Forecasting of Short-Term Traffic Flow Based on SVR with SFLA

The forecasting of accurate short-term traffic flow is the key issue in intelligent transportation systems (ITS), and it is also an important prerequisite of real-time traffic signal control, traffic assignment, route guidance, incident detection, etc. In this paper, a shuffled frog-leaping algorithm (SFLA)-support vector regression (SVR) forecasting model of short-term traffic flow is proposed. The SVR-SFLA model is combined due to the features of nonlinearity, complexity and randomness of short-term traffic flow. Support vector regression has been successfully employed to solve the regression problem of nonlinearity and small samples, but it is very crucial to select the appropriate parameters of learning accuracy and generalization performance of SVR. The shuffled frog-leaping algorithm is used to determine the free parameters of support vector regression. Two adjacent intersections of a typical urban road network are selected as the study object. The experimental results demonstrate that SFLA-SVR outperforms the back propagation (BP) neural-network model in prediction accuracy.

• Record URL:
  https://doi.org/10.1061/41184(419)58
• Availability:
  • Find a library where document is available. Order URL: http://worldcat.org/isbn/9780784411841
• Supplemental Notes:
  • Copyright © 2011 ASCE
• Corporate Authors:

  American Society of Civil Engineers

  1801 Alexander Bell Drive
  Reston, VA  United States  20191-4400
• Authors:
  • Ding, Hongfei
  • Lu, Ming
  • Tang, Li
• Conference:
  • Third International Conference on Transportation Engineering (ICTE)
  • Location: Chengdu , China
  • Date: 2011-7-23 to 2011-7-25
• Publication Date: 2011

Language

• English

Media Info

• Media Type: Digital/other
• Features: Figures; References; Tables;
• Pagination: pp 346-351
• Monograph Title: ICTE 2011

Subject/Index Terms

• TRT Terms: Algorithms; Mathematical prediction; Neural networks; Regression analysis; Traffic flow; Traffic forecasting; Traffic models
• Uncontrolled Terms: Support vector regression
• Subject Areas: Highways; Operations and Traffic Management; Planning and Forecasting; I71: Traffic Theory;

Filing Info

• Accession Number: 01449395
• Record Type: Publication
• ISBN: 9780784411841
• Files: TRIS, ASCE
• Created Date: Oct 18 2012 11:19AM