-Comp Press, Edinburgh, Scotland
• Corporate Authors:

  National University of Singapore

  Department of Civil Engineering, 1 Engineering Drive 2
  Singapore,   Singapore  117576
• Authors:
  • Jin, X
  • Cheu, R L
  • Srinivasen, D
  • Ng, K C
• Publication Date: 1999

Language

• English

Media Info

• Pagination: p. 235-242
• Serial:
  • Novel design and information technology applications for civil and structural engineering
  • Publisher: National University of Singapore

Subject/Index Terms

• TRT Terms: Artificial intelligence; Automatic incident detection; Freeways; Neural networks
• Subject Areas: Data and Information Technology; Highways;

Filing Info

• Accession Number: 00801238
• Record Type: Publication
• Source Agency: UC Berkeley Transportation Library
• Files: PATH
• Created Date: Nov 7 2000 12:00AM