计算机科学

计算机科学 ›› 2024, Vol. 51 ›› Issue (11A): 240200045-9.doi: 10.11896/jsjkx.240200045

• 大数据&数据科学 • 上一篇    下一篇

基于全局时空图卷积神经网络的城市交通流量预测

王佳昊, 黎文斌, 郭仕尧, 向平   

  1. 电子科技大学信息与软件工程学院 成都 610051
  • 出版日期:2024-11-16 发布日期:2024-11-13
  • 作者简介:(wangjh@uestc.edu.cn)
  • 基金资助:
    电子科技大学-智小金-智能家居联合研究中心项目(H04W210180);内江市科技孵化和成果转化专项资金(2021KJFH004);四川省科技支撑计划项目(2022YFG0212,2021YFG0024);泸州市科技计划项目(2022-XDY-192)

Urban Traffic Flow Prediction Based on Global Spatiotemporal Graph Convolutional NeuralNetwork

WANG Jiahao, LI Wenbin, GUO Shiyao, XIANG Ping   

  1. School of Information and Software Engineering,University of Electronic Science and Technology,Chengdu 610051,China
  • Online:2024-11-16 Published:2024-11-13
  • About author:WANG Jiahao,born in 1978,Ph.D,associate professor,is a member of CCF(No.27769M).His main research interests include IoT,information security and data minig.
    LI Wenbin,born in 1999,master.His main research interest is patiotemporal data prediction.
  • Supported by:
    UESTC-ZHIXIAOJING Joint Research Center of Smart Home(H04W210180),Neijiang Technology Incubation and Transformation Funds(2021KJFH004),Science and Technology Support Plan of Sichuan Province of China(2022YFG0212,2021YFG0024) and Luzhou Science and Technology Plan Project(2022-XDY-192).

PDF (PC)

206

摘要： 交通流量预测在智能交通系统(ITS)中发挥着重要作用,将城市中复杂的时空相关性高效且全面地提取出来是交通流量预测中面临的关键挑战。交通速度不仅在时间维度上具有短期和长期周期性依赖关系,而且在空间维度上具有局部和全局依赖性,现有方法对捕获交通数据的时空依赖关系有一定的局限。为此,文中提出了一种基于全局时空图卷积神经网络(Global Spatial-Temporal Graph Convolutional Network,GSTGCN)的深度学习模型,用于解决在城市交通速度预测的局限性。该模型中存在3种时空分量,可相应地对交通数据中的近期、天周期、周周期这3种不同的时空相关性进行建模。每个时空分量都由时间模块和空间模块组成,时间模块为了更好地获取交通数据的时间维度信息,引入了Informer机制以自适应地分配特征权重。空间模型为了更好地获取交通数据的空间关系,引入了图卷积神经网络来提取交通数据的局部和全局空间信息。在两个不同的真实数据集上进行了测试,结果表明所提出的GSTGCN优于最先进的基线模型。

关键词: 交通流量预测, 全局时空图卷积网络, 时空依赖性

Abstract: Traffic flow prediction plays an important role in intelligent transportation systems(ITS).The key challenge in traffic flow prediction is to efficiently and comprehensively extract the complex spatiotemporal correlations in cities.Traffic speed has not only short-term and long-term periodic dependencies in the temporal dimension,but also local and global dependencies in the spatial dimension.Existing methods have certain limitations in capturing the spatiotemporal dependencies of traffic data.To this end,this paper proposes a deep learning model based on the global spatialtemporal graph convolutional network(GSTGCN) to address the limitations of urban traffic speed prediction.There are three spatiotemporal components in the model,which can model the three different spatiotemporal correlations in traffic data,namely,recent,daily,and weekly cycles.Each spatiotemporal component consists of a time module and a spatial module.In order to better obtain the temporal dimension information of traffic data,the time module introduces the Informer mechanism to adaptively assign feature weights.In order to better obtain the spatial relationship of traffic data,the spatial model introduces a graph convolutional neural network to extract local and global spatial information of traffic data.In the experiments,the proposed model is tested on two different real-world datasets.The results show that the proposed GSTGCN outperforms the most advanced baseline models.

