TRB Pubsindex
Text Size:
x

« Prev Next »

Return to Results | New Search

Bookmark and Share

Title:

Spline-Based Multiregime Traffic Stream Models

Accession Number:

01126634

Record Type:

Component

Availability:

Transportation Research Board Business Office

500 Fifth Street, NW
Washington, DC 20001 United States

Abstract:

A methodological framework for developing multi-regime traffic stream models using B-spline regression is presented in this study. The new method is a data-driven approach, which does not presume any linearity and monotone at any regime, and non-linearity is automatically taken into account. The paper chooses up to quadratic B-spline as basis functions for fitting a three-regime speed-occupancy relationship. The determination of number of regimes is justified based on cluster analysis, trade-off between model accuracy and model complexity, and domain knowledge of traffic flow. The benefits of the new method include good data fitting performance, model flexibility and preservation of smoothness of the developed multi-regime traffic stream models.

Monograph Accession #:

01120148

Report/Paper Numbers:

09-2398

Language:

English

Corporate Authors:

Transportation Research Board

500 Fifth Street, NW
Washington, DC 20001 United States

Authors:

Sun, Lu
Zhou, Jie
Zhang, Yong

Pagination:

31p

Publication Date:

2009

Conference:

Transportation Research Board 88th Annual Meeting

Location: Washington DC, United States
Date: 2009-1-11 to 2009-1-15
Sponsors: Transportation Research Board

Media Type:

DVD

Features:

Appendices (1) ; Figures; Maps; References; Tables (2)

Subject Areas:

Highways; Planning and Forecasting; I72: Traffic and Transport Planning

Source Data:

Transportation Research Board Annual Meeting 2009 Paper #09-2398

Files:

TRIS, TRB

Created Date:

Jan 30 2009 6:45PM