International journal of advanced smart convergence

The Institute of Internet, Broadcasting and Communication (한국인터넷방송통신학회)
권호 표지
DOI QR코드

DOI QR Code

Traffic Flow Prediction with Spatio-Temporal Information Fusion using Graph Neural Networks

  • Huijuan Ding (Dept. of Computer Information Engineering, Cheongju Univ.) ;
  • Giseop Noh (Division of Software Convergence, Cheongju Univ.)
  • Received : 2023.10.10
  • Accepted : 2023.10.21
  • Published : 2023.12.31
Download PDF
⟨ Previous Next ⟩

Abstract

Traffic flow prediction is of great significance in urban planning and traffic management. As the complexity of urban traffic increases, existing prediction methods still face challenges, especially for the fusion of spatiotemporal information and the capture of long-term dependencies. This study aims to use the fusion model of graph neural network to solve the spatio-temporal information fusion problem in traffic flow prediction. We propose a new deep learning model Spatio-Temporal Information Fusion using Graph Neural Networks (STFGNN). We use GCN module, TCN module and LSTM module alternately to carry out spatiotemporal information fusion. GCN and multi-core TCN capture the temporal and spatial dependencies of traffic flow respectively, and LSTM connects multiple fusion modules to carry out spatiotemporal information fusion. In the experimental evaluation of real traffic flow data, STFGNN showed better performance than other models.

