Dynamic Global-Local Spatial-Temporal Network for Traffic Speed Prediction

doi:10.1109/ACCESS.2020.3038380

	Dynamic Global-Local Spatial-Temporal Network for Traffic Speed Prediction
	Feng, Dong 1,2,3; Wu, Zhongcheng 1,3; Zhang, Jun 1,2,3; Wu, Ziheng 4
刊名	IEEE ACCESS
	2020
卷号	8
关键词	Correlation Convolution Feature extraction Predictive models Forecasting Market research Data models Traffic speed prediction spatial-temporal network graph convolutional network dynamic graph learning
ISSN号	2169-3536
DOI	10.1109/ACCESS.2020.3038380
通讯作者	Zhang, Jun(zhang_jun@hmfl.ac.cn)
英文摘要	Predicting traffic speed accurately is a very challenging task of the intelligent traffic system (ITS), due to the complex and dynamic spatial-temporal dependencies from both temporal and spatial aspects. There not only exits short-term local neighboring fluctuation and long-term global trend in temporal aspect, but also local and global correlations in spatial aspect. Most existing work focus on the local spatial-temporal dependencies, ignoring the global dynamic spatial-temporal corrections, which is comparably critical for traffic speed prediction. To address this problem, we propose a novel Dynamic Global-Local Spatial-Temporal Network(DGLSTNet) for traffic speed prediction, which consists of multiple spatial-temporal module considering the local and global information simultaneously from both temporal and spatial perspective. Each temporal module applies stacked dilated convolution block to exploit multi-scale local temporal information. Moreover, we empoly a global temporal attention block to capture global dependencies of temporal domain in an attention mechanism. In each spatial module, we not only learn the local but also focus on dynamic global spatial information learned by dymamic graph learning block. Combining the feature results from local and global perspective, the capability and expressiveness of traffic predicting model is improved. Experiment results on two real-world traffic datasets have demonstrated that our proposed model can effectively capture the comprehensive spatial-temporal dependencies and can achieve state-of-the-art prediction performance compared with the existing works.
资助项目	innovation and development project named the Internet of Vehicles Data Sharing Center and Operation Management Cloud Service Platform of Anhui Province, China ; Key Research and Development Program of Anhui Province, Research on Data Sharing Standardization of New Energy Vehicle[202004h07020031] ; Natural Science Foundation of Anhui Province[1908085QF253] ; High Magnetic Field Laboratory of Anhui Province
WOS关键词	MODEL
WOS研究方向	Computer Science ; Engineering ; Telecommunications
语种	英语
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
WOS记录号	WOS:000594429300001
资助机构	innovation and development project named the Internet of Vehicles Data Sharing Center and Operation Management Cloud Service Platform of Anhui Province, China ; Key Research and Development Program of Anhui Province, Research on Data Sharing Standardization of New Energy Vehicle ; Natural Science Foundation of Anhui Province ; High Magnetic Field Laboratory of Anhui Province
内容类型	期刊论文
源URL	[http://ir.hfcas.ac.cn:8080/handle/334002/105403]
专题	中国科学院合肥物质科学研究院
通讯作者	Zhang, Jun
作者单位	1.Univ Sci & Technol China, Sch Hefei Inst Phys Sci, Hefei 230026, Peoples R China 2.High Magnet Field Lab Anhui Prov, Hefei 230031, Peoples R China 3.Chinese Acad Sci, Hefei Inst Phys Sci, High Magnet Field Lab, Hefei 230031, Peoples R China 4.Anhui Univ Technol, Sch Elect & Informat Engn, Maanshan 243000, Peoples R China
推荐引用方式 GB/T 7714	Feng, Dong,Wu, Zhongcheng,Zhang, Jun,et al. Dynamic Global-Local Spatial-Temporal Network for Traffic Speed Prediction[J]. IEEE ACCESS,2020,8.
APA	Feng, Dong,Wu, Zhongcheng,Zhang, Jun,&Wu, Ziheng.(2020).Dynamic Global-Local Spatial-Temporal Network for Traffic Speed Prediction.IEEE ACCESS,8.
MLA	Feng, Dong,et al."Dynamic Global-Local Spatial-Temporal Network for Traffic Speed Prediction".IEEE ACCESS 8(2020).