Abstract
Accurate traffic flow forecasting is a prerequisite guarantee for the realization of intelligent transportation. Due to the complex time and space features of traffic flow, its forecasting has always been a research hotspot in this field. Aiming at the difficulty of capturing and modelling the temporal and spatial correlation and dynamic features of traffic flow, this paper proposes a novel graph convolutional network traffic flow forecasting model (STAGCN) based on the temporal and spatial attention mechanism. STAGCN model is mainly composed of three modules: Spatio-temporal Attention (STA-Block), Graph Convolutional Network (GCN) and Standard Convolutional Network (CN), model the periodicity, spatial correlation and time dependence of traffic flow respectively. STA-Block module models the spatio-temporal correlation between different time steps through the spatio-temporal attention mechanism and gating fusion mechanism, and uses GCN and CN to capture the spatial and temporal features of traffic flow respectively. Finally, the output of the three components is predicted through a gated fusion mechanism. A large number of experiments have been conducted on two data sets of PeMS. The experimental results demonstrate that compared with the baseline method, the STAGCN model proposed in this paper has better forecasting performance.
Article PDF
Similar content being viewed by others
Explore related subjects
Discover the latest articles, news and stories from top researchers in related subjects.Avoid common mistakes on your manuscript.
Abbreviations
- G :
-
traffic road network
- V :
-
group of road nodes
- N :
-
number of nodes
- E :
-
set of edges
- A :
-
adjacency matrix
- τ :
-
time slices
- Y :
-
future traffic flow sequence
- i :
-
road node
- t :
-
time, min
- f :
-
traffic flow sequence
- D :
-
value of the features of all nodes
- \(X_t^i\) :
-
eigenvalues of node i at time t
- X t :
-
feature values of nodes at the moment of t
- \(y_t^i\) :
-
traffic flow of node i at time t
- T h :
-
input of the recent component
- T d :
-
input of the daily-period component
References
Blu, T., Thevenaz, P. and Unser, M. (2004). Linear interpolation revitalized. IEEE Trans. Image Processing 13, 5, 710–719.
Chao, C., Petty, K. and Skabardonis, A. (2000). Freeway performance measurement: Mining loop detector data. Transportation Research Record J. Transportation Research Board 1748, 1, 96–102.
Chen, W., Chen, L., Xie, Y., Cao, W., Gao, Y. and Feng, X. (2020). Multi-range attentive bicomponent graph convolutional network for traffic forecasting. 34th AAAI Conf. Artificial Intelligence (AAAI), New York, USA.
Cheng, W., Shen, Y., Zhu, Y. and Huang, L. (2018). A neural attention model for urban air quality inference: Learning the weights of monitoring stations. 32nd AAAI Conf. Artificial Intelligence (AAAI), New Orleans, Louisiana, USA.
Cui, Z., Henrickson, K., Ke, R. and Wang, Y. (2019). Traffic graph convolutional recurrent neural network: A deep learning framework for network-scale traffic learning and forecasting. IEEE Trans. Intelligent Transportation Systems 21, 11, 4883–4894.
Cui, Z., Ke, R., Pu, Z. and Wang, Y. (2018). Deep bidirectional and unidirectional LSTM recurrent neural network for network-wide traffic speed prediction. arXiv. 1801.02143.
Defferrard, M., Bresson, X. and Vandergheynst, P. (2016). Convolutional neural networks on graphs with fast localized spectral filtering. 30th Int. Conf. Neural Information Processing Systems (NIPS), Barcelona, Spain.
Deng, D., Shahabi, C., Demiryurek, U., Zhu, L., Yu, R. and Liu, Y. (2016). Latent space model for road networks to predict time-varying traffic. 22nd ACM SIGKDD Int. Conf. knowledge Discovery and Data Mining (KDD), San Francisco, California, USA.
Huang, W., Song, G., Hong, H. and Xie, K. (2014). Deep architecture for traffic flow prediction: Deep belief networks with multitask learning. IEEE Trans. Intelligent Transportation Systems 15, 5, 2191–2201.
Kipf, T. N. and Welling, M. (2016). Semi-supervised classification with graph convolutional networks. arXiv: 1609.02907.
Kumar, K., Parida, M. and Katiyar, V. K. (2013). Short term traffic flow prediction for a non urban highway using artificial neural network. Procedia-Social and Behavioral Sciences, 104, 755–764.
Kumar, S. V. and Vanajakshi, L. (2015). Short-term traffic flow prediction using seasonal ARIMA model with limited input data. European Transport Research Review 7, 3, 1–9.
Lecun, Y., Bengio, Y. and Hinton, G. (2015). Deep learning. Nature 521, 7553, 436–444.
Li, Y., Yu, R., Shahabi, C. and Liu, Y. (2017). Diffusion convolutional recurrent neural network: Data-driven traffic forecasting. arXiv. 1707.01926.
Liang, Y., Ke, S., Zhang, J., Yi, X. and Zheng, Y. (2018). GeoMAN: Multi-level attention networks for geo-sensory time series prediction. 27th Int. Joint Conf. Artificial Intelligence (IJCAI), Stockholm, Sweden.
Lippi, M., Bertini, M. and Frasconi, P. (2013). Short-term traffic flow forecasting: An experimental comparison of time-series analysis and supervised learning. IEEE Trans. Intelligent Transportation Systems 14, 2, 871–882.