Keywords

References

  1. A. Ang and M. Piazzesi, 'A no-arbitrage vector autoregression of term structure dynamics with macroeconomic and latent variables', J. Monet. Econ., vol. 50, no. 4, pp. 745-787, May 2003, doi: 10.1016/S0304-3932(03)00032-1.
  2. J. Bruna, W. Zaremba, A. Szlam, and Y. LeCun, 'Spectral Networks and Locally Connected Networks on Graphs'. arXiv, May 21, 2014. doi: 10.48550/arXiv.1312.6203.
  3. S. Abu-El-Haija et al., 'MixHop: Higher-Order Graph Convolutional Architectures via Sparsified Neighborhood Mixing', in Proceedings of the 36th International Conference on Machine Learning, PMLR, May 2019, pp. 21-29. Accessed: Nov. 22, 2023. [Online]. Available: https://proceedings.mlr.press/v97/abu-el-haija19a.html
  4. S. Bai, J. Z. Kolter, and V. Koltun, 'An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modeling'. arXiv, Apr. 19, 2018. doi: 10.48550/arXiv.1803.01271.
  5. Z. Wu, S. Pan, G. Long, J. Jiang, and C. Zhang, 'Graph WaveNet for Deep Spatial-Temporal Graph Modeling'. arXiv, May 31, 2019. doi: 10.48550/arXiv.1906.00121.
  6. L. Zhao et al., 'T-GCN: A Temporal Graph Convolutional Network for Traffic Prediction', IEEE Trans. Intell. Transp. Syst., vol. 21, no. 9, pp. 3848-3858, Sep. 2020, doi: 10.1109/TITS.2019.2935152.
  7. Z. Wu, S. Pan, G. Long, J. Jiang, X. Chang, and C. Zhang, 'Connecting the Dots: Multivariate Time Series Forecasting with Graph Neural Networks', in Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, in KDD '20. New York, NY, USA: Association for Computing Machinery, 20 2020, pp. 753-763. doi: 10.1145/3394486.3403118.
  8. R. C. Staudemeyer and E. R. Morris, 'Understanding LSTM -- a tutorial into Long Short-Term Memory Recurrent Neural Networks'. arXiv, Sep. 12, 2019. doi: 10.48550/arXiv.1909.09586.
  9. B. Yu, H. Yin, and Z. Zhu, 'Spatio-Temporal Graph Convolutional Networks: A Deep Learning Framework for Traffic Forecasting', in Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence, Jul. 2018, pp. 3634-3640. doi: 10.24963/ijcai.2018/505.
  10. 'Modeling and Forecasting Vehicular Traffic Flow as a Seasonal ARIMA Process: Theoretical Basis and Empirical Results | Journal of Transportation Engineering | Vol 129, No 6'. Accessed: Nov. 22, 2023. [Online]. Available: https://ascelibrary.org/doi/abs/10.1061/(ASCE)0733-947X(2003)129:6(664)
  11. E. Zivot and J. Wang, Eds., 'Vector Autoregressive Models for Multivariate Time Series', in Modeling Financial Time Series with S-PLUS®, New York, NY: Springer, 2006, pp. 385-429. doi: 10.1007/978-0-387-32348-0_11.
  12. 'Forecasting holiday daily tourist flow based on seasonal support vector regression with adaptive genetic algorithm - ScienceDirect'. Accessed: Nov. 22, 2023. [Online]. Available: https://www.sciencedirect.com/science/article/pii/S1568494614005328
  13. U. Johansson, H. Bostrom, T. Lofstrom, and H. Linusson, 'Regression conformal prediction with random forests', Mach. Learn., vol. 97, no. 1, pp. 155-176, Oct. 2014, doi: 10.1007/s10994-014-5453-0.
  14. J. L. Elman, 'Distributed representations, simple recurrent networks, and grammatical structure', Mach. Learn., vol. 7, no. 2, pp. 195-225, Sep. 1991, doi: 10.1007/BF00114844.
  15. S. Hochreiter and J. Schmidhuber, 'Long Short-Term Memory', Neural Comput., vol. 9, no. 8, pp. 1735-1780, Jan. 1997, doi: 10.1162/neco.1997.9.8.1735.
  16. K. Cho et al., 'Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation'. arXiv, Sep. 02, 2014. doi: 10.48550/arXiv.1406.1078.
  17. J. Gehring, M. Auli, D. Grangier, D. Yarats, and Y. N. Dauphin, 'Convolutional Sequence to Sequence Learning', in Proceedings of the 34th International Conference on Machine Learning, PMLR, Jul. 2017, pp. 1243-1252. Accessed: Nov. 23, 2023. [Online]. Available: https://proceedings.mlr.press/v70/gehring17a.html
  18. C. Song, Y. Lin, S. Guo, and H. Wan, 'Spatial-Temporal Synchronous Graph Convolutional Networks: A New Framework for Spatial-Temporal Network Data Forecasting', Proc. AAAI Conf. Artif. Intell., vol. 34, no. 01, Art. no. 01, Apr. 2020, doi: 10.1609/aaai.v34i01.5438.
  19. J. Chen, T. Ma, and C. Xiao, 'FastGCN: Fast Learning with Graph Convolutional Networks via Importance Sampling'. arXiv, Jan. 30, 2018. doi: 10.48550/arXiv.1801.10247.
  20. W.-L. Chiang, X. Liu, S. Si, Y. Li, S. Bengio, and C.-J. Hsieh, 'Cluster-GCN: An Efficient Algorithm for Training Deep and Large Graph Convolutional Networks', in Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, in KDD '19. New York, NY, USA: Association for Computing Machinery, 25 2019, pp. 257-266. doi: 10.1145/3292500.3330925.
  21. A. Bojchevski, O. Shchur, D. Zugner, and S. Gunnemann, 'NetGAN: Generating Graphs via Random Walks', in Proceedings of the 35th International Conference on Machine Learning, PMLR, Jul. 2018, pp. 610-619. Accessed: Nov. 23, 2023. [Online]. Available: https://proceedings.mlr.press/v80/bojchevski18a.html
  22. 'Attention Based Spatial-Temporal Graph Convolutional Networks for Traffic Flow Forecasting | Proceedings of the AAAI Conference on Artificial Intelligence'. Accessed: Nov. 23, 2023. [Online]. Available: https://ojs.aaai.org/index.php/AAAI/article/view/3881
  23. Y. Li, R. Yu, C. Shahabi, and Y. Liu, 'Diffusion Convolutional Recurrent Neural Network: Data-Driven Traffic Forecasting'. arXiv, Feb. 22, 2018. doi: 10.48550/arXiv.1707.01926.
  24. Z. Pan, Y. Liang, W. Wang, Y. Yu, Y. Zheng, and J. Zhang, 'Urban Traffic Prediction from Spatio-Temporal Data Using Deep Meta Learning', in Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, in KDD '19. New York, NY, USA: Association for Computing Machinery, 25 2019, pp. 1720-1730. doi: 10.1145/3292500.3330884.