A deep learning traffic flow prediction framework based on multi-channel graph convolution

doi:10.1080/03081060.2021.1992180

IR > 计算机与通信学院

	A deep learning traffic flow prediction framework based on multi-channel graph convolution
	Zhao, Yuanmeng; Cao, Jie; Zhang, Hong; Liu, Zongli
	2021-11-17
发表期刊	TRANSPORTATION PLANNING AND TECHNOLOGY
ISSN	0308-1060
卷号	44 期号:8 页码:887-900
摘要	Accurate and timely traffic flow prediction is a critical part of the steps to alleviate traffic congestion. Fully considering the spatial-temporal dependencies of traffic flow is the key to accurately predicting traffic flow. Addressing the problem that traditional methods are difficult to capture the complex spatial-temporal dependence of urban traffic flow, and therefore cannot meet the accuracy requirements for medium and long-term prediction tasks, this paper uses Graph Convolution (GCN) and Long Short-Term Memory (LSTM) methods to capture time and space dependence through data analysis, and proposes a new type of deep learning model MCGC-LSTM. GCN is utilized to learn spatial dependence by analyzing the topological structure of an urban road traffic network, while LSTM is utilized to learn temporal dependence by analyzing the dynamic changes of traffic flow. The experimental results based on a real data set show that this method can achieve better prediction accuracy.
关键词	Traffic flow deep learning graph convolution (GCN) Long Short-Term Memory (LSTM) spatial-temporal features
DOI	10.1080/03081060.2021.1992180
收录类别	SCIE
语种	英语
WOS研究方向	Transportation
WOS类目	Transportation Science & Technology
WOS记录号	WOS:000721171800001
出版者	TAYLOR & FRANCIS LTD
来源库	WOS
引用统计	被引频次[WOS]：0 [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	https://ir.lut.edu.cn/handle/2XXMBERH/150049
专题	计算机与通信学院
通讯作者	Cao, Jie
作者单位	Lanzhou Univ Technol, Coll Comp & Commun, Pengjiaping St, Lanzhou, Gansu, Peoples R China
第一作者单位	计算机与通信学院
通讯作者单位	计算机与通信学院
第一作者的第一单位	计算机与通信学院
推荐引用方式 GB/T 7714	Zhao, Yuanmeng,Cao, Jie,Zhang, Hong,et al. A deep learning traffic flow prediction framework based on multi-channel graph convolution[J]. TRANSPORTATION PLANNING AND TECHNOLOGY,2021,44(8):887-900.
APA	Zhao, Yuanmeng,Cao, Jie,Zhang, Hong,&Liu, Zongli.(2021).A deep learning traffic flow prediction framework based on multi-channel graph convolution.TRANSPORTATION PLANNING AND TECHNOLOGY,44(8),887-900.
MLA	Zhao, Yuanmeng,et al."A deep learning traffic flow prediction framework based on multi-channel graph convolution".TRANSPORTATION PLANNING AND TECHNOLOGY 44.8(2021):887-900.