Multicomponent Spatial-Temporal Graph Attention Convolution Networks for Traffic Prediction with Spatially Sparse Data

doi:10.1155/2021/9134942

	Multicomponent Spatial-Temporal Graph Attention Convolution Networks for Traffic Prediction with Spatially Sparse Data
	Liu, Shaohua 1; Dai, Shijun 1; Sun, Jingkai 1; Mao, Tianlu 2; Zhao, Junsuo 3; Zhang, Heng 3
	2021-12-23
发表期刊	COMPUTATIONAL INTELLIGENCE AND NEUROSCIENCE
ISSN	1687-5265
卷号	2021 页码:12
摘要	Predicting traffic data on traffic networks is essential to transportation management. It is a challenging task due to the complicated spatial-temporal dependency. The latest studies mainly focus on capturing temporal and spatial dependencies with spatially dense traffic data. However, when traffic data become spatially sparse, existing methods cannot capture sufficient spatial correlation information and thus fail to learn the temporal periodicity sufficiently. To address these issues, we propose a novel deep learning framework, Multi-component Spatial-Temporal Graph Attention Convolutional Networks (MSTGACN), for traffic prediction, and we successfully apply it to predicting traffic flow and speed with spatially sparse data. MSTGACN mainly consists of three independent components to model three types of periodic information. Each component in MSTGACN combines dilated causal convolution, graph convolution layer, and the weight-shared graph attention layer. Experimental results on three real-world traffic datasets, METR-LA, PeMS-BAY, and PeMSD7-sparse, demonstrate the superior performance of our method in the case of spatially sparse data.
DOI	10.1155/2021/9134942
收录类别	SCI
语种	英语
资助项目	Major Program of National Natural Science Foundation of China[91938301] ; National Natural Science Foundation of China[62002345]
WOS研究方向	Mathematical & Computational Biology ; Neurosciences & Neurology
WOS类目	Mathematical & Computational Biology ; Neurosciences
WOS记录号	WOS:000772625100005
出版者	HINDAWI LTD
引用统计	被引频次：3[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://119.78.100.204/handle/2XEOYT63/18923
专题	中国科学院计算技术研究所期刊论文_英文
通讯作者	Mao, Tianlu
作者单位	1.Beijing Univ Posts & Telecommun, Sch Elect Engn, Beijing 100876, Peoples R China 2.Chinese Acad Sci, Inst Comp Technol, Beijing Key Lab Mobile Comp & Pervas Device, Beijing 100190, Peoples R China 3.Chinese Acad Sci, Inst Software, Beijing 100190, Peoples R China
推荐引用方式 GB/T 7714	Liu, Shaohua,Dai, Shijun,Sun, Jingkai,et al. Multicomponent Spatial-Temporal Graph Attention Convolution Networks for Traffic Prediction with Spatially Sparse Data[J]. COMPUTATIONAL INTELLIGENCE AND NEUROSCIENCE,2021,2021:12.
APA	Liu, Shaohua,Dai, Shijun,Sun, Jingkai,Mao, Tianlu,Zhao, Junsuo,&Zhang, Heng.(2021).Multicomponent Spatial-Temporal Graph Attention Convolution Networks for Traffic Prediction with Spatially Sparse Data.COMPUTATIONAL INTELLIGENCE AND NEUROSCIENCE,2021,12.
MLA	Liu, Shaohua,et al."Multicomponent Spatial-Temporal Graph Attention Convolution Networks for Traffic Prediction with Spatially Sparse Data".COMPUTATIONAL INTELLIGENCE AND NEUROSCIENCE 2021(2021):12.