Traffic Flow Forecasting Using Approximate Nearest Neighbor Nonparametric Regression

Details

• Creators:
  Oswald, R. K. ; Scherer, William T. ; Smith, Brian L., 1967-
• Corporate Contributors:
  University of Virginia. Center for Transportation Studies ; National ITS Implementation Research Center (Va.)
• Subject/TRT Terms:
  • Deployment
  • Methodology
  • Decision support systems
  • Guidelines
  • Traffic flow
  • Traffic forecasting
  • Nonparametric regression (NPR)
  • Real time systems
• Publication/ Report Number:
  UVA-CE-ITS_01-4
• Resource Type:
  Tech Report
• Geographical Coverage:
  United States
• Corporate Publisher:
  University of Virginia. Center for Transportation Studies
• Abstract:
  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.
• Format:
  PDF
• Download URL:
  https://rosap.ntl.bts.gov/view/dot/15834/dot_15834_DS1.pdf
• File Type:
  [PDF - 743.57 KB]
• Collection(s):
  US Transportation Collection
• Main Document Checksum:
  urn:sha-512:4db2454a4fecc31bb3acda0263d4edc2297869e8184385a73482587a23e62d571650c7ca479bba109714533f468c54da609fb9507a82422e29a63cee80c001da