Key words: Traffic flow prediction, Global spatiotemporal graph convolutional neural network, spatiotemporal dependence

中图分类号: 

  • TP181
[1]FANG Z X,HUANG S Q,SU R X,et al.Detecting Hierarchical Congestion Intervals Based on the Fusion of Multi-source Highway Data[J].Geomatics and Information Science of Wuhan University,2020,45(5):682-690.
[2]HSUEH Y L,YANG Y R.A short-term traffic speed prediction model based on LSTM networks [J].International Journal of Intelligent Transportation Systems Research,2021,19(3):510-524.
[3]MAKRIDAKIS S,HIBON M.ARMA models and the Box-Jenkins methodology[J].Journal of Forecasting,1997,16:147-163.
[4]CHEN J,LI D,ZHANG G,et al.Localized space-time autore-gressive parameters estimation for traffic flow prediction in urban road networks[J].Applied Sciences,2018,8:277.
[5]ZIVOT E,WANG J.Vector autoregressive models for multivariate time series[C]//Modeling Financial Time Series with S-Plus©;Springer:New York,NY,USA,2006:385-429.
[6]ZHENG Z,SU D.Short-term traffic volume forecasting:Ak-nearest neighbor approach enhanced by constrained linearly sewing principle component algorithm[J].Transportation Research Part C Emerging Technologies,2014,43:143-157.
[7]WU C H,HO J M,LEE D T.Travel-time prediction with support vector regression[J].IEEE Transactions on Intelligent Transportation Systems,2004,5:276-281.
[8]LIPPI M,BERTINI M,FRASCONI P.Short-term traffic flow forecasting:An experimental comparison of time-series analysis and supervised learning[J].IEEE Transactions on Intelligent Transportation Systems,2013,14: 871-882.
[9]CHEN W,CHEN L,XIE Y,et al.Multi-Range Attentive Bi-component Graph Convolutional Network for Traffic Forecasting[J].arXiv:1911.12093,2019.
[10]LV Y,DUAN Y,KANG W,et al.Traffic flow prediction with big data: A deep learning approach[J].IEEE Transactions on Intelligent Transportation Systems,2014,16:865-873.
[11]LUO X,LI D,YANG Y,et al.Spatiotemporal traffic flow prediction with KNN and LSTM[J].Journal of Advanced Transportation,2019,2019:4145353.
[12]HOCHREITER S,SCHMIDHUBERJ.Long short-term memory[J].Neural Computer,1997,9:1735-1780.
[13]YU R,LI Y,SHAHABI C,DEMIRYUREK U,et al.Deeplearning:A generic approach for extreme condition traffic forecasting[C]//Proceedings of the 2017 SIAM International Conference on Data Mining.Houston,TX,USA,2017:777-785.
[14]CUI Z,KE R,WANG Y.Deep stacked bidirectional and unidirectional LSTM recurrent neural network for network-wide traffic speed prediction[C]//Proceedings of the 6th Interna-tional Workshop on Urban Computing(UrbComp 2017).Halifax,NS,Canada,2017.
[15]ZHANG J,ZHENG Y,QI D.Deep spatio-temporal residual networks for citywide crowd flows prediction[C]//Proceedings of the Thirty-First AAAI Conference on Artificial Intelligence,San Francisco,CA,USA,2017.
[16]LIU P,ZHANG Y,KONG D,et al.Improved Spatio-Temporal Residual Networks for Bus Traffic Flow Prediction[J].Applied Science,2019,9:615.
[17]DU S,LI T,GONG X,et al.A hybrid method for traffic flow forecasting using multimodal deep learning[J].arXiv:1803.02099,2018.
[18]YAO H,TANG X,WEI H,et al.Modeling spatial-temporal dynamics for traffic prediction[J].arXiv:1803.01254,2018.
[19]YAO H,WU F,KE J,et al.Deep multi-view spatial-temporal network for taxi demand prediction[C]//Proceedings of the Thirty-Second AAAI Conference on Artificial Intelligence,New Orleans,LA,USA,2018.
