计算机科学

计算机科学 ›› 2024, Vol. 51 ›› Issue (3): 72-80.doi: 10.11896/jsjkx.230100045

• 数据库&大数据&数据科学 • 上一篇    下一篇

基于缺失数据的交通速度预测算法

黄坤, 孙未未   

  1. 复旦大学计算机科学技术学院 上海200438
    上海市数据科学重点实验室(复旦大学) 上海200438
    上海智能电子与系统研究院 上海200438
  • 收稿日期:2023-01-09 修回日期:2023-04-30 出版日期:2024-03-15 发布日期:2024-03-13
  • 通讯作者: 孙未未(wwsun@fudan.edu.cn)
  • 作者简介:(khuang20@fudan.edu.cn)
  • 基金资助:
    国家自然科学基金(62172107)

Traffic Speed Forecasting Algorithm Based on Missing Data

HUANG Kun, SUN Weiwei   

  1. School of Computer Science,Fudan University,Shanghai 200438,China
    Shanghai Key Laboratory of Data Science,Fudan University,Shanghai 200438,China
    Shanghai Institute of Intelligent Electronics and Systems,Shanghai 200438,China
  • Received:2023-01-09 Revised:2023-04-30 Online:2024-03-15 Published:2024-03-13
  • About author:HUANG Kun,born in 1997,postgra-duate,is a student member of CCF(No.O9885G).Her main research interests include spatial-temporal data mining and so on.SUN Weiwei,born in 1973,Ph.D,professor,is a senior member of CCF(No.08792S).His main research interests include big spatial-temporal data and so on.
  • Supported by:
    National Natural Science Foundation of China(62172107).

PDF (PC)

132

摘要： 交通速度预测是智能交通系统的基础,可以缓解交通拥堵,节约公共资源,提高人们的生活质量。在真实情况下,采集到的交通速度数据通常存在缺失,而现有研究成果大多数只考虑了数据相对完整的场景。文章主要针对缺失场景下的交通速度数据进行研究,捕捉其中的时空相关性,并对未来交通速度进行预测。为了充分利用到交通数据的时空特征,提出了一种新的基于深度学习的交通速度预测模型。首先,提出了“还原-预测”算法,先使用自监督学习方法让模型还原缺失数据,再对交通速度进行预测;其次,引入了对比学习的方法,使得速度时间序列的特征表示更鲁棒;最后,模拟了不同数据缺失率的场景,通过实验验证了所提方法在各种缺失率下的预测准确率都优于现有方法,并设计了实验对对比学习方法和不同的还原算法进行分析,证明了所提方法的有效性。

关键词: 交通速度预测, 缺失数据还原, 图神经网络, 对比学习, 深度学习

Abstract: Traffic speed forecasting is the foundation of intelligent transportation system,which can ease traffic congestion,save public resources and improve people's quality of life.In real situations,the collected traffic speed data are usually missing,and most of the existing research results only consider the scenarios with relatively complete data.The paper focuses on the traffic speed data in the missing scenarios,captures the spatio-temporal correlation,and predicts the future traffic speed.In order to make full use of the spatio-temporal characteristics of traffic data,this study proposes a new deep learning-based traffic speed forecasting model.Firstly,a “recover-predict” algorithm is designed,which first uses a self-supervised learning method to enable the model to recover the missing data and then predict the traffic speed.Secondly,a contrastive learning method is introduced to make the feature representation of the speed time series more robust.Finally,the scenarios with different missing data rates are simulated,and experimental results show that the prediction accuracy of the proposed method outperform existing methods with various missing rates,and experiments are designed to analyze the comparative learning method and different recovery algorithms to prove the effectiveness of the proposed method.

Key words: Traffic speed forecasting, Recovery of missing data, Graph neural network, Contrastive learning, Deep learning

中图分类号: 

