Get 20M+ Full-Text Papers For Less Than $1.50/day. Start a 14-Day Trial for You or Your Team.

Learn More →

Lanczos method for spatio‐temporal graph convolutional networks to forecast expressway flow

Lanczos method for spatio‐temporal graph convolutional networks to forecast expressway flow Traffic forecasting has made pronounced progress with the development of graph convolution networks and the use of the topology of road networks. However, existing works face some limitations when it comes to modelling spatial dependencies. For example, pre‐defined graphs rely on global information to establish spatial relationships, and the spatial receptive field is limited by the polynomial convolutional method. To address these limitations, the authors propose the Lanczos method for Spatio‐Temporal Graph Convolutional Networks (LSTGCN); this approach uses the low‐rank approximation theory to drive pre‐defined graphs to collect important information and eliminate spatial redundancy. Additionally, a learnable dynamic graph feature (LDGF) module generates adaptive graphs and perceives the latent invariance‐variability between graph nodes. To further improve the model's ability to capture spatial dependencies and temporal correlations, multi‐span spatial learning is employed for enlarged receptive fields, which can be well integrated into gated recurrent units. The authors conducted baselines comparison and ablation experiments on real‐world datasets, and the findings show that the LSTGCN model outperforms the baselines and improves prediction accuracy. Notably, this work is the first attempt to use graph low‐rank theory for traffic prediction. http://www.deepdyve.com/assets/images/DeepDyve-Logo-lg.png IET Intelligent Transport Systems Wiley

Lanczos method for spatio‐temporal graph convolutional networks to forecast expressway flow

Download PDF
13 pages

Loading next page...
 
/lp/wiley/lanczos-method-for-spatio-temporal-graph-convolutional-networks-to-QeszVBWrc0
Publisher
Wiley
Copyright
© 2023 The Institution of Engineering and Technology.
eISSN
1751-9578
DOI
10.1049/itr2.12390
Publisher site
See Article on Publisher Site

Abstract

Traffic forecasting has made pronounced progress with the development of graph convolution networks and the use of the topology of road networks. However, existing works face some limitations when it comes to modelling spatial dependencies. For example, pre‐defined graphs rely on global information to establish spatial relationships, and the spatial receptive field is limited by the polynomial convolutional method. To address these limitations, the authors propose the Lanczos method for Spatio‐Temporal Graph Convolutional Networks (LSTGCN); this approach uses the low‐rank approximation theory to drive pre‐defined graphs to collect important information and eliminate spatial redundancy. Additionally, a learnable dynamic graph feature (LDGF) module generates adaptive graphs and perceives the latent invariance‐variability between graph nodes. To further improve the model's ability to capture spatial dependencies and temporal correlations, multi‐span spatial learning is employed for enlarged receptive fields, which can be well integrated into gated recurrent units. The authors conducted baselines comparison and ablation experiments on real‐world datasets, and the findings show that the LSTGCN model outperforms the baselines and improves prediction accuracy. Notably, this work is the first attempt to use graph low‐rank theory for traffic prediction.

Journal

IET Intelligent Transport Systems – Wiley

Published: Jun 4, 2023

Keywords: big data; convolutional neural nets; intelligent transportation systems; management and control; network theory (graphs); spatiotemporal phenomena; traffic modelling

