MCAGCN: Multi‐component attention graph convolutional neural network for road travel time prediction

Abstract With the development of intelligent transportation technology, road travel time prediction has become an important research direction. Owing to the complex periodic dependence and non‐linear features of road travel time series, achieving accurate and effective predictions remains a challeng...

Full description

Bibliographic Details
Main Authors: Zhihua Zhao, Li Chao, Xue Zhang, Nengfu Xie, Qingtian Zeng
Format: Article
Language:English
Published: Wiley 2024-01-01
Series:IET Intelligent Transport Systems
Subjects:
Online Access:https://doi.org/10.1049/itr2.12440
_version_ 1827381592259035136
author Zhihua Zhao
Li Chao
Xue Zhang
Nengfu Xie
Qingtian Zeng
author_facet Zhihua Zhao
Li Chao
Xue Zhang
Nengfu Xie
Qingtian Zeng
author_sort Zhihua Zhao
collection DOAJ
description Abstract With the development of intelligent transportation technology, road travel time prediction has become an important research direction. Owing to the complex periodic dependence and non‐linear features of road travel time series, achieving accurate and effective predictions remains a challenging task. Most existing traffic sequence prediction methods lack modelling of the dynamic correlation between multiple period information, resulting in unsatisfactory prediction results. To address this, a multi‐component attention graph convolutional network (MCAGCN) is proposed for road travel time prediction. First, the spatial‐temporal features of three historical components (hourly, daily and weekly) are modelled individually. A skip attention layer is then used to fuse multi‐scale spatial‐temporal features to enhance the model's feature extraction capabilities. Secondly, a component attention layer is proposed to calculate the correlation between different components using the temporal features of the prediction moment, to achieve dynamic modelling between different period information. The experimental results on the Tianchi, METR‐LA, and PeMS‐BAY datasets, which are real‐world traffic forecasting datasets, demonstrate the superiority of MCAGCN.
first_indexed 2024-03-08T13:58:31Z
format Article
id doaj.art-e31abcf463814809bad56d7fe0d272fb
institution Directory Open Access Journal
issn 1751-956X
1751-9578
language English
last_indexed 2024-03-08T13:58:31Z
publishDate 2024-01-01
publisher Wiley
record_format Article
series IET Intelligent Transport Systems
spelling doaj.art-e31abcf463814809bad56d7fe0d272fb2024-01-15T09:12:38ZengWileyIET Intelligent Transport Systems1751-956X1751-95782024-01-0118113915310.1049/itr2.12440MCAGCN: Multi‐component attention graph convolutional neural network for road travel time predictionZhihua Zhao0Li Chao1Xue Zhang2Nengfu Xie3Qingtian Zeng4College of Electronic and Information Engineering Shandong University of Science and Technology Qingdao ChinaCollege of Electronic and Information Engineering Shandong University of Science and Technology Qingdao ChinaCollege of Computer Science and Engineering Shandong University of Science and Technology Qingdao ChinaKey Laboratory of Agricultural Blockchain Application Ministry of Agriculture and Rural Affairs Agricultural Information Institute Chinese Academy of Agricultural Sciences Beijing ChinaCollege of Electronic and Information Engineering Shandong University of Science and Technology Qingdao ChinaAbstract With the development of intelligent transportation technology, road travel time prediction has become an important research direction. Owing to the complex periodic dependence and non‐linear features of road travel time series, achieving accurate and effective predictions remains a challenging task. Most existing traffic sequence prediction methods lack modelling of the dynamic correlation between multiple period information, resulting in unsatisfactory prediction results. To address this, a multi‐component attention graph convolutional network (MCAGCN) is proposed for road travel time prediction. First, the spatial‐temporal features of three historical components (hourly, daily and weekly) are modelled individually. A skip attention layer is then used to fuse multi‐scale spatial‐temporal features to enhance the model's feature extraction capabilities. Secondly, a component attention layer is proposed to calculate the correlation between different components using the temporal features of the prediction moment, to achieve dynamic modelling between different period information. The experimental results on the Tianchi, METR‐LA, and PeMS‐BAY datasets, which are real‐world traffic forecasting datasets, demonstrate the superiority of MCAGCN.https://doi.org/10.1049/itr2.12440data analysisdata mininggraph theory
spellingShingle Zhihua Zhao
Li Chao
Xue Zhang
Nengfu Xie
Qingtian Zeng
MCAGCN: Multi‐component attention graph convolutional neural network for road travel time prediction
IET Intelligent Transport Systems
data analysis
data mining
graph theory
title MCAGCN: Multi‐component attention graph convolutional neural network for road travel time prediction
title_full MCAGCN: Multi‐component attention graph convolutional neural network for road travel time prediction
title_fullStr MCAGCN: Multi‐component attention graph convolutional neural network for road travel time prediction
title_full_unstemmed MCAGCN: Multi‐component attention graph convolutional neural network for road travel time prediction
title_short MCAGCN: Multi‐component attention graph convolutional neural network for road travel time prediction
title_sort mcagcn multi component attention graph convolutional neural network for road travel time prediction
topic data analysis
data mining
graph theory
url https://doi.org/10.1049/itr2.12440
work_keys_str_mv AT zhihuazhao mcagcnmulticomponentattentiongraphconvolutionalneuralnetworkforroadtraveltimeprediction
AT lichao mcagcnmulticomponentattentiongraphconvolutionalneuralnetworkforroadtraveltimeprediction
AT xuezhang mcagcnmulticomponentattentiongraphconvolutionalneuralnetworkforroadtraveltimeprediction
AT nengfuxie mcagcnmulticomponentattentiongraphconvolutionalneuralnetworkforroadtraveltimeprediction
AT qingtianzeng mcagcnmulticomponentattentiongraphconvolutionalneuralnetworkforroadtraveltimeprediction