MFDGCN: Multi-Stage Spatio-Temporal Fusion Diffusion Graph Convolutional Network for Traffic Prediction

被引:8
|
作者
Cui, Zhengyan [1 ]
Zhang, Junjun [1 ]
Noh, Giseop [2 ]
Park, Hyun Jun [2 ]
机构
[1] Cheongju Univ, Dept Comp Informat Engn, Cheongju 28503, South Korea
[2] Cheongju Univ, Div Software Convergence, Cheongju 28503, South Korea
来源
APPLIED SCIENCES-BASEL | 2022年 / 12卷 / 05期
关键词
traffic prediction; spatio-temporal prediction; graph convolutional network; temporal convolutional network; multi-head attention; NEURAL-NETWORKS; FLOW;
D O I
10.3390/app12052688
中图分类号
O6 [化学];
学科分类号
0703 ;
摘要
Traffic prediction is a popular research topic in the field of Intelligent Transportation System (ITS), as it can allocate resources more reasonably, relieve traffic congestion, and improve road traffic efficiency. Graph neural networks are widely used in traffic prediction because they are good at dealing with complex nonlinear structures. Existing traffic prediction studies use distance-based graphs to represent spatial relationships, which ignores the deep connections between non-adjacent spatio-temporal information. The use of a simple approach to fuse spatio-temporal information is not conducive to obtaining long-term deep spatio-temporal dependencies. Therefore, we propose a new deep learning model Multi-Stage Spatio-Temporal Fusion Diffusion Graph Convolutional Network (MFDGCN). It generates multiple static and dynamic spatio-temporal association graphs to enhance features and adopts the multi-stage hybrid spatio-temporal fusion method. This promotes the effective fusion of a spatio-temporal multimodal and uses the diffuse convolution method to model the graph structure and time series in traffic prediction, respectively. The model can better predict both long and short-term traffic simultaneously. We evaluated MFDGCN using real road network traffic data and it shows good performance.
引用
收藏
页数:15
相关论文
共 50 条
  • [1] Dynamic Spatio-Temporal Graph Fusion Convolutional Network for Urban Traffic Prediction
    Ma, Haodong
    Qin, Xizhong
    Jia, Yuan
    Zhou, Junwei
    [J]. APPLIED SCIENCES-BASEL, 2023, 13 (16):
  • [2] Traffic Prediction Based on Multi-graph Spatio-Temporal Convolutional Network
    Yao, Xiaomin
    Zhang, Zhenguo
    Cui, Rongyi
    Zhao, Yahui
    [J]. WEB INFORMATION SYSTEMS AND APPLICATIONS (WISA 2021), 2021, 12999 : 144 - 155
  • [3] Spatio-Temporal Identity Multi-Graph Convolutional Network for Traffic Prediction in the Metaverse
    Nan, Haihan
    Li, Ruidong
    Zhu, Xiaoyan
    Ma, Jianfeng
    Xue, Kaiping
    [J]. IEEE JOURNAL ON SELECTED AREAS IN COMMUNICATIONS, 2024, 42 (03) : 669 - 679
  • [4] Spatio-temporal fusion graph convolutional network for traffic flow forecasting
    Ma, Ying
    Lou, Haijie
    Yan, Ming
    Sun, Fanghui
    Li, Guoqi
    [J]. INFORMATION FUSION, 2024, 104
  • [5] Deep spatio-temporal graph convolutional network for traffic accident prediction
    Yu, Le
    Du, Bowen
    Hu, Xiao
    Sun, Leilei
    Han, Liangzhe
    Lv, Weifeng
    [J]. NEUROCOMPUTING, 2021, 423 (423) : 135 - 147
  • [6] Federated Spatio-Temporal Traffic Flow Prediction Based on Graph Convolutional Network
    Wang, Hanqiu
    Zhang, Rongqing
    Cheng, Xiang
    Yang, Liuqing
    [J]. 2022 14TH INTERNATIONAL CONFERENCE ON WIRELESS COMMUNICATIONS AND SIGNAL PROCESSING, WCSP, 2022, : 221 - 225
  • [7] Robust Traffic Prediction Using Probabilistic Spatio-Temporal Graph Convolutional Network
    Karim, Atkia Akila
    Nower, Naushin
    [J]. ENGINEERING APPLICATIONS OF NEURAL NETWORKS, EANN 2024, 2024, 2141 : 259 - 273
  • [8] Dynamic Spatio-temporal traffic flow prediction based on multi fusion graph attention network
    Cheng, Manru
    Jiang, Guo-Ping
    Song, Yurong
    Yang, Chen
    [J]. 2022 41ST CHINESE CONTROL CONFERENCE (CCC), 2022, : 7285 - 7291
  • [9] Adaptive Spatio-Temporal Convolutional Network for Traffic Prediction
    Zhang, Mingyang
    Li, Yong
    Sun, Funing
    Guo, Diansheng
    Hui, Pan
    [J]. 2021 21ST IEEE INTERNATIONAL CONFERENCE ON DATA MINING (ICDM 2021), 2021, : 1475 - 1480
  • [10] Dynamic traffic correlations based spatio-temporal graph convolutional network for urban traffic prediction
    Xu, Yuanbo
    Cai, Xiao
    Wang, En
    Liu, Wenbin
    Yang, Yongjian
    Yang, Funing
    [J]. INFORMATION SCIENCES, 2023, 621 : 580 - 595