[20]WU Z,PAN S,CHEN F,et al.A comprehensive survey ongraph neural networks[J].arXiv:1901.00596,2019.
[21]BRUNA J,ZAREMBA W,SZLAM A,et al.Spectral networks and locally connected networks on graphs[J].arXiv:1312.6203,2013.
[22]DEFFERRARD M,BRESSON X,VANDERGHEYNST P.Convolutional neural networks on graphs with fast localized spectral filtering[C]//Advances in Neural Information Processing Systems;Neural Information Processing Systems(NIPS).Barcelona,Spain,2016:3844-3852.
[23]KIPF T N,WELLING M.Semi-supervised classification withgraph convolutional networks[J].arXiv:1609.02907,2016.
[24]ATWOOD J,TOWSLEYD.Diffusion-convolutional neural networks[C]//Advances in Neural Information Processing Systems,Neural Information Processing Systems(NIPS).Barcelona,Spain,2016:1993-2001.
[25]GILMER J,SCHOENHOLZ S S,RILEY P F,et alNeural message passing for quantum chemistry[C]//Proceedings of the 34th International Conference on Machine Learning.Sydney,Australia,2017,70:1263-1272.
[26]HAMILTON W,YING Z,LESKOVEC J.Inductive representation learning on large graphs[C]//Advances in Neural Information Processing Systems;Neural Information Processing Systems(NIPS).Long Beach,CA,USA,2017:1024-1034.
[27]GROVER A,LESKOVEC J.node2vec:Scalable feature learning for networks[C]//Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mi-ning.San Francisco,CA,USA,2016:855-864.
[28]CUI P,WANG X,PEI J,et al.A survey on network embedding[J].IEEE Transactions on Knowledge and Data Engineering,2018,31:833-852.
[29]LI Y,YU R,SHAHABI C,LIU Y.Diffusion Convolutional Recurrent Neural Network:Data-Driven Traffic Forecasting[C]//Proceedings of the International Conference on Learning Representations(ICLR'18).Vancouver,BC,Canada,30 April-3 May 2018.
[30]FANG S,ZHANG Q,MENG G,et al.Gstnet:Global spatial-temporal network for traffic flow prediction[C]//Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence.Macao,China.2019:10-16.
[31]YU B,YIN H,ZHU Z.Spatio-temporal Graph ConvolutionalNetworks:A Deep Learning Framework for Traffic Forecasting[C]//Proceedings of the 27th International Joint Conference on Artificial Intelligence(IJCAI).Stockholm,Sweden,2018.
[32]PAN Z,LIANG Y,WANGW,et al.Urban Traffic Prediction from Spatio-Temporal Data Using Deep Meta Learning[C]//Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining.Anchorage,AK,USA2019:1720-1730.
[33]WU Z,PAN S,LONG G,et al.Graph WaveNet for Deep Spatial-Temporal Graph Modeling[J].arXiv:1906.00121,2019.
[34]OORD A V D,DIELEMAN S,ZEN H,et al.Wavenet:A gene-rative model for raw audio[J].arXiv:1609.03499,2016.
[35]CHEN W,CHEN L,XIE Y,et al.Multi-Range Attentive Bi-component Graph Convolutional Network for Traffic Forecasting[J].arXiv:1911.12093,2019.
[36]YUAN J,ZHENG Y,XIE X.Discovering regions of different functions in a city using human mobility and POIs[C]//Proceedings of the 8th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining(SIGKDD).Beijing,China:ACM,2012:186-194.
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed   
No Suggested Reading articles found!
渝ICP备16013121号-4
地址：重庆市渝北区洪湖西路18号    邮编：401121  
电话：023-63500828（编辑部） 023-67039612（会议/专题） 023-67039623（财务/发票）
E-mail：jsjkx12@163.com
本系统由北京玛格泰克科技发展有限公司设计开发