FREEWAY TRAFFIC PREDICTION USING NEURAL NETWORKS

This paper presents the design of multilayer feedforward neural networks to predict freeway traffic conditions at a loop detector station. The neural networks make use of 30-second volume, occupancy and speed averaged across all lanes in the past 2 intervals as inputs, and predict the same set of local parameters in the next 1 or 2 time intervals. Networks with various design and training parameters have been trained and evaluated with 2 weeks of morning data collected at I-880 Freeway in the San Francisco Bay Area. The results show that the neural nets have high accuracy in volume, occupancy and speed predictions during low, moderate and perhaps high volume conditions, including recurring congestion and possibly during incidents.

Language

  • English

Media Info

  • Features: Figures; References; Tables;
  • Pagination: p. 247-254

Subject/Index Terms

Filing Info

  • Accession Number: 00769603
  • Record Type: Publication
  • ISBN: 0784403333
  • Files: TRIS
  • Created Date: Sep 26 1999 12:00AM