Journal of Applied Science and Engineering

Published by Tamkang University Press

1.30

Impact Factor

2.10

CiteScore

Ruihao Cao1,2, Zhirou Ma2, and Jie Liu1,2This email address is being protected from spambots. You need JavaScript enabled to view it.

1School of Artificial Intelligence and Information Technology, Nanjing University of Chinese Medicine, China

2Nanjing Institute of Software Technology, China


 

Received: November 13, 2023
Accepted: March 14, 2024
Publication Date: April 13, 2024

 Copyright The Author(s). This is an open access article distributed under the terms of the Creative Commons Attribution License (CC BY 4.0), which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are cited.


Download Citation: ||https://doi.org/10.6180/jase.202502_28(2).0003  


Accurate traffic flow prediction poses a significant challenge in Intelligent Transport Systems. Most existing traffic flow prediction models operate under the assumption of complete or nearly complete datasets. However, real-world scenarios often involve missing data due to various human and natural factors. In this paper, we propose a novel approach, the Spatio-Temporal Causal Graph-based Graph Neural Network model (STCG), designed to address this challenge in traffic flow prediction. This model not only handles missing data but also automatically derives the causal graph, employing graph neural network techniques to capture nonlinear correlations between different sensors. It establishes a mapping between current and future traffic states, enabling predictions in the presence of missing data. Experimental findings demonstrate that compared to the benchmark model, the proposed STCG model yields superior performance in terms of mean square error, root mean square error, and mean absolute percentage error when data is missing. Additionally, the model significantly reduces computational complexity, thereby shortening training times. In conclusion, the STCG model exhibits potential applications in enhancing traffic flow prediction, particularly in handling missing data, thus improving prediction accuracy and efficiency.


Keywords: Traffic flow prediction; Data missing; Causality; Causal graph; Graph neural network