Lv, Y., Duan, Y., Kang, W., Li, Z. and Wang, F. Y. (2015). Traffic flow prediction with big data: A deep learning approach. IEEE Trans. Intelligent Transportation Systems 16, 2, 865–873.
Polson, N. G. and Sokolov, V. O. (2017). Deep learning for short-term traffic flow prediction. Transportation Research Part C: Emerging Technologies, 79, 1–17.
Sen, R., Yu, H. F. and Dhillon, I. S. (2019). Think globally, act locally: A deep neural network approach to high-dimensional time series forecasting. arXiv. 1905.03806.
Shekhar, S. and Williams, B. M. (2007). Adaptive seasonal time series models for forecasting short-term traffic flow. Transportation Research Record 2024, 1, 116–125.
Shen, T., Zhou, T., Long, G., Jiang, J. Pan, S. and Zhang, C. (2018). DiSAN: Directional self-attention network for RNN/CNN-free language understanding. 32nd AAAI Conf. Artificial Intelligence (AAAI), New Orleans, Louisiana, USA.
Simonovsky, M. and Komodakis, N. (2017). Dynamic edge-conditioned filters in convolutional neural networks on graphs. IEEE Conf. Computer Vision and Pattern Recognition (CVPR), Honolulu, Hawaii, USA.
Song, C., Lin, Y., Guo, S. and Wan, H. (2020). Spatial-temporal synchronous graph convolutional networks: A new framework for spatial-temporal network data forecasting. 34th AAAI Conf. Artificial Intelligence (AAAI), New York, USA.
Tong, Y., Chen, Y., Zhou, Z., Chen, L., Wang, J., Yang, Q., Ye, J. and Lv, W. (2017). The simpler the better: A unified approach to predicting original taxi demands based on large-scale online platforms. 23rd ACM SIGKDD Int. Conf. Knowledge Discovery & Data Mining (KDD), Halifax, Nova Scotia, Canada.
Veličković, P., Cucurull, G., Casanova, A., Romero, A., Lio, P. and Bengio, Y. (2017). Graph attention networks. arXiv.1710.10903.
Wang, J., Cao, Y., Du, Y. and Li, L. (2019). DST: A deep urban traffic flow prediction framework based on spatial-temporal features. 12th Int. Conf. Knowledge Science, Engineering and Management (KSEM), Athens, Greece.
Wu, F., Wang, H. and Li, Z. (2016). Interpreting traffic dynamics using ubiquitous urban data. 24th ACM SIGSPATIAL Int. Conf. Advances in Geographic Information Systems (GIS), San Francisco, California, USA.
Wu, Z., Pan, S., Long, G., Jiang, J. and Zhang, C. (2019). Graph wavenet for deep spatial-temporal graph modeling. arXiv. 1906.00121.
Xu, K., Ba, J., Kiros, R., Cho, K., Courville, A., Salakhudinov, R., Zemel, R. and Bengio, Y. (2015). Show, attend and tell: Neural image caption generation with visual attention. 32nd Int. Conf. Machine Learning (ICML), Lille, France.
Xu, M., Dai, W., Liu, C., Gao, X., Lin, W., Qi, G. J. and Xiong, H. (2020). Spatial-temporal transformer networks for traffic flow forecasting. arXiv. 2001.02908.
Yang, B., Sun, S., Li, J., Lin, X. and Tian, Y. (2019). Traffic flow prediction using LSTM with feature enhancement. Neurocomputing, 332, 320–327.
Yao, H., Wu, F., Ke, J., Tang, X., Jia, Y., Lu, S., Gong, P., Ye, J. and Li, Z. (2018). Deep multi-view spatial-temporal network for taxi demand prediction. 32nd AAAI Conf. Artificial Intelligence (AAAI), New Orleans, Louisiana, USA.
Yu, B., Yin, H. and Zhu, Z. (2017) Spatio-temporal graph convolutional networks: A deep learning framework for traffic forecasting. arXiv. 1709.04875.
Zhang, J., Yu, Z. and Qi, D. (2016a) Deep spatio-temporal residual networks for citywide crowd flows prediction. arXiv. 1610.00081.
Zhang, J., Zheng, Y., Qi, D., Li, R. and Yi, K. (2016b) DNN-based prediction model for spatio-temporal data. 24th ACM SIGSPATIAL Int. Conf. Advances in Geographic Information Systems (GIS), San Francisco, California, USA.
Zhang, Y., Jiang, Q., Li, S., Jin, X., Ma, X. and Yan, X. (2019). You may not need order in time series forecasting. arXiv. 1910.09620.
Zheng, C., Fan, X., Wang, C. and Qi, J. (2020). Gman: A graph multi-attention network for traffic prediction. 34th AAAI Conf. Artificial Intelligence (AAAI), New York, USA.
Acknowledgement
This work was supported by Natural Science Foundation of Gansu Province, China (Grant No. 20JR 5RA450); National Key Research and Development Plan (Grant No.2019YFB1707303).
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher’s Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Zhang, H., Chen, L., Cao, J. et al. Traffic Flow Forecasting of Graph Convolutional Network Based on Spatio-Temporal Attention Mechanism. Int.J Automot. Technol. 24, 1013–1023 (2023). https://doi.org/10.1007/s12239-023-0083-9
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s12239-023-0083-9