A spatio-temporal ensemble method for large-scale traffic state prediction

Yang Liu, Zhiyuan Liu, Hai L. Vu, Cheng Lyu

Research output: Contribution to journalArticleResearchpeer-review

Abstract

How to effectively ensemble multiple models while leveraging the spatio-temporal information is a challenging but practical problem. However, there is no existing ensemble method explicitly designed for spatio-temporal data. In this paper, a fully convolutional model based on semantic segmentation technology is proposed, termed as spatio-temporal ensemble net. The proposed method is suitable for grid-based spatio-temporal prediction in dense urban areas. Experiments demonstrate that through spatio-temporal ensemble net, multiple traffic state prediction base models can be combined to improve the prediction accuracy.

Original languageEnglish
Number of pages19
JournalComputer-Aided Civil and Infrastructure Engineering
DOIs
Publication statusAccepted/In press - 23 Jun 2019

Cite this

@article{9c80718d0db7492a8efc13f460db384d,
title = "A spatio-temporal ensemble method for large-scale traffic state prediction",
abstract = "How to effectively ensemble multiple models while leveraging the spatio-temporal information is a challenging but practical problem. However, there is no existing ensemble method explicitly designed for spatio-temporal data. In this paper, a fully convolutional model based on semantic segmentation technology is proposed, termed as spatio-temporal ensemble net. The proposed method is suitable for grid-based spatio-temporal prediction in dense urban areas. Experiments demonstrate that through spatio-temporal ensemble net, multiple traffic state prediction base models can be combined to improve the prediction accuracy.",
author = "Yang Liu and Zhiyuan Liu and Vu, {Hai L.} and Cheng Lyu",
year = "2019",
month = "6",
day = "23",
doi = "10.1111/mice.12459",
language = "English",
journal = "Computer-Aided Civil and Infrastructure Engineering",
issn = "1093-9687",
publisher = "Wiley-Blackwell",

}

A spatio-temporal ensemble method for large-scale traffic state prediction. / Liu, Yang; Liu, Zhiyuan; Vu, Hai L.; Lyu, Cheng.

In: Computer-Aided Civil and Infrastructure Engineering, 23.06.2019.

Research output: Contribution to journalArticleResearchpeer-review

TY - JOUR

T1 - A spatio-temporal ensemble method for large-scale traffic state prediction

AU - Liu, Yang

AU - Liu, Zhiyuan

AU - Vu, Hai L.

AU - Lyu, Cheng

PY - 2019/6/23

Y1 - 2019/6/23

N2 - How to effectively ensemble multiple models while leveraging the spatio-temporal information is a challenging but practical problem. However, there is no existing ensemble method explicitly designed for spatio-temporal data. In this paper, a fully convolutional model based on semantic segmentation technology is proposed, termed as spatio-temporal ensemble net. The proposed method is suitable for grid-based spatio-temporal prediction in dense urban areas. Experiments demonstrate that through spatio-temporal ensemble net, multiple traffic state prediction base models can be combined to improve the prediction accuracy.

AB - How to effectively ensemble multiple models while leveraging the spatio-temporal information is a challenging but practical problem. However, there is no existing ensemble method explicitly designed for spatio-temporal data. In this paper, a fully convolutional model based on semantic segmentation technology is proposed, termed as spatio-temporal ensemble net. The proposed method is suitable for grid-based spatio-temporal prediction in dense urban areas. Experiments demonstrate that through spatio-temporal ensemble net, multiple traffic state prediction base models can be combined to improve the prediction accuracy.

UR - http://www.scopus.com/inward/record.url?scp=85068062922&partnerID=8YFLogxK

U2 - 10.1111/mice.12459

DO - 10.1111/mice.12459

M3 - Article

JO - Computer-Aided Civil and Infrastructure Engineering

JF - Computer-Aided Civil and Infrastructure Engineering

SN - 1093-9687

ER -