TRB Pubsindex
Text Size:
x

« Prev Next »

Return to Results | New Search

Bookmark and Share

Title:

A Meta-Learner Ensemble Framework for Real-Time Short-Term Traffic Speed Forecasting

Accession Number:

01764213

Record Type:

Component

Abstract:

This study presents a novel ensemble learning approach called stacking for real-time short-term traffic state prediction. The approach consists of a level-1 meta-learner that combines predictions from several different level-0 models by making use of the past performance information of the level-0 models. The meta-learner consists of least square estimation procedure with non-negatively constraints on past predictions and observed traffic state information. The parameters obtained from the meta-learner are then used to assign weights to the predictions made by level-0 models to obtain the final prediction. The proposed approach is general enough and could be applied in a variety of different situations where longitudinal data feeds might be available, ranging from the demand for certain products and services to freight container demand. The authors apply the proposed approach to one-day traffic speed data from 13 different loop detectors located on interstate 435 in Kansas City in the state of Missouri. The loop detectors provide space mean speed information at 1-minute interval and the authors used this data to predict traffic space mean speed 15 minutes and 60 minutes in advance. The authors' results indicate that the proposed approach outperforms all level-0 models and provides significantly better results in both breakdown and non-breakdown states of traffic flow.

Supplemental Notes:

This paper was sponsored by TRB committee AED50 Standing Committee on Artificial Intelligence and Advanced Computing Applications.

Report/Paper Numbers:

TRBAM-21-02198

Language:

English

Corporate Authors:

Transportation Research Board

Authors:

Tahlyan, Divyakant
Kim, Eunhye
Mahmassani, Hani S

ORCID 0000-0002-8443-8928

Pagination:

17p

Publication Date:

2021

Conference:

Transportation Research Board 100th Annual Meeting

Location: Washington DC, United States
Date: 2021-1-5 to 2021-1-29
Sponsors: Transportation Research Board; Transportation Research Board

Media Type:

Web

Features:

Figures; References; Tables

Geographic Terms:

Kansas City (Missouri)

Subject Areas:

Highways; Operations and Traffic Management; Planning and Forecasting

Source Data:

Transportation Research Board Annual Meeting 2021 Paper #TRBAM-21-02198

Files:

TRIS, TRB, ATRI

Created Date:

Dec 23 2020 11:22AM