SHORT-TERM TRAFFIC FLOW PREDICTION USING NEURO-GENETIC ALGORITHMS

This paper presents a new short-term traffic flow prediction system based on an advanced Time Delay Neural Network model, the structure of which is synthesized using a genetic algorithm. The model predicts flow and occupancy values at a freeway section based on contributions from its recent temporal profile as well as its spatial profile. An in-depth study of the variables pertinent to traffic flow prediction was conducted examining the extent of the "look-back" in time interval, the extent of prediction in the future, the extent of spatial contributions, the resolution of the input data, and their effects on prediction accuracy. The model's performance is validated using simulated and actual traffic flow data acquired from the ATMS Testbed in Orange County, California. Both temporal and spatial effects were found to be essential for proper prediction. Results obtained indicate that the prediction errors vary inversely with the extent of the spatial contribution, and that the inclusion of 3 loop stations in both directions of the subject station is sufficient for practical purposes. Results also indicate that the level of data aggregation/resolution should be comparable to the prediction horizon for best accuracy. The model performed acceptably using both simulated and actual data.

• Availability:
  • Find a library where document is available. Order URL: http://worldcat.org/oclc/34620932
• Corporate Authors:

  Taylor & Francis

  4 Park Square, Milton Park
  Abingdon,   United Kingdom  OX14 4RN
• Authors:
  • Abdulhai, B
  • Porwal, H
  • Recker, W
• Publication Date: 2002-1

Language

• English

Media Info

• Features: Appendices; Figures; References;
• Pagination: p. 3-41
• Serial:
  • ITS Journal
  • Volume: 7
  • Issue Number: 1
  • Publisher: Taylor & Francis
  • ISSN: 1024-8072
  • Serial URL: http://firstsearch.oclc.org/journal=1024-8072;screen=info;ECOIP

Subject/Index Terms

• TRT Terms: Freeways; Genetic algorithms; Highway transportation; Intersections; Neural networks; Traffic control; Traffic engineering; Traffic flow; Traffic flow theory; Traffic models
• Subject Areas: Highways; Operations and Traffic Management; I71: Traffic Theory;

Filing Info

• Accession Number: 00929724
• Record Type: Publication
• Files: TRIS
• Created Date: Aug 1 2002 12:00AM