A Spatial–Temporal Multitask Collaborative Learning Model for Multistep Traffic Flow Prediction

Kun Tang, Shuyan Chen, Aemal J. Khattak

Research output: Contribution to journalArticle

2 Citations (Scopus)

Abstract

Traffic flow prediction is a fundamental capability for successful deployment of intelligent transportation systems. Traditionally, multiple related prediction tasks are undertaken individually, without considering the relationships among the tasks. This paper presents a spatial–temporal multitask collaborative learning model for multistep traffic flow prediction. The novel approach learns multiple related prediction tasks collaboratively by extracting and utilizing appropriate shared information across tasks. First, each traffic flow prediction problem is formulated as a supervised machine-learning task. Next, the sparse features shared across multiple tasks are learned by solving a regularized optimization problem. To deal with the non-convex and non-smooth challenges, the optimization problem is then transformed into an equivalent convex problem. Finally, the global optimal solution of the convex problem is found by solving a variation of this problem using an alternating minimization algorithm. The proposed model incorporates both the spatial correlation between different observed stations and the intrinsic relationship between different traffic flow parameters, as well as the coarse-grain temporal correlation between different days in a week and the fine-grain temporal correlation between different prediction steps. Application of the proposed model to a real case study for SR180-E freeway in Fresno, California showed its effectiveness, robustness and advantages for multistep traffic flow prediction.

Original languageEnglish (US)
Pages (from-to)1-13
Number of pages13
JournalTransportation Research Record
Volume2672
Issue number45
DOIs
StatePublished - Dec 1 2018

Fingerprint

Highway systems
Learning systems

ASJC Scopus subject areas

  • Civil and Structural Engineering
  • Mechanical Engineering

Cite this

A Spatial–Temporal Multitask Collaborative Learning Model for Multistep Traffic Flow Prediction. / Tang, Kun; Chen, Shuyan; Khattak, Aemal J.

In: Transportation Research Record, Vol. 2672, No. 45, 01.12.2018, p. 1-13.

Research output: Contribution to journalArticle

@article{5f7ed896fbbe40a9914ea5250cfe176d,
title = "A Spatial–Temporal Multitask Collaborative Learning Model for Multistep Traffic Flow Prediction",
abstract = "Traffic flow prediction is a fundamental capability for successful deployment of intelligent transportation systems. Traditionally, multiple related prediction tasks are undertaken individually, without considering the relationships among the tasks. This paper presents a spatial–temporal multitask collaborative learning model for multistep traffic flow prediction. The novel approach learns multiple related prediction tasks collaboratively by extracting and utilizing appropriate shared information across tasks. First, each traffic flow prediction problem is formulated as a supervised machine-learning task. Next, the sparse features shared across multiple tasks are learned by solving a regularized optimization problem. To deal with the non-convex and non-smooth challenges, the optimization problem is then transformed into an equivalent convex problem. Finally, the global optimal solution of the convex problem is found by solving a variation of this problem using an alternating minimization algorithm. The proposed model incorporates both the spatial correlation between different observed stations and the intrinsic relationship between different traffic flow parameters, as well as the coarse-grain temporal correlation between different days in a week and the fine-grain temporal correlation between different prediction steps. Application of the proposed model to a real case study for SR180-E freeway in Fresno, California showed its effectiveness, robustness and advantages for multistep traffic flow prediction.",
author = "Kun Tang and Shuyan Chen and Khattak, {Aemal J.}",
year = "2018",
month = "12",
day = "1",
doi = "10.1177/0361198118790330",
language = "English (US)",
volume = "2672",
pages = "1--13",
journal = "Transportation Research Record",
issn = "0361-1981",
publisher = "US National Research Council",
number = "45",

}

TY - JOUR

T1 - A Spatial–Temporal Multitask Collaborative Learning Model for Multistep Traffic Flow Prediction

AU - Tang, Kun

AU - Chen, Shuyan

AU - Khattak, Aemal J.

PY - 2018/12/1

Y1 - 2018/12/1

N2 - Traffic flow prediction is a fundamental capability for successful deployment of intelligent transportation systems. Traditionally, multiple related prediction tasks are undertaken individually, without considering the relationships among the tasks. This paper presents a spatial–temporal multitask collaborative learning model for multistep traffic flow prediction. The novel approach learns multiple related prediction tasks collaboratively by extracting and utilizing appropriate shared information across tasks. First, each traffic flow prediction problem is formulated as a supervised machine-learning task. Next, the sparse features shared across multiple tasks are learned by solving a regularized optimization problem. To deal with the non-convex and non-smooth challenges, the optimization problem is then transformed into an equivalent convex problem. Finally, the global optimal solution of the convex problem is found by solving a variation of this problem using an alternating minimization algorithm. The proposed model incorporates both the spatial correlation between different observed stations and the intrinsic relationship between different traffic flow parameters, as well as the coarse-grain temporal correlation between different days in a week and the fine-grain temporal correlation between different prediction steps. Application of the proposed model to a real case study for SR180-E freeway in Fresno, California showed its effectiveness, robustness and advantages for multistep traffic flow prediction.

AB - Traffic flow prediction is a fundamental capability for successful deployment of intelligent transportation systems. Traditionally, multiple related prediction tasks are undertaken individually, without considering the relationships among the tasks. This paper presents a spatial–temporal multitask collaborative learning model for multistep traffic flow prediction. The novel approach learns multiple related prediction tasks collaboratively by extracting and utilizing appropriate shared information across tasks. First, each traffic flow prediction problem is formulated as a supervised machine-learning task. Next, the sparse features shared across multiple tasks are learned by solving a regularized optimization problem. To deal with the non-convex and non-smooth challenges, the optimization problem is then transformed into an equivalent convex problem. Finally, the global optimal solution of the convex problem is found by solving a variation of this problem using an alternating minimization algorithm. The proposed model incorporates both the spatial correlation between different observed stations and the intrinsic relationship between different traffic flow parameters, as well as the coarse-grain temporal correlation between different days in a week and the fine-grain temporal correlation between different prediction steps. Application of the proposed model to a real case study for SR180-E freeway in Fresno, California showed its effectiveness, robustness and advantages for multistep traffic flow prediction.

UR - http://www.scopus.com/inward/record.url?scp=85052324447&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85052324447&partnerID=8YFLogxK

U2 - 10.1177/0361198118790330

DO - 10.1177/0361198118790330

M3 - Article

AN - SCOPUS:85052324447

VL - 2672

SP - 1

EP - 13

JO - Transportation Research Record

JF - Transportation Research Record

SN - 0361-1981

IS - 45

ER -