Short-Time Prediction Model for Urban Traffic Flow Based on Joint Spatio-Temporal Learning

doi:10.19678/j.issn.1000-3428.0063680

Abstract

Abstract: A joint spatio-temporal analysis can reflect the changing pattern of a studied object in the spatio-temporal dimension, which is significant for revealing the spatio-temporal interactions and mechanisms of regional processes.With a focus on joint spatio-temporal feature learning and modeling of traffic flow physical characteristics, this paper proposes a dynamic hierarchical network model called the JST-DHNet, which involves multi-scale joint spatio-temporal learning and physics-informed learning.First, instead of simply connecting adjacent graph snapshots like in previous studies, we developed multiple spatio-temporal graph structures using the graph product.Next, based on the joint time-vertex wavelet transform and Fourier transform, two spatial-temporal synchronous learning modules with different scales are designed to learn the global and local spatio-temporal characteristics of traffic flow, respectively.Based on the macroscopic fluid-dynamical properties of the traffic flow, we developed a novel spatio-temporal diffusion convolution with a graph-based partial differential equation, which enables the learning of the propagation mechanism of traffic waves in actual physical scenarios.Finally, the fusion of joint spatio-temporal features at different scales is performed by adopting an attention mechanism.After testing on four datasets of actual road network traffic flow with different sizes, the experimental results show that JST-DHNet outperforms other separated learning models.Compared with the existing joint spatio-temporal learning model called Spatial-Temporal Synchronous Graph Convolutional Network(STSGCN), JST-DHNet not only improves the prediction accuracy of the Mean Absolute Percentage Error (MAPE), Mean Absolute Error (MAE), and Root-Mean-Squared Error (RMSE) by 4.46%, 6.65%, and 10.11%, respectively, but also shortens the training time by nearly 80%.

Key words: Intelligent Traffic System(ITS), spatio-temporal union, traffic flow prediction, Graph Signal Processing (GSP), traffic flow theory

摘要： 时空联合分析可反映研究对象在时空维的变化规律，对揭示区域过程的时空交互关系和机制具有重要意义。聚焦时空联合特征的学习与交通流物理特性的建模问题，提出一种层次化的动态网络模型JST-DHNet，以融合不同尺度下的时空联合学习与内嵌领域知识学习。利用基于图乘积运算替代以往矩阵拼接方式构建多种时空图结构。结合时空小波变换与时空傅里叶变换，设计2种不同层次的时空同步学习模块，分别学习交通流的全域与局域时空特征。针对交通流的宏观流体动力学性质，通过基于图的广义偏微分方程设计一种新的时空扩散卷积，以学习真实场景下的交通波传播机制。在此基础上，采用注意力机制将不同尺度的时空联合特征进行融合。在4种不同路网规模的真实交通流数据集上进行测试，结果表明，JST-DHNet的预测性能优于采用时空分离式学习模块的预测模型，相比STSGCN时空联合学习模型，JST-DHNet预测精度的平均绝对百分比误差、平均绝对误差和均方根误差分别降低4.46%、6.65%、10.11%，且训练时间缩短近80%。

关键词: 智能交通系统, 时空域联合, 交通流预测, 图信号处理, 交通流理论

CLC Number:

TP391

GE Yuran, FU Qiang. Short-Time Prediction Model for Urban Traffic Flow Based on Joint Spatio-Temporal Learning[J]. Computer Engineering, 2023, 49(1): 270-278.

葛宇然, 付强. 基于时空联合学习的城市交通流短时预测模型[J]. 计算机工程, 2023, 49(1): 270-278.

