Traffic Prediction Method Integrating Graph Wavelet and Attention Mechanism

doi:10.3778/j.issn.1673-9418.2111012

Abstract

Abstract: Traffic predicting is a critical component of modern intelligent transportation systems for traffic management and control. However, the traffic flow is complex. On one hand, the urban road structure is highly correlative, and there often exists a nonlinear structural dependence between different roads. On the other hand, traffic flow data often change dynamically over time. In recent years, many studies have tried to use deep learning methods to extract complex structural features in traffic flow. However, the process of local feature extraction still lacks flexibility, and ignores the dynamic variability as well as the correlation of spatio-temporal features. To this end, this paper proposes a new traffic prediction method integrating graph wavelet and attention mechanism. This method uses wavelet transform and an adaptive matrix to extract local and global spatial features of traffic flow respectively, and combines the improved recurrent neural network to extract local temporal characteristic information. Meanwhile, the attention mechanism is adopted in this method to capture the temporal and spatial dynamic variability. Then this method applies a spatio-temporal feature fusion mechanism to fusing local and global temporal and spatial features. Experimental results show that this method can extract spatial and temporal features of real traffic datasets well, and it outperforms the existing methods.

Key words: graph convolutional network, intelligent transportation system, attention mechanism, wavelet transform, spatio-temporal correlation

摘要： 交通流预测是现代智能交通系统管理和控制的重要环节。然而，交通流复杂多变，一方面城市道路之间联系性强，另一方面道路交通情况还会随着时间呈现动态变化。近年来有许多研究者尝试利用深度学习方法提取交通流中复杂的结构特征，但是局部特征提取的过程缺乏灵活性，同时忽略了时空特征的动态变化性以及局部和全局时空特征之间的关联性。因此，提出了一种融合图小波和注意力机制的交通流预测方法。该方法采用小波变换和自适应矩阵分别提取交通流局部和全局空间特征信息，并结合改进的循环神经网络提取局部时间特征信息。同时，该方法通过注意力机制来捕获时空动态变化性，并利用一种时空特征融合机制来融合局部和全局时空特征信息。实验结果表明，该方法能很好地提取真实交通数据集中空间和时间特征，预测效果优于现有的方法。

关键词: 图卷积网络, 智能交通系统, 注意力机制, 小波变换, 时空相关性

XUE Yanming, LI Guanghui, QI Tao. Traffic Prediction Method Integrating Graph Wavelet and Attention Mechanism[J]. Journal of Frontiers of Computer Science and Technology, 2023, 17(6): 1405-1416.

薛延明, 李光辉, 齐涛. 融合图小波和注意力机制的交通流预测方法[J]. 计算机科学与探索, 2023, 17(6): 1405-1416.

