作者：南秋彩¹, 杨柳²

作者单位：1. 黄河交通学院, 河南 焦作 450062;
2. 长沙理工大学, 湖南 长沙 410114

关键词：交通预测;图卷积神经网络;降维卷积;特征学习

摘要：

由于交通预测问题的时空复杂性，在智能交通系统中完成预测是一项具有挑战性的任务。虽然交通预测的时间依赖性已经得到很好的研究和讨论，但由于空间依赖的变化较大，特别是在城市复杂交通环境中，对空间依赖的交通预测研究相对较少。该文提出一种新的图卷积预测网络模型，并将其应用于两个具有不同几何约束的城市交通网络。首先，该模型利用多重加权邻接矩阵对速度数据进行图形卷积运算，将速度限制、距离和道路角度等特征组合在一起。其次，对组合特征进行空间隔离降维运算，以学习特征之间的依赖关系，并将输出的大小降低到计算可行水平。然后，将多权图卷积网络的输出应用于具有长短期记忆单元模型，以学习时间依赖。最后，将所提出的预测网络应用于城市核心区和城市混合区两个交通网络，其性能不仅优于其余六种比较模型，而且降低了城市混合区交通网络的预测方差。结果表明，所提出的预测网络能够在不同的空间复杂度下提供稳健的交通预测性能，这在城市交通预测中具有很强的优势。