/ / Recommend / Download Citations

URL: http://www.ecice06.com/EN/10.19678/j.issn.1000-3428.0063680

http://www.ecice06.com/EN/Y2023/V49/I1/270

Figures/Tables 12

References

[1] 王婧娟, 陈庆奎.一种时空周期性注意力网络的交通流量预测模型[J].小型微型计算机系统, 2022, 43(11):2321-2327. WANG J J, CHEN Q K.Traffic flow prediction model based on the spatio-temporal periodic attention network[J].Journal of Chinese Computer Systems, 2022, 43(11):2321-2327.(in Chinese)
[2] LANA I, DEL SER J, VELEZ M, et al.Road traffic forecasting:recent advances and new challenges[J].IEEE Intelligent Transportation Systems Magazine, 2018, 10(2):93-109.
[3] 杨立宁, 李艳婷.基于SVD和ARIMA的时空序列分解与预测[J].计算机工程, 2021, 47(3):53-61. YANG L N, LI Y T.Spatio-temporal sequence decomposition and prediction based on SVD and ARIMA[J].Computer Engineering, 2021, 47(3):53-61.(in Chinese)
[4] CHANDRA S R, AL-DEEK H.Predictions of freeway traffic speeds and volumes using vector autoregressive models[J].Journal of Intelligent Transportation Systems, 2009, 13(2):53-72.
[5] CAI L R, YU Y D, ZHANG S Y, et al.A sample-rebalanced outlier-rejected-nearest neighbor regression model for short-term traffic flow forecasting[J].IEEE Access, 2020, 8:22686-22696.
[6] WEI D L, LIU H C.An adaptive-margin support vector regression for short-term traffic flow forecast[J].Journal of Intelligent Transportation Systems, 2013, 17(4):317-327.
[7] KUMAR S V.Traffic flow prediction using Kalman filtering technique[J].Procedia Engineering, 2017, 187:582-587.
[8] JIANG W W, LUO J Y.Graph neural network for traffic forecasting:a survey[J].Expert Systems with Applications, 2022, 207:117921.
[9] YU B, YIN H T, ZHU Z X.Spatio-temporal graph convolutional networks:a deep learning framework for traffic forecasting[C]//Proceedings of the 27th International Joint Conference on Artificial Intelligence.Washington D.C., USA:IEEE Press, 2018:3634-3640.
[10] GUO S N, LIN Y F, FENG N, et al.Attention based spatial-temporal graph convolutional networks for traffic flow forecasting[J].Proceedings of the AAAI Conference on Artificial Intelligence, 2019, 33:922-929.
[11] YAGUANG L, ROSE Y, CYRUS S, et al.Diffusion convolutional recurrent neural network:data-driven traffic forecasting[EB/OL].[2021-11-05].https://arxiv.org/pdf/1707.01926.pdf.
[12] 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 Intelligence.Washington D.C., USA:IEEE Press, 2019:1907-1913.
[13] SUN L, YAN Z, MELLADO S M, et al.3DOF pedestrian trajectory prediction learned from long-term autonomous mobile robot deployment data[C]//Proceedings of IEEE International Conference on Robotics and Automation.Washington D.C., USA:IEEE Press, 2018:5942-5948.
[14] 朱煜, 赵江坤, 王逸宁, 等.基于深度学习的人体行为识别算法综述[J].自动化学报, 2016, 42(6):848-857. ZHU Y, ZHAO J K, WANG Y N, et al.A review of human action recognition based on deep learning[J].Acta Automatica Sinica, 2016, 42(6):848-857.(in Chinese)
[15] BAI L, YAO L N, KANHERE S S, et al.STG2Seq:spatial-temporal graph to sequence model for multi-step passenger demand forecasting[C]//Proceedings of the 28th International Joint Conference on Artificial Intelligence.Washington D.C., USA:IEEE Press, 2019:1981-1987.
[16] SONG C, LIN Y F, GUO S N, et al.Spatial-temporal synchronous graph convolutional networks:a new framework for spatial-temporal network data forecasting[J].Proceedings of the AAAI Conference on Artificial Intelligence, 2020, 34(1):914-921.
[17] PAN C, CHEN S, ORTEGA A.Spatio-temporal graph scattering transform[C]//Proceedings of the 9th International Conference on Learning Representations.Washington D.C., USA:IEEE Press, 2021:122-136.
[18] LOUKAS A, FOUCARD D.Frequency analysis of time-varying graph signals[C]//Proceedings of IEEE Global Conference on Signal and Information Processing.Washington D.C., USA:IEEE Press, 2016:346-350.
[19] GRASSI F, LOUKAS A, PERRAUDIN N, et al.A time-vertex signal processing framework:scalable processing and meaningful representations for time-series on graphs[J].IEEE Transactions on Signal Processing, 2018, 66(3):817-829.
[20] KIPF T, WELLING M.Semi-supervised classification with graph convolutional networks[C]//Proceedings of the 5th International Conference on Learning Representations.Washington D.C., USA:IEEE Press, 2017:16-22.
[21] NATALI A, ISUFI E, LEUS G.Forecasting multi-dimensional processes over graphs[C]//Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing.Washington D.C., USA:IEEE Press, 2020:5575-5579.
[22] GAO F, WOLF G, HIRN M.Geometric scattering for graph data analysis[C]//Proceedings of the 36th International Conference on Machine Learning.Washington D.C., USA:IEEE Press, 2019:2122-2131.
[23] MIN Y, WENKEL F, WOLF G.Scattering GCN:overcoming oversmoothness in graph convolutional networks[J].Advances in Neural Information Processing Systems, 2020, 33:14498-14508.
[24] 陈永, 张薇.高速跟驰交通流动力学模型研究[J].物理学报, 2020, 69(6):064501. CHEN Y, ZHANG W.Dynamic model of high speed following traffic flow[J].Acta Physica Sinica, 2020, 69(6):064501.(in Chinese)
[25] GRASSI F, PERRAUDIN N, RICAUD B.Tracking time-vertex propagation using dynamic graph wavelets[C]//Proceedings of IEEE Global Conference on Signal and Information Processing.Washington D.C., USA:IEEE Press, 2016:351-355.
[26] SUTSKEVER I, VINYALS O, LE Q V.Sequence to sequence learning with neural networks[C]//Proceedings of the 27th International Conference on Neural Information Processing Systems.Washington D.C., USA:IEEE Press, 2014:3104-3112.

Please choose a citation manager

Content to export