References

[1] LIPPI M, BERTINI M, FRASCONI P. Short-term traffic flow forecasting: an experimental comparison of time-series analysis and supervised learning[J]. IEEE Transactions on Intelligent Transportation Systems, 2013, 14(2): 871-882.
[2] SMOLA A J, SCH?LKOPF B. A tutorial on support vector regression[J]. Statistics and Computing, 2004, 14(3): 199-222.
[3] KUMAR S V, VANAJAKSHI L. Short-term traffic flow prediction using seasonal ARIMA model with limited input data[J]. European Transport Research Review, 2015, 7(3): 1-9.
[4] MA X, TAO Z, WANG Y, et al. Long short-term memory neural network for traffic speed prediction using remote microwave sensor data[J]. Transportation Research Part C: Emerging Technologies, 2015, 54: 187-197.
[5] VINAYAKUMAR R, SOMAN K P, POORNACHANDRAN P. Applying deep learning approaches for network traffic prediction[C]//Proceedings of the 2017 International Con-ference on Advances in Computing, Communications and Informatics, Udupi, Sep 13-16, 2017. Piscataway: IEEE, 2017: 2353-2358.
[6] MA X, DAI Z, HE Z, et al. Learning traffic as images: a deep convolutional neural network for large-scale transportation network speed prediction[J]. Sensors, 2017, 17(4): 818.
[7] CHEN Q, SONG X, YAMADA H, et al. Learning deep rep-resentation from big and heterogeneous data for traffic acci-dent inference[C]//Proceedings of the 30th AAAI Confer-ence on Artificial Intelligence, Phoenix, Feb 12-17, 2016. Menlo Park: AAAI, 2016: 338-344.
[8] WELLING M, KIPF T N. Semi-supervised classification with graph convolutional networks[J]. arXiv:1609.02907, 2016.
[9] ZHAO L, SONG Y, ZHANG C, et al. T-GCN: a temporal graph convolutional network for traffic prediction[J]. IEEE Transactions on Intelligent Transportation Systems, 2019, 21(9): 3848-3858.
[10] YU B, YIN H, ZHU Z. Spatio-temporal graph convolutional networks: a deep learning framework for traffic forecasting[C]//Proceedings of the 27th International Joint Conference on Artificial Intelligence, Stockholm, Jul 13-19, 2018: 3634- 3640.
[11] LI Y G, YU R, SHAHABI C, et al. Diffusion convolutional recurrent neural network: data-driven traffic forecasting[C]//Proceedings of the 6th International Conference on Learning Representations, Vancouver, Apr 30-May 3, 2018: 1-16.
[12] CUI Z, HENRICKSON K, KE R, et al. Traffic graph convolutional recurrent neural network: a deep learning framework for network-scale traffic learning and forecast-ing[J]. IEEE Transactions on Intelligent Transportation Systems, 2019, 21(11): 4883-4894.
[13] WANG X Y, MA Y, WANG Y Q, et al. Traffic flow prediction via spatial temporal graph neural network[C]//Proceedings of the Web Conference 2020, Taipei, China, Apr 20-24, 2020. New York: ACM, 2020: 1082-1092.
[14] 冯宁, 郭晟楠, 宋超, 等. 面向交通流量预测的多组件时空图卷积网络[J]. 软件学报, 2019, 30(3): 759-769.
FENG N, GUO S N, SONG C, et al. Multi-component spatial-temporal graph convolution networks for traffic flow forecasting[J]. Journal of Software, 2019, 30(3): 759-769.
[15] CUI Z, KE R, PU Z, et al. Learning traffic as a graph: a gated graph wavelet recurrent neural network for network-scale traffic prediction[J]. Transportation Research Part C: Emerging Technologies, 2020, 115: 102620.
[16] HAMMOND D K, VANDERGHEYNST P, GRIBONVAL R. Wavelets on graphs via spectral graph theory[J]. Applied and Computational Harmonic Analysis, 2011, 30(2): 129-150.
[17] DEFFERRARD M, BRESSON X, VANDERGHEYNST P. Convolutional neural networks on graphs with fast localized spectral filtering[C]//Advances in Neural Information Pro-cessing Systems 29, Barcelona, Dec 5-10, 2016: 3844-3852.
[18] WU Z H, PAN S R, LONG G D, et al. Graph WaveNet for deep spatial-temporal graph modeling[C]//Proceedings of the 28th International Joint Conference on Artificial Intelli-gence, Macao, China, Aug 10-16, 2019: 1907-1913.
[19] ZHAO J Y, HUANG F Q, LV J, et al. Do RNN and LSTM have long memory?[C]//Proceedings of the 37th International Conference on Machine Learning, Jul 13-18, 2020: 11365-11375.
[20] VASWANI A, SHAZEER N, PARMAR N, et al. Attention is all you need[C]//Advances in Neural Information Processing Systems 30, Long Beach, Dec 4-9, 2017: 5998-6008.
[21] CUI Z, KE R, PU Z, et al. Deep bidirectional and unidirec-tional LSTM recurrent neural network for network-wide traffic speed prediction[J]. arXiv:1801.02143, 2018.
[22] WANG Y H, ZHANG W B, HENRICKSON K, et al. Digital roadway interactive visualization and evaluation network applications to WSDOT operational data usage: WA-RD 854.1[R]. Seattle: University of Washing, 2016.
[23] CHEN C, PETTY K, SKABARDONIS A, et al. Freeway performance measurement system: mining loop detector data[J]. Transportation Research Record, 2001 (1): 96-102.
[24] ZHENG C P, FAN X L, WANG C, et al. GMAN: a graph multiattention network for traffic prediction[C]//Proceed-ings of the 34th AAAI Conference on Artificial Intelligence, the 32nd Innovative Applications of Artificial Intelligence Conference, the 10th AAAI Symposium on Educational Advances in Artificial Intelligence, New York, Feb 7-12, 2020. Menlo Park: AAAI, 2020: 1234-1241.