NTL Catalog Record

Title	Traffic flow forecasting using approximate nearest neighbor nonparametric regression
Record ID	23528
Personal Name Creator	Oswald, R. K.; Scherer, William T.; Smith, Brian L., 1967-
Corporate Contributor	Center for Transportation Studies (University of Virginia); National ITS Implementation Research Center
Publication Date	20001200
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.
TRT Terms	Deployment ; Methodology ; Decision support systems ; Guidelines ; Traffic flow ; Traffic forecasting
General Subjects	Nonparametric regression (NPR); Real time systems
Classification	NTL - INTELLIGENT TRANSPORTATION SYSTEMS - INTELLIGENT TRANSPORTATION SYSTEMS; NTL - OPERATIONS AND TRAFFIC CONTROLS - Traffic Flow
Report Number	UVA-CE-ITS_01-4
Resource type	Tech Report
URL	http://ntl.bts.gov/lib/23000/23500/23528/paper-Scherer-TrafficForecasting-Non-parametric.pdf
Format	PDF
Language:	English
Database	NTL Digital Repository

TRIS is a bibliographic database funded by sponsors of the Transportation Research Board (TRB), primarily the state departments of transportation and selected federal transportation agencies. TRIS Online is hosted by the National Transportation Library under a cooperative agreement between the Bureau of Transportation Statistics and TRB.