References

  • Traffic prediction using artificial intelligence: Review of recent advances and emerging opportunities
    Shaygan, M.; Meese, C.; Li, W.; Zhao, X.(G.); Nejad, M.
  • Machine learning‐based traffic prediction models for intelligent transportation systems
    Boukerche, A.; Wang, J.
  • A comprehensive survey on graph neural networks
    Wu, Z.; Pan, S.; Chen, F.; Long, G.; Zhang, C.; Yu, P.S.
  • Diffusion convolutional recurrent neural network: Data‐driven traffic forecasting
    Li, Y.; Yu, R.; Shahabi, C.; Liu, Y.
  • Attention based spatial‐temporal graph convolutional networks for traffic flow forecasting
    Guo, S.; Lin, Y.; Feng, N.; Song, C.; Wan, H.
  • Graph WaveNet for deep spatial‐temporal graph modeling
    Wu, Z.; Pan, S.; Long, G.; Jiang, J.; Zhang, C.
  • Adaptive graph convolutional recurrent network for traffic forecasting
    Bai, L.; Yao, L.; Li, C.; Wang, X.; Wang, C.
  • Tensor low‐rank reconstruction for semantic segmentation
    Chen, W.; Zhu, X.; Sun, R.
  • Short‐term prediction of traffic volume in urban arterials
    Hamed, M.M.; Ai‐Masaeid, H.R.; Bani Said, Z.M.
  • Traffic‐flow‐prediction systems based on upstream traffic
    Hobeika, A.G.; Kim, C.K.
  • Robust causal dependence mining in big data network and its application to traffic flow predictions
    Li, L.; Su, X.; Wang, Y.; Lin, Y.; Li, Z.; Li, Y.
  • Short‐term traffic volume forecasting: A k‐nearest neighbor approach enhanced by constrained linearly sewing principle component algorithm
    Zheng, Z.; Su, D.
  • A map reduce‐based nearest neighbor approach for big‐data‐driven traffic flow prediction
    Xia, D.; Li, H.; Wang, B.; Li, Y.; Zhang, Z.
  • Traffic flow time series prediction based on statistics learning theory
    Ding, A.L.; Zhao, X.M.; Jiao, L.C.
  • Forecasting of short‐term freeway volume with v‐support vector machines
    Zhang, Y.; Xie, Y.
  • Accurate multisteps traffic flow prediction based on SVM
    Mingheng, Z.; Yaobao, Z.; Ganglong, H.; Gang, C.
  • Traffic flow prediction during the holidays based on DFT and SVR
    Luo, X.; Li, D.; Zhang, S.
  • Macroscopic modelling of arterial traffic: An extension to the cell transmission model
    Shirke, C.; Bhaskar, A.; Chung, E.
  • Location specific cell transmission model for freeway traffic
    Chen, X.; Shi, Q.; Li, L.
  • Travel times in quasi‐dynamic traffic assignment
    Gun, J.P.T.; Pel, A.J.; Arem, B.
  • A logical calculus of the ideas immanent in nervous activity
    McCulloch, W.S.; Pitts, W.
  • Machine learning‐based traffic prediction models for intelligent transportation systems
    Boukerche, A.; Wang, J.
  • Pattern sensitive prediction of traffic flow based on generative adversarial framework
    Lin, Y.; Dai, X.; Li, L.; Wang, F.Y.
  • Traffic flow prediction with big data: A deep learning approach
    Lv, Y.; Duan, Y.; Kang, W.; Li, Z.; Wang, F.Y.
  • Learning precise timing with LSTM recurrent networks
    Gers, F.A.; Schraudolph, N.N.; Schmidhuber, J.
  • Using LSTM and GRU neural network methods for traffic flow prediction
    Fu, R.; Zhang, Z.; Li, L.
  • Spectral networks and deep locally connected networks on graphs
    Bruna, J.; Zaremba, W.; Szlam, A.; LeCun, Y.
  • Learning traffic as images: A deep convolutional neural network for large‐scale transportation network speed prediction
    Ma, X.; Dai, Z.; He, Z.; Ma, J.; Wang, Y.; Wang, Y.
  • Spatio‐temporal graph convolutional networks: A deep learning framework for traffic forecasting
    Yu, B.; Yin, H.; Zhu, Z.
  • Spatial‐temporal synchronous graph convolutional networks: A new framework for spatial‐temporal network data forecasting
    Song, C.; Lin, Y.; Guo, S.; Wan, H.
  • Spatial‐temporal graph ODE networks for traffic flow forecasting
    Fang, Z.; Long, Q.; Song, G.; Xie, K.
  • Spatial‐temporal fusion graph neural networks for traffic flow forecasting
    Li, M.; Zhu, Z.
  • Transferability of spectral graph convolutional neural networks
    Levie, R.; Huang, W.; Bucci, L.; Bronstein, M.; Kutyniok, G.
  • Accelerated filtering on graphs using Lanczos method
    Šušnjara, A.; Perraudin, N.; Kressner, D.
  • Lanczosnet: Multi‐scale deep graph convolutional networks
    Liao, R.; Zhao, Z.; Urtasun, R.; Zemel, R.S.
  • Convolutional sequence to sequence learning
    Gehring, J.; Auli, M.; Grangier, D.; Yarats, D.; Dauphin, Y.N.
  • Learning phrase representations using RNN encoder‐decoder for statistical machine translation
    Cho, K.; Merrienboer, B.; Gulcehre, C.