文献类型: 外文期刊
作者: Wang, Yi 1 ; Jing, Changfeng 1 ; Xu, Shishuo 1 ; Guo, Tao 2 ;
作者机构: 1.Beijing Univ Civil Engn & Architecture, Sch Geomatics & Urban Spatial Informat, Beijing, Peoples R China
2.Sichuan Acad Agr Sci, Inst Remote Sensing Applicat, Chengdu 610066, Peoples R China
关键词: Traffic flow forecasting; Spatiotemporal graph neural network; Network deepening; Network degradation; Dynamic spatiotemporal correlation; Intelligent transportation systems
期刊名称:INFORMATION SCIENCES ( 影响因子:8.233; 五年影响因子:7.299 )
ISSN: 0020-0255
年卷期: 2022 年 607 卷
页码:
收录情况: SCI
摘要: Traffic flow forecasting is a crucial task in transportation and necessary for congestion mitigation, traffic control, and intelligent traffic management. Deep learning models can aid in high-accuracy traffic flow forecasting; however, the current research focuses only the ability of the model to capture dynamic spatiotemporal features, and studies on the effect of deeper network layers on spatiotemporal features-a critical factor affecting traffic flow forecasting accuracy-are limited. In this paper, we propose an attention-based spatiotemporal graph attention network (ASTGAT) model designed for network degradation and over-smoothing problems to investigate in-depth spatiotemporal information. Compared to other networks, ASTGAT can capture dynamic spatiotemporal correlations in data and deepen the network to improve prediction accuracy through multiple residual convolution and high-low feature concat. ASTGAT comprises three components that separately model the temporal relationships of the recent, daily, and weekly periods. Each component stacks multiple spatiotemporal blocks constructed using the attention mechanism, dilated gated convolution, and graph attention network. The graph and temporal attention layers capture spatiotemporal information dynamically, and the graph attention layer alleviates the over-smoothing phenomenon to deepen the network. The combined utilization of the attention mechanism and dilated gated convolution layer improves the medium and long temporal span prediction ability. We validated ASTGAT using two open highway data sets, and the results demonstrated that our ASTGAT model effectively extracts in-depth spatiotemporal information and the prediction results outperform those predicted by the current eight baselines. Our research is dedicated to establishing a better scientific basis for intelligent traffic management that can assist in decision making.(c) 2022 Elsevier Inc. All rights reserved.
- 相关文献
作者其他论文 更多>>
-
Detection of citrus diseases in complex backgrounds based on image-text multimodal fusion and knowledge assistance
作者:Qiu, Xia;Chen, Hongwen;Huang, Ping;Zhong, Dan;Guo, Tao;Pu, Changbin;Li, Zongnan;Liu, Yongling;Wang, Si;Qiu, Xia;Chen, Hongwen;Zhong, Dan;Guo, Tao;Pu, Changbin;Li, Zongnan;Wang, Si;Chen, Jin
关键词:citrus disease; deep learning; multimodal fusion; background diversity; knowledge assistance
-
Manganese and copper additions differently reduced cadmium uptake and accumulation in dwarf Polish wheat (Triticum polonicum L.)
作者:Chen, Xing;Yang, Shan;Ma, Jian;Huang, Yiwen;Wang, Yi;Li, Siyu;Long, Dan;Xiao, Xue;Wu, Dandan;Fan, Xing;Kang, Houyang;Zhou, Yonghong;Cheng, Yiran;Zeng, Jian;Li, Jun;Sha, Lina;Zhang, Haiqin
关键词:Cadmium; Wheat; Manganese; Copper; Uptake and accumulation
-
Transcriptomics and metagenomics of common cutworm (Spodoptera litura) and fall armyworm (Spodoptera frugiperda) demonstrate differences in detoxification and development
作者:Tang, Ruixiang;Liu, Fangyuan;Wang, Jiao;Wang, Lei;Li, Jing;Fan, Zhenxin;Yue, Bisong;Lan, Yue;Liu, Xu;Guo, Tao
关键词:Spodoptera litura; Spodoptera frugiperda; Developmental stages; Transcriptome; Metagenomics
-
Measurement of Urban-Rural Integration Level in Suburbs and Exurbs of Big Cities Based on Land-Use Change in Inland China: Chengdu
作者:Wang, Meimei;Yang, Yongchun;Guo, Tao
关键词:built-up land; urban-rural integration (URI); URI level; land-use change; path; Chengdu
-
Spatiotemporal modeling of land subsidence using a geographically weighted deep learning method based on PS-InSAR
作者:Li, Huijun;Zhu, Lin;Gong, Huili;Dai, Zhenxue;Guo, Tao;Guo, Gaoxuan;Wang, Jingbo;Teatini, Pietro;Teatini, Pietro
关键词:Land subsidence; Spatiotemporal modeling; GW-LSTM; PS-InSAR; Uncertainty analysis
-
Water Quality Index (WQI) as a Potential Proxy for Remote Sensing Evaluation of Water Quality in Arid Areas
作者:Zhang, Fei;Liu, Changjiang;Wang, Xiaoping;Wang, Weiwei;Cao, Naixin;Zhang, Fei;Liu, Changjiang;Wang, Xiaoping;Wang, Weiwei;Cao, Naixin;Chan, Ngai Weng;Shi, Jingchao;Kung, Hsiang-Te;Li, Xinguo;Guo, Tao
关键词:Water Quality Index (WQI); Ebinur Lake; remote sensing
-
The semi-dwarfing gene Rht-dp from dwarf polish wheat (Triticum polonicum L.) is the "Green Revolution" gene Rht-B1b
作者:Chai, Songyue;Yao, Qin;Zhang, Xu;Xiao, Xue;Fan, Xing;Sha, Lina;Kang, Houyang;Zhang, Haiqin;Zhou, Yonghong;Wang, Yi;Zeng, Jian;Li, Jun
关键词:Dwarf polish wheat; Homologous cloning; Molecular mapping; Rht-B1b; RNA-seq