  1. [1] K.-H. N. Bui, J. Cho, and H. Yi, (2022) “Spatialtemporal graph neural network for traffic forecasting: An overview and open research issues" Applied Intelligence 52(3): 2763–2774. DOI: 10.1007/s10489-021-02587-w.
  2. [2] M. Saleem, S. Abbas, T. M. Ghazal, M. A. Khan, N. Sahawneh, and M. Ahmad, (2022) “Smart cities: Fusionbased intelligent traffic congestion control system for vehicular networks using machine learning techniques" Egyptian Informatics Journal 23(3): 417–426. DOI: 10.1016/j.eij.2022.03.003.
  3. [3] A. Ali, Y. Zhu, and M. Zakarya, (2022) “Exploiting dynamic spatio-temporal graph convolutional neural networks for citywide traffic flows prediction" Neural Networks 145: 233–247. DOI: 10.1016/j.neunet.2021.10.021.
  4. [4] J. James, (2022) “Graph construction for traffic prediction: a data-driven approach" IEEE Transactions on Intelligent Transportation Systems 23(9): 15015–15027. DOI: 10.1109/TITS.2021.3136161.
  5. [5] W. Jiang, J. Luo, M. He, and W. Gu, (2023) “Graph neural network for traffic forecasting: The research progress" ISPRS International Journal of Geo-Information 12(3): 100. DOI: 10.3390/ijgi12030100.
  6. [6] Q. Zhang, J. Chang, G. Meng, S. Xiang, and C. Pan. “Spatio-temporal graph structure learning for traffic forecasting”. In: Proceedings of the AAAI conference on artificial intelligence. 34. 01. 2020, 1177–1185. DOI: 10.1609/aaai.v34i01.5470.
  7. [7] B. Yu, H. Yin, and Z. Zhu. “Spatio-temporal graph convolutional networks: A deep learning framework for traffic forecasting”. In: Proceedings of the TwentySeventh International Joint Conference on Artificial Intelligence. 2018, 3634–3640. DOI: 10.24963/ijcai.2018/505.
  8. [8] L. Zhao, Y. Song, C. Zhang, Y. Liu, P. Wang, T. Lin, M. Deng, and H. Li, (2019) “T-gcn: A temporal graph convolutional network for traffic prediction" IEEE Transactions on Intelligent Transportation Systems 21(9): 3848–3858. DOI: 10.1109/TITS.2019.2935152.
  9. [9] Y. Li, R. Yu, C. Shahabi, and Y. Liu. “Diffusion convolutional recurrent neural network: Data-driven traffic forecasting”. In: International Conference on Learning Representations. 2018.
  10. [10] Z. Wu, S. Pan, G. Long, J. Jiang, and C. Zhang. “Graph wavenet for deep spatial-temporal graph modeling”. In: Proceedings of the 28th International Joint Conference on Artificial Intelligence. 2019, 1907–1913.
  11. [11] S. Wang and G. Mao, (2019) “Fundamental limits of missing traffic data estimation in urban networks" IEEE Transactions on Intelligent Transportation Systems 21(3): 1191–1203. DOI: 10.1109/TITS.2019.2903524.
  12. [12] J.-M. Yang, Z.-R. Peng, and L. Lin, (2021) “Real-time spatiotemporal prediction and imputation of traffic status based on LSTM and Graph Laplacian regularized matrix factorization" Transportation Research Part C: Emerging Technologies 129: 103228. DOI: 10.1016/j.trc.2021.103228.
  13. [13] L. Li, B. Du, Y. Wang, L. Qin, and H. Tan, (2020) “Realtime spatiotemporal prediction and imputation of traffic status based on LSTM and Graph Laplacian regularized matrix factorization" Knowledge-Based Systems 194: 105592. DOI: 10.1016/j.knosys.2020.105592.
  14. [14] J. Du, H. Chen, and W. Zhang, (2019) “A deep learning method for data recovery in sensor networks using effective spatio-temporal correlation data" Sensor Review 39(2): 208–217. DOI: 10.1108/SR-02-2018-0039.
  15. [15] Q. Li, H. Tan, Y. Wu, L. Ye, and F. Ding, (2020) “Traffic flow prediction with missing data imputed by tensor completion methods" IEEE Access 8: 63188–63201. DOI: 10.1109/ACCESS.2020.2984588.
  16. [16] C. K. Assaad, E. Devijver, and E. Gaussier, (2022) “Traffic flow prediction with missing data imputed by tensor completion methods" Journal of Artificial Intelligence Research 73: 767–819. DOI: 10.1613/jair.1.13428.
  17. [17] J. Runge, A. Gerhardus, G. Varando, V. Eyring, and G. Camps-Valls, (2023) “Causal inference for time series" Nature Reviews Earth & Environment 4(7): 487–505. DOI: 10.1038/s43017-023-00471-4.
  18. [18] J. Y. Zhu, C. Zhang, H. Zhang, S. Zhi, V. O. Li, J. Han, and Y. Zheng, (2017) “pg-causality: Identifying spatiotemporal causal pathways for air pollutants with urban big data" IEEE Transactions on Big Data 4(4): 571–585. DOI: 10.1109/TBDATA.2017.2723899.