  • TP301
[1]ZHANG J,WANG F,WANG K,et al.Data-Driven Intelligent Transportation Systems:A Survey[J].IEEE Transactions on Intelligent Transportation Systems,2011,12(4):1624-1639.
[2]YU B,YIN H,ZHU Z.Spatio-Temporal Graph Convolutional Networks:A Deep Learning Framework for Traffic Forecasting[C]//Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence(IJCAI 2018).Stockholm:Morgan Kaufmann,2018:3634-3640.
[3]WU Z,PAN S,LONG G,et al.Graph WaveNet for Deep Spatial-Temporal Graph Modeling[C]//Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence(IJCAI 2019).Macao:Morgan Kaufmann,2019:1907-1913.
[4]LIU D,WANG J,SHANG S,et al.MSDR:Multi-Step Depen-dency Relation Networks for Spatial Temporal Forecasting[C]//Proceedings of the 28th ACM SIGKDD Conference on Know-ledge Discovery and Data Mining.Washington:ACM,2022:1042-1050.
[5]ZHENG C,FAN X,WANG C,et al.GMAN:A Graph Multi-Attention Network for Traffic Prediction[C]//Proceedings of the Thirty-Fourth AAAI Conference on Artificial Intelligence(AAAI 2020).New York:AAAI,2020:1234-1241.
[6]JI J,WANG J,JIANG Z,et al.STDEN:Towards Physics-guided Neural Networks for Traffic Flow Prediction[C]//Proceedings of the Thirty-Sixth AAAI Conference on Artificial Intelligence(AAAI 2022).AAAI,2022:4048-4056.
[7]HADSELL R,CHOPRA S,LECUN Y.Dimensionality Reduc-tion by Learning an Invariant Mapping[C]//2006 IEEE Computer Society Conference on Computer Vision and Pattern Re-cognition(CVPR 2006).New York:IEEE,2006:1735-1742.
[8]VASWANI A,SHAZEER N,PARMAR N,et al.Attention isAll You Need[C]//Advances in Neural Information Processing Systems 30:Annual Conference on Neural Information Proces-sing Systems 2017.Long Beach:MIT Press,2017:5998-6008.
[9]YU G,ZHANG C.Switching ARIMA Model Based Forecasting for Traffic Flow[C]//2004 IEEE International Conference on Acoustics,Speech,and Signal Processing.Montreal:IEEE,2004:429-432.
[10]JEONG Y S,BYON Y J,CASTRO-NETO M M,et al.Super-vised Weighting-Online Learning Algorithm for Short-Term Traffic Flow Prediction[J].IEEE Transactions on Intelligent Transportation Systems,2013,14(4):1700-1707.
[11]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,2015,16(2):865-873.
[12]ZANG D,LING J,WEI Z,et al.Long-Term Traffic Speed Prediction Based on Multiscale Spatio-Temporal Feature Learning Network[J].IEEE Transactions on Intelligent Transportation Systems,2019,20(10):3700-3709.
[13]SHI X,CHEN Z,WANG H,et al.Convolutional LSTM Net-work:A Machine Learning Approach for Precipitation Nowcas-ting[C]//Advances in Neural Information Processing Systems 28:Annual Conference on Neural Information Processing Systems 2015.Montreal:MIT Press.2015:802-810.
[14]CHEN D,YAN X,LIU X,et al.A Multiscale-Grid-BasedStacked Bidirectional GRU Neural Network Model for Predicting Traffic Speeds of Urban Expressways[J].IEEE Access,2021,9:1321-1337.
[15]CHUNG J,GULCEHRE C,CHO K,et al.Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling[C]//NIPS 2014 Workshop on Deep Learning.2014.
[16]GORI M,MONFARDINI G,SCARSELLI F.A New Model for Learning in Graph Domains[C]//Proceedings of 2005 IEEE International Joint Conference on Neural Networks.Montreal:IEEE,2005,2:729-734.
[17]KIPF T N,WELLING M.Semi-Supervised Classification withGraph Convolutional Networks[C]//Conference Track Procee-dings of the 5th International Conference on Learning Representations(ICLR 2017).Toulon,2017.
[18]HAMILTON W L,YING Z,LESKOVEC J.Inductive Representation Learning on Large Graphs[C]//Advances in Neural Information Processing Systems 30:Annual Conference on Neural Information Processing Systems 2017.Long Beach:MIT Press,2017:1024-1034.
[19]HOCHREITER S,SCHMIDHUBER J.Long Short-Term Me-mory[J].Neural Computation,1997,9(8):1735-1780.
[20]LIU J,ONG G P,CHEN X.GraphSAGE-Based Traffic Speed Forecasting for Segment Network With Sparse Data[J].IEEE Transactions on Intelligent Transportation Systems,2022,23(3):1755-1766.
[21]HUANG K,SIDIROPOULOS N D,SWAMI A.Non-NegativeMatrix Factorization Revisited:Uniqueness and Algorithm for Symmetric Decomposition[J].IEEE Transactions on Signal Processing,2013,62(1):211-224.
[22]CHEN X,YANG J,SUN L.A Nonconvex Low-Rank Tensor Completion Model for Spatiotemporal Traffic Data Imputation[J].Transportation Research Part C:Emerging Technologies,2020,117:102673.
[23]ZHANG Y,THORBURN P J,XIANG W,et al.SSIM-A Deep Learning Approach for Recovering Missing Time Series Sensor Data[J].IEEE Internet Things Journal,2019,6(4):6618-6628.
[24]SUTSKEVER I,VINYALS O,LE Q V.Sequence to Sequence Learning with Neural Networks[C]//Advances in Neural Information Processing Systems 27:Annual Conference on Neural Information Processing Systems 2014.Montreal:MIT Press,2014:3104-3112.
[25]XU D,PENG H,WEI C,et al.Traffic State Data Imputation:An Efficient Generating Method Based on the Graph Aggregator[J].IEEE Transactions on Intelligent Transportation Systems,2022,23(8):13084-13093.
[26]GOODFELLOW I J,POUGET-ABADIE J,MIRZA M,et al.Generative Adversarial Nets[C]//Advances in Neural Information Processing Systems 27:Annual Conference on Neural Information Processing Systems 2014.Montreal:MIT Press,2014:2672-2680.
[27]TSAI Y H H,BAI S,YAMADA M,et al.Transformer Dissection:An Unified Understanding for Transformer's Attention via the Lens of Kernel[C]//Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing(EMNLP-IJCNLP).Hong Kong:ACL,2019:4343-4352.
[28]HE K,FAN H,WU Y,et al.Momentum Contrast for Unsupervised Visual Representation Learning[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition(CVPR 2020).Seattle:IEEE,2020:9729-9738.
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