Short-term Hourly Traffic Forecasts using Hong Kong Annual Traffic Census

This paper proposes a method to predict hourly traffic flows up to and into the near future, using historical data collected from the Hong Kong Annual Traffic Census (ATC). Two parametric (auto-regressive integrated moving-average and neural network) and two non-parametric (non-parametric regression (NPR) and Gaussian maximum likelihood (GML)) models were employed and evaluated. Comparisons of the prediction errors at the selected ATC core station showed that the non-parametric models were more promising for predicting hourly traffic flows at the selected ATC station and did not require any extensive model calibration. Further analysis encompassing 87 ATC stations revealed that the NPR is likely to react to unexpected changes more effectively than the GML method, while the GML model performs better under steady traffic flows. Bearing in mind the dynamic nature of the traffic pattern in Hong Kong, the NPR model is recommended as the most suitable model for short term prediction of hourly traffic flows.

• Availability:
  • Find a library where document is available. Order URL: http://worldcat.org/issn/00494488
• Authors:
  • Lam, William H K
  • Tang, Y F
  • Chan, K S
  • Tam, Mei-Lam
• Publication Date: 2006-5

Language

• English

Media Info

• Media Type: Print
• Features: Figures; References; Tables;
• Pagination: pp 291-310
• Serial:
  • Transportation
  • Volume: 33
  • Issue Number: 3
  • Publisher: Springer
  • ISSN: 0049-4488
  • EISSN: 1572-9435
  • Serial URL: http://link.springer.com/journal/11116

Subject/Index Terms

• TRT Terms: Mathematical prediction; Maximum likelihood method; Neural networks; Nonparametric analysis; Parametric analysis; Regression analysis; Traffic counting stations; Traffic counts; Traffic data; Traffic flow; Traffic forecasting
• Identifier Terms: ARMA (Auto-Regressive Moving Average model)
• Geographic Terms: Hong Kong (China)
• Subject Areas: Data and Information Technology; Highways; Operations and Traffic Management; Planning and Forecasting; I71: Traffic Theory; I72: Traffic and Transport Planning;

Filing Info

• Accession Number: 01029691
• Record Type: Publication
• Files: TRIS
• Created Date: Jul 26 2006 9:13AM