TRB Pubsindex
Text Size:

Title:

Multiple-Model Combined Forecasting Method for Online Prediction of Border Crossing Traffic at Peace Bridge

Accession Number:

01371095

Record Type:

Component

Abstract:

This paper presents a novel forecasting method for the on-line, short-term prediction of hourly traffic volumes at the Peace Bridge, one of the Niagara Frontier busiest border crossings. The method is based on combining forecasts from traditional time series analysis, specifically the Seasonal Autoregressive Integrated Moving Average (SARIMA) model, with forecasts made by Support Vector Regression (SVR). The two models’ forecasts are combined using: (1) a simple fixed weight procedure; and (2) the fuzzy adaptive variable weight method, based on the Fresh Degree Function. Based on an analysis of the diurnal distribution of traffic volumes, six separate classes are defined and individual models are developed for weekdays (Monday - Thursday), Fridays, Saturdays, Sundays, holidays and game days. The study’s findings appear to confirm the hypothesis that, while the SARIMA model does a good job capturing the linear characteristics of the data (e.g., seasonality and trend), SVR appears to outperform SARIMA in modeling the data’s nonlinear aspects. The study also shows that combining forecasts from the two models, especially using the fuzzy adaptive variable weight method, yields excellent prediction performance, with values for the Mean Absolute Percent Error in the predictions of only about 7%. Key Words: Seasonal Autoregressive Integrated Moving Average (SARIMA); Support Vector Machines (SVM); fuzzy adaptive variable weight method; short-term traffic volume prediction; border crossing.

Supplemental Notes:

This paper was sponsored by TRB committee ABJ70 Artificial Intelligence and Advanced Computing Applications

Monograph Accession #:

01362476

Report/Paper Numbers:

12-3398

Language:

English

Corporate Authors:

Transportation Research Board

500 Fifth Street, NW
Washington, DC 20001 United States

Authors:

Lin, Lei
Sadek, Adel W
Wang, Qian

Pagination:

15p

Publication Date:

2012

Conference:

Transportation Research Board 91st Annual Meeting

Location: Washington DC, United States
Date: 2012-1-22 to 2012-1-26
Sponsors: Transportation Research Board

Media Type:

Digital/other

Features:

Figures; References; Tables

Subject Areas:

Data and Information Technology; Highways; Operations and Traffic Management; Planning and Forecasting; I70: Traffic and Transport; I72: Traffic and Transport Planning

Source Data:

Transportation Research Board Annual Meeting 2012 Paper #12-3398

Files:

TRIS, TRB

Created Date:

Feb 8 2012 5:16PM