TRAFFIC FLOW FORECASTING USING APPROXIMATE NEAREST NEIGHBOR NONPARAMETRIC REGRESSION

The purpose of this research is to enhance nonparametric regression (NPR) for use in real-time systems by first reducing execution time using advanced data structures and imprecise computations and then developing a methodology for applying NPR. Due to the nature of the enhancements to nonparametric regression, each application of NPR will be specific for each system. This research, therefore, provides general guidelines for deploying nonparametric regression, similar to how Box and Jenkins (1970) provided a methodology for conducting time series analysis

  • Record URL:
  • Supplemental Notes:
    • Publication Date: December 2000. National ITS Implementation Research Center, George Mason University, Fairfax VA. Format: website
  • Corporate Authors:

    National ITS Implementation Research Center

    ,    
  • Authors:
    • Oswald, R K
    • Scherer, William T
    • Smith, Brian Lee
  • Publication Date: 2000

Language

  • English

Subject/Index Terms

Filing Info

  • Accession Number: 00962443
  • Record Type: Publication
  • Source Agency: UC Berkeley Transportation Library
  • Report/Paper Numbers: UVA-CE-ITS-01-4
  • Files: PATH, NTL
  • Created Date: Sep 2 2003 12:00AM