A novel residual graph convolution deep learning model for short-term network-based traffic forecasting

doi:10.1080/13658816.2019.1697879

CORC > 海洋研究所 > 中国科学院海洋研究所 > 海洋环流与波动重点实验室

	A novel residual graph convolution deep learning model for short-term network-based traffic forecasting
	Zhang, Yang 4,5; Cheng, Tao 4; Ren, Yibin 1,3; Xie, Kun 2
刊名	INTERNATIONAL JOURNAL OF GEOGRAPHICAL INFORMATION SCIENCE
	2019-12-04
卷号	34 期号:5 页码:27
关键词	Short-term traffic forecasting spatial-temporal dependency network topology graph convolution residual long short-term memory
ISSN号	1365-8816
DOI	10.1080/13658816.2019.1697879
通讯作者	Zhang, Yang(yang.zhang.16@ucl.ac.uk)
英文摘要	Short-term traffic forecasting on large street networks is significant in transportation and urban management, such as real-time route guidance and congestion alleviation. Nevertheless, it is very challenging to obtain high prediction accuracy with reasonable computational cost due to the complex spatial dependency on the traffic network and the time-varying traffic patterns. To address these issues, this paper develops a residual graph convolution long short-term memory (RGC-LSTM) model for spatial-temporal data forecasting considering the network topology. This model integrates a new graph convolution operator for spatial modelling on networks and a residual LSTM structure for temporal modelling considering multiple periodicities. The proposed model has few parameters, low computational complexity, and a fast convergence rate. The framework is evaluated on both the 10-min traffic speed data from Shanghai, China and the 5-min Caltrans Performance Measurement System (PeMS) traffic flow data. Experiments show the advantages of the proposed approach over various state-of-the-art baselines, as well as consistent performance across different datasets.
资助项目	UK Economic and Social Research Council[ES/L011840/1] ; China Scholarship Council[201603170309] ; University College London
WOS研究方向	Computer Science ; Geography ; Physical Geography ; Information Science & Library Science
语种	英语
出版者	TAYLOR & FRANCIS LTD
WOS记录号	WOS:000500113700001
内容类型	期刊论文
版本	出版稿
源URL	[http://ir.qdio.ac.cn/handle/337002/163861]
专题	海洋研究所_海洋环流与波动重点实验室
通讯作者	Zhang, Yang
作者单位	1.Chinese Acad Sci, Ctr Ocean Megasci, Qingdao, Shandong, Peoples R China 2.Old Dominion Univ, Dept Civil & Environm Engn, Norfolk, VA USA 3.Chinese Acad Sci, Inst Oceanol, CAS Key Lab Ocean Circulat & Waves, Qingdao, Shandong, Peoples R China 4.UCL, Dept Civil Environm & Geomat Engn, SpaceTimeLab Big Data Analyt, London, England 5.Natl Univ Def Technol, Coll Syst Engn, Changsha, Hunan, Peoples R China
推荐引用方式 GB/T 7714	Zhang, Yang,Cheng, Tao,Ren, Yibin,et al. A novel residual graph convolution deep learning model for short-term network-based traffic forecasting[J]. INTERNATIONAL JOURNAL OF GEOGRAPHICAL INFORMATION SCIENCE,2019,34(5):27.
APA	Zhang, Yang,Cheng, Tao,Ren, Yibin,&Xie, Kun.(2019).A novel residual graph convolution deep learning model for short-term network-based traffic forecasting.INTERNATIONAL JOURNAL OF GEOGRAPHICAL INFORMATION SCIENCE,34(5),27.
MLA	Zhang, Yang,et al."A novel residual graph convolution deep learning model for short-term network-based traffic forecasting".INTERNATIONAL JOURNAL OF GEOGRAPHICAL INFORMATION SCIENCE 34.5(2019):27.