Abstract
In the Intelligent Traffic System (ITS), accurate prediction of the state of the traffic at the next moment is of great significance to transportation planning. Existing researches mainly focus on the research of the topological structure of the road network in space, and consider the temporal dependence at the same time. However, we have noticed that it is not only important to consider the dependence of time and space at the same time, but also other organizational relationships between the road network will also affect the forecast results. In this paper, we reconsider the correlation between roads and capture their correlation in both space and time. More specifically, we first encode the road network into two graphs (connect graph and similar graph) based on the connectivity and historical pattern similarity, and merge the graphs to make the connected edges carry more information. Then graph convolution is used for the fused graph. In order to capture the temporal dependence, we use one-dimensional convolution to first convolve the information before the graph convolution, and then perform the one-dimensional convolution on the information after the fusion graph, which can achieve fast spatial-state propagation from graph convolution through fast spatial-state propagation. We evaluate the predictive performance of our model by real-world traffic dataset and experiments prove that the addition of multi-graph is effective. Compared with the relatively new baseline, RMSE has dropped by about 10\(\%\).
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Ahmed, M., Cook, A.: Analysis of freeway traffic time series data by using Box-Jenkins techniques. Transp. Res. Rec. 773, 1–9 (1979)
Dauphin, Y.N., Fan, A., Auli, M., Grangier, D.: Language modeling with gated convolutional networks (2016)
Defferrard, M., Bresson, X., Vandergheynst, P.: Convolutional neural networks on graphs with fast localized spectral filtering (2016)
Defferrard, M., Bresson, X., Vandergheynst, P.: Convolutional neural networks on graphs with fast localized spectral filtering (2016)
Hamed, M., Al-Masaeid, H., Said, Z.: Short-term prediction of traffic volume in urban arterials. J. Transp. Eng. ASCE - J. Transp. Eng. ASCE 121 (05 1995). https://doi.org/10.1061/(ASCE)0733-947X(1995)121:3(249)
Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Computation 9(8), 1735–1780 (1997)
KipF, T.N., Welling, M.: Semi-supervised classification with graph convolutional networks (2016)
Liu, J., Wei, G.: A summary of traffic flow forecasting methods. J. Highw. Transp. Res. Dev. 3, 82–85 (2004)
Okutani, I., Stephanedes, Y.J.: Dynamic prediction of traffic volume through Kalman filtering theory. Transp. Res. Part B Methodol. 18(1), 1–11 (1984). https://doi.org/10.1016/0191-2615(84)90002-X. https://www.sciencedirect.com/science/article/pii/019126158490002X
Pearson, K.: VII. Note on regression and inheritance in the case of two parents. Proc. Roy. Soc. Lond. 58, 240-242 (1895)
Sainath, T.N., et al.: Deep convolutional neural networks for large-scale speech tasks. Neural Netw. 64, 39–48 (2015)
Smola\(\dagger \), A., Lkopf\(\ddagger \), B.: A tutorial on support vector regression. Stat. Comput. 14(3), 199–222 (2004)
Tobler, W.R.: A computer movie simulating urban growth in the Detroit region. Econ. Geogr. 46(2) (1970)
Wang, Y., Huang, M., Zhu, X., Zhao, L.: Attention-based LSTM for aspect-level sentiment classification. In: Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing, pp. 606–615. Association for Computational Linguistics, Austin, Texas, November 2016. https://doi.org/10.18653/v1/D16-1058. https://www.aclweb.org/anthology/D16-1058
Williams, B.M., Hoel, L.A.: Modeling and forecasting vehicular traffic flow as a seasonal ARIMA process: theoretical basis and empirical results. J. Transp. Eng. 129(6), 664–672 (2003)
Yan, S., Xiong, Y., Lin, D.: Spatial temporal graph convolutional networks for skeleton-based action recognition (2018)
Zhang, J., Man, K.F.: Time series prediction using RNN in multi-dimension embedding phase space. In: SMC98 Conference IEEE International Conference on Systems (2002)
Zhao, B., Xu, Z., Tang, Y., Li, J., Liu, B., Tian, H.: Effective knowledge-aware recommendation via graph convolutional networks. In: Wang, G., Lin, X., Hendler, J., Song, W., Xu, Z., Liu, G. (eds.) WISA 2020. LNCS, vol. 12432, pp. 96–107. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-60029-7_9
Zhao, L., Song, Y., Zhang, C., Liu, Y., Li, H.: T-GCN: a temporal graph convolutional network for traffic prediction. IEEE Trans. Intell. Transp. Syst. PP(99), 1–11 (2019)
Zhuo, Q., Li, Q., Han, Y., Yong, Q.: Long short-term memory neural network for network traffic prediction. In: 2017 12th International Conference on Intelligent Systems and Knowledge Engineering (ISKE) (2017)
Acknowledgements
This work is supported by the school-enterprise cooperation project of Yanbian University [2020-15], State Language Commission of China under Grant No. YB135-76 and Doctor Starting Grants of Yanbian University [2020-16].
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Yao, X., Zhang, Z., Cui, R., Zhao, Y. (2021). Traffic Prediction Based on Multi-graph Spatio-Temporal Convolutional Network. In: Xing, C., Fu, X., Zhang, Y., Zhang, G., Borjigin, C. (eds) Web Information Systems and Applications. WISA 2021. Lecture Notes in Computer Science(), vol 12999. Springer, Cham. https://doi.org/10.1007/978-3-030-87571-8_13
Download citation
DOI: https://doi.org/10.1007/978-3-030-87571-8_13
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-87570-1
Online ISBN: 978-3-030-87571-8
eBook Packages: Computer ScienceComputer Science (R0)
