Traffic Flow Prediction Based on Wavelet Analysis and Artificial Neural Network

The time series of traffic flow can be deconstructed into several stationary detailed time series. A tendency time series according to the algorithm of this multi-scale is presented in this paper. Decomposed time series are forecasted with BP neural network to obtain the prediction series. Then the forecasting results are reconstructed by wavelet theory. The real detected traffic data are used to testify the precision of the model; the results show that the method of coupling multi-scale decomposition and BP neural network has advantages over the traditional BP neural network in predicted qualification-rate.

• Record URL:
  https://doi.org/10.1061/41139(387)493
• Availability:
  • Find a library where document is available. Order URL: http://worldcat.org/isbn/9780784411391
• Supplemental Notes:
  • © 2010 American Society of Civil Engineers.
• Corporate Authors:

  American Society of Civil Engineers

  1801 Alexander Bell Drive
  Reston, VA  United States  20191-4400
• Authors:
  • Li, Hongbo
  • Peng, Yong
• Conference:
  • International Conference of Logistics Engineering and Management (ICLEM) 2010
  • Location: Chengdu , China
  • Date: 2010-10-8 to 2010-10-10
• Publication Date: 2010-9

Language

• English

Media Info

• Media Type: Web
• Features: References;
• Pagination: pp 3528-3534
• Monograph Title: ICLEM 2010: Logistics For Sustained Economic Development: Infrastructure, Information, Integration

Subject/Index Terms

• TRT Terms: Forecasting; Neural networks; Real time information; Time series analysis; Traffic data; Traffic flow; Wavelets
• Subject Areas: Highways; Operations and Traffic Management; I73: Traffic Control;

Filing Info

• Accession Number: 01525844
• Record Type: Publication
• ISBN: 9780784411391
• Files: TRIS, ASCE
• Created Date: Nov 12 2013 1:53PM