Abstract
Traffic flow forecasting is a hotspot in the field of the smart city. It is a highly nonlinear, complex, and dynamic problem affected by many factors. The traditional methods cannot well model the dynamic spatial-temporal correlations of long-range time series data in the traffic network, which reduces the forecast accuracy. In this paper, we proposed a novel attention-based graph neural network predictor to forecast traffic flow. A more flexible and efficient convolution operation is defined in our predictor based on graph wavelet transform. The predictor can capture both spatial and temporal relationships based on a graph wavelet neural network. More specifically, the network adopts the spatial-temporal attention mechanism to capture the dynamic spatial-temporal correlations, and the dilated 1D convolution component is stacked to handle long sequences. We made experiments on two real-world benchmark datasets to verify the accuracy of the proposed network.
This work is supported by the National Natural Science Foundation of China under Grant Nos. (61703013, 91646201).
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
Abadi, A., Rajabioun, T., Ioannou, P.A.: Traffic flow prediction for road transportation networks with limited traffic data. IEEE Trans. Intell. Transp. Syst. 16(2), 653–662 (2015)
Mackenzie, J., Roddick, J.F., Zito, R.: An evaluation of HTM and LSTM for short-term arterial traffic flow prediction. IEEE Trans. Intell. Transp. Syst. 20(5), 1847–1857 (2019)
Feng, X., Ling, X., Zheng, H., Chen, Z., Xu, Y.: Adaptive multi-kernel SVM with spatial-temporal correlation for short-term traffic flow prediction. IEEE Trans. Intell. Transp. Syst. 20(6), 2001–2013 (2019)
Guo, S., Lin, Y., Feng, N., Song, C., Wan, H.: Attention based spatial-temporal graph convolutional networks for traffic flow forecasting. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 33, pp. 922–929 (2019). https://doi.org/10.1609/aaai.v33i01.3301922
Xu, B., Shen, H., Cao, Q., Qiu, Y., Cheng, X.: Graph wavelet neural network. In: International Conference for Learning Representations (ICLR 2019), New Orleans, LA, USA, p. 13 (2019). https://openreview.net/forum?id=H1ewdiR5tQ
Donnat, C., Zitnik, M., Hallac, D., Leskovec, J.: Learning structural node embeddings via diffusion wavelets. In: Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, London, United Kingdom, pp. 1320–1329 (2018). https://doi.org/10.1145/3219819.3220025
Hammond, D.K., Vandergheynst, P., Gribonval, R.: Wavelets on graphs via spectral graph theory. Appl. Comput. Harmonic Anal. 30(2), 129–150 (2011). https://doi.org/10.1016/j.acha.2010.04.005
Tremblay, N., Borgnat, P.: Graph wavelets for multiscale community mining. IEEE Trans. Signal Process. 62(20), 5227–5239 (2014)
Kamarianakis, Y., Vouton, V.: Forecasting traffic flow conditions in an urban network: comparison of multivariate and univariate approaches. Transp. Res. Rec. 1857, 74–84 (2003). https://doi.org/10.3141/1857-09
Williams, B., Hoel, L.: Modeling and forecasting vehicular traffic flow as a seasonal ARIMA process: theoretical basis and empirical results. J. Transp. Eng. 129, 664–672 (2003). https://doi.org/10.1061/(ASCE)0733-947X(2003)129:6(664)
Fradinata, E., Kesuma, Z.M., Rusdiana, S., Zaman, N.: Forecast analysis of instant noodle demand using support vector regression (SVR). In: IOP Conference Series: Materials Science and Engineering, Politeknik Aceh Selatan Campus, Indonesia, vol. 506 (2019). https://doi.org/10.1088/1757-899X/506/1/012021.
Ma, Y., Zhang, Z., Ihler, A.: Multi-lane short-term traffic forecasting with convolutional LSTM network. IEEE Access 8, 34629–34643 (2020)
Adege, A.B., Lin, H., Wang, L.: Mobility predictions for IoT devices using gated recurrent unit network. IEEE Internet Things J. 7(1), 505–517 (2020)
Seo, Y., Defferrard, M., Vandergheynst, P., Bresson, X.: Structured sequence modeling with graph convolutional recurrent networks, vol. 1, no. 1, pp. 1–10. arXiv:1612.07659 [stat.ML] (2016)
Li, Y., Yu, R., Shahabi, C., Liu, Y.: Diffusion convolutional recurrent neural network: data-driven traffic forecasting. In: International Conference on Learning Representations, Vancouver, BC, Canada, p. 16 (2018)
Yu, B., Yin, H., Zhu, Z.: Spatio-temporal graph convolutional networks: a deep learning framework for traffic forecasting. In: Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence, IJCAI 2018, Stockholm, Sweden, 13–19 July 2018, pp. 3634–3640 (2018). https://doi.org/10.24963/ijcai.2018/505.
Kipf, T.N., Welling, M.: Semi-supervised classification with graph convolutional networks. In: International Conference on Learning Representations (ICLR 2017), Toulon, France, 24–26 April 2017. https://openreview.net/forum?id=SJU4ayYgl
Defferrard, M., Bresson, X., Vandergheynst, P.: Convolutional neural networks on graphs with fast localized spectral filtering. In: Advances in Neural Information Processing Systems 29: Annual Conference on Neural Information Processing Systems 2016, Barcelona, Spain, pp. 3837–3845 (2016)
Mishra, K., Basu, S., Maulik, U.: DaNSe: a dilated causal convolutional network based model for load forecasting. In: Deka, B., Maji, P., Mitra, S., Bhattacharyya, D.K., Bora, P.K., Pal, S.K. (eds.) PReMI 2019. LNCS, vol. 11941, pp. 234–241. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-34869-4_26
Khanna, A., Londhe, N.D., Gupta, S., Semwal, A.: A deep residual U-Net convolutional neural network for automated lung segmentation in computed tomography images. Biocybern. Biomed. Eng. 40(3), 1314–1327 (2020). https://doi.org/10.1016/j.bbe.2020.07.007
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
Jiang, S., Zhu, M., Li, J. (2021). Traffic Flow Forecasting Using a Spatial-Temporal Attention Graph Convolutional Network Predictor. In: Meng, X., Xie, X., Yue, Y., Ding, Z. (eds) Spatial Data and Intelligence. SpatialDI 2020. Lecture Notes in Computer Science(), vol 12567. Springer, Cham. https://doi.org/10.1007/978-3-030-69873-7_8
Download citation
DOI: https://doi.org/10.1007/978-3-030-69873-7_8
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-69872-0
Online ISBN: 978-3-030-69873-7
eBook Packages: Computer ScienceComputer Science (R0)