  19. [19] Z. He, C.-Y. Chow, and J.-D. Zhang, (2020) “STNN: A spatio-temporal neural network for traffic predictions" IEEE Transactions on Intelligent Transportation Systems 22(12): 7642–7651. DOI: 10.1109/TITS.2020.3006227.
  20. [20] H. K. Joy and M. R. Kounte, (2022) “Deep CNN based video compression with lung ultrasound sample" Journal of Applied Science and Engineering 26(3): 313–321. DOI: 10.6180/jase.202303_26(3).0002.
  21. [21] A. Belhadi, Y. Djenouri, D. Djenouri, and J. C.-W. Lin, (2020) “A recurrent neural network for urban long-term traffic flow forecasting" Applied Intelligence 50: 3252– 3265. DOI: 10.1007/s10489-020-01716-1.
  22. [22] Y. Tian, K. Zhang, J. Li, X. Lin, and B. Yang, (2018) “LSTM-based traffic flow prediction with missing data" Neurocomputing 318: 297–305. DOI: 10.1016/j.neucom.2018.08.067.
  23. [23] Y. Ren, D. Zhao, D. Luo, H. Ma, and P. Duan, (2020) “Global-local temporal convolutional network for traffic flow prediction" IEEE Transactions on Intelligent Transportation Systems 23(2): 1578–1584. DOI: 10.1109/TITS.2020.3025076.
  24. [24] J. Zhang, Y. Zheng, and D. Qi. “Deep spatio-temporal residual networks for citywide crowd flows prediction”. In: Proceedings of the AAAI conference on artificial intelligence. 31. 1. 2017, 1655–1661. DOI: 10.1609/aaai.v31i1.10735.
  25. [25] D. Yang, K. Chen, M. Yang, and X. Zhao, (2019) “Urban rail transit passenger flow forecast based on LSTM with enhanced long-term features" IET Intelligent Transport Systems 13(10): 1475–1482. DOI: 10.1049/ iet-its.2018.5511.
  26. [26] K. Wang, C. Ma, Y. Qiao, X. Lu, W. Hao, and S. Dong, (2021) “A hybrid deep learning model with 1DCNNLSTM-Attention networks for short-term traffic flow prediction" Physica A: Statistical Mechanics and its Applications 583: 126293. DOI: 10.1016/j.physa.2021. 126293.
  27. [27] D. Seng, F. Lv, Z. Liang, X. Shi, and Q. Fang, (2021) “Forecasting traffic flows in irregular regions with multigraph convolutional network and gated recurrent unit" Frontiers of Information Technology & Electronic Engineering 22(9): 1179–1193. DOI: 10.1631/FITEE.2000243.
  28. [28] Z. Cui, L. Lin, Z. Pu, and Y. Wang, (2020) “Graph Markov network for traffic forecasting with missing data" Transportation Research Part C: Emerging Technologies 117: 102671. DOI: 10.1016/j.trc.2020.102671.
  29. [29] C. Tang, J. Sun, Y. Sun, M. Peng, and N. Gan, (2020) “A general traffic flow prediction approach based on spatialtemporal graph attention" IEEE Access 8: 153731– 153741. DOI: 10.1109/ACCESS.2020.3018452.
  30. [30] A. Shojaie and E. B. Fox, (2022) “Granger causality: A review and recent advances" Annual Review of Statistics and Its Application 9: 289–319. DOI: 10.1146/annurev-statistics-040120-010930.
  31. [31] A. Wismüller, A. M. Dsouza, M. A. Vosoughi, and A. Abidin, (2021) “Large-scale nonlinear Granger causality for inferring directed dependence from short multivariate time-series data" Scientific reports 11(1): 7817. DOI: 10.1038/s41598-021-87316-6.
  32. [32] A. Tank, I. Covert, N. Foti, A. Shojaie, and E. B. Fox, (2021) “Neural Granger Causality" IEEE Transactions on Pattern Analysis and Machine Intelligence 44(8): 4267–4279. DOI: 10.1109/TPAMI.2021.3065601.
  33. [33] W. Ren, B. Li, and M. Han, (2020) “A novel Granger causality method based on HSIC-Lasso for revealing nonlinear relationship between multivariate time series" Physica A: Statistical Mechanics and its Applications 541: 123245. DOI: 10.1016/j.physa.2019.123245.
  34. [34] S. Löwe, D. Madras, R. Zemel, and M. Welling. “Amortized causal discovery: Learning to infer causal graphs from time-series data”. In: Conference on Causal Learning and Reasoning. 2022, 509–525.
  35. [35] Y. Cheng, R. Yang, T. Xiao, Z. Li, J. Suo, K. He, and Q. Dai. “CUTS: Neural Causal Discovery from Irregular Time-Series Data”. In: International Conference on Learning Representations. 2022.
  36. [36] G. Hooker, L. Mentch, and S. Zhou, (2021) “Unrestricted permutation forces extrapolation: variable importance requires at least one more model, or there is no free variable importance" Statistics and Computing 31: 1– 16. DOI: 10.1007/s11222-021-10057-z.