Graph convolutional neural network based traffic prediction
NAN Qiucai¹, YANG Liu²
1. Huanghe Jiaotong University, Jiaozuo 450062, China;
2. Changsha University of Science and Technology, Changsha 410114, China
Abstract: Due to the spatial and temporal complexity of the traffic prediction problem, accomplishing prediction in intelligent transportation systems is a challenging task. Although the time dependence of traffic prediction has been well studied and discussed, relatively little research has been done on spatially dependent traffic prediction due to the large variability of spatial dependence, especially in complex urban traffic environments. In this paper, a new graph convolution prediction network model is proposed and applied to two urban traffic networks with different geometric constraints. First, the model performs graph convolution operations on speed data using multiple weighted adjacency matrices to combine features such as speed limits, distances, and road angles. Second, spatially isolated dimensionality reduction operations are performed on the combined features to learn the dependencies between the features and reduce the size of the output to a computationally feasible level. Then, the output of the multi-weighted graph convolutional network is applied to a model with long and short-term memory units to learn temporal dependencies. Finally, the proposed prediction network is applied to two traffic networks in urban core and mixed urban areas, and its performance not only outperforms the remaining six comparative models, but also reduces the prediction variance of the traffic network in mixed urban areas. The results show that the proposed prediction network can provide robust traffic prediction performance under different spatial complexities, which is a strong advantage in urban traffic prediction.
Keywords: defect traffic forecast;graph convolution neural network;reduced dimension convolution;feature learning
2023, 49(9):123-132  收稿日期: 2022-08-28;收到修改稿日期: 2022-10-26
基金项目: 湖南省教育厅重点项目（20A009）
作者简介: 南秋彩（1981-）女，河南郏县人，副教授，硕士，研究方向为交通工程管理
参考文献
[1] 康雁, 谢思宇, 王飞, 等. 基于双路信息时空图卷积网络的交通预测模型[J]. 计算机科学, 2021, 48(S2): 46-51+62
[2] 管星宇, 潘义勇. 基于随机参数线性回归的交通流速度-密度关系模型研究[J]. 森林工程, 2021, 37(5): 90-95
[3] 马晓磊, 孙硕, 丁川, 等. 基于TVP-VAR模型的多模式交通需求耦合分析[J]. 北京航空航天大学学报, 2018, 44(1): 18-26
[4] 张腾飞, 袁鹏程. 基于ARIMA的短时交通量预测模型[J]. 智能计算机与应用, 2020, 10(7): 273-278
[5] 周毅, 胡姝婷, 李伟, 等. 图神经网络驱动的交通预测技术: 探索与挑战[J]. 物联网学报, 2021, 5(4): 1-16
[6] 申雷霄, 陆宇航, 郭建华. 卡尔曼滤波短时交通流预测普通国省道适应性研究[J]. 交通信息与安全, 2021, 39(5): 117-127
[7] 陈亮, 王金泓, 何涛, 等. 基于SVR的区域交通碳排放预测研究[J]. 交通运输系统工程与信息, 2018, 18(2): 13-19
[8] 刘永乐, 谷远利. 基于CNN-BiLSTM的高速公路交通流量时空特性预测[J]. 交通科技与经济, 2022, 24(1): 9-18
[9] 王维强, 牛振东, 曹玉娟, 等. 基于ARMA-TS-GARCH有限混合模型的交通数据分析[J]. 中南大学学报(自然科学版), 2010, 41(05): 1860-1864
[10] LV Y, DUAN Y, KANG W, et al. Traffic flow prediction with big data: a deep learning approach[J]. IEEE Transactions on Intelligent Transportation Systems, 2014, 16(2): 865-873
[11] 张壮壮, 屈立成, 李翔, 等. 基于时空卷积神经网络的数据缺失交通流预测[J]. 计算机工程与应用, 2022, 58(7): 259-265
[12] GUO K, HU Y, QIAN Z, et al. Optimized graph convolution recurrent neural network for traffic prediction[J]. IEEE Transactions on Intelligent Transportation Systems, 2020, 22(2): 1138-1149
[13] VINAYAKUMAR R, SOMAN K P, POORNACHANDRAN P. Applying deep learning approaches for network traffic prediction[C]//2017 International Conference on Advances in Computing, Communications and Informatics (ICACCI), 2017: 2353-2358.
[14] CHAKRABORTY P, ADU-GYAMFI Y O, PODDAR S, et al. Traffic congestion detection from camera images using deep convolution neural networks[J]. Transportation Research Record, 2018, 2672(45): 222-231
[15] YU B, LEE Y, SOHN K. Forecasting road traffic speeds by considering area-wide spatio-temporal dependencies based on a graph convolutional neural network (GCN)[J]. Transportation research part C:emerging technologies, 2020, 114: 189-204
[16] ZHU J, WANG Q, TAO C, et al. AST-GCN: Attribute-augmented spatiotemporal graph convolutional network for traffic forecasting[J]. IEEE Access, 2021, 9: 35973-35983
[17] JIANG M, CHEN W, LI X. S-GCN-GRU-NN: A novel hybrid model by combining a Spatiotemporal Graph Convolutional Network and a Gated Recurrent Units Neural Network for short-term traffic speed forecasting[J]. Journal of Data, Information and Management, 2021, 3(1): 1-20
[18] LI Z, XIONG G, CHEN Y, et al. A hybrid deep learning approach with GCN and LSTM for traffic flow prediction[C]//2019 IEEE intelligent transportation systems conference (ITSC), 2019: 1929-1933.
[19] YAO H, WU F, KE J, et al. Deep multi-view spatial-temporal network for taxi demand prediction[C]//Proceedings of the AAAI conference on artificial intelligence. 2018: 3634-3640.
[20] LOGANATHAN G, SAMARABANDU J, WANG X. Sequence to sequence pattern learning algorithm for real-time anomaly detection in network traffic[C]. 2018 IEEE Canadian Conference on Electrical & Computer Engineering (CCECE), 2018: 335-342.
[21] VLAHOGIANNI E I, KARLAFTIS M G, GOLIAS J C. Short-term traffic forecasting: Where we are and where we’re going[J]. Transportation Research Part C:Emerging Technologies, 2014, 43: 3-19
[22] DISSANAYAKE B, HEMACHANDRA O, LAKSHITHA N, et al. A comparison of ARIMAX, VAR and LSTM on multivariate short-term traffic volume forecasting[C]//Conference of Open Innovations Association, 2021 (28): 564-570.
[23] MA X, HAO X, CHEN H. Fuzzy Neural Network-Based Assessment of Road Traffic Situations Using Extracted Information Obtained from Optical High-Resolution Satellite Remote Sensing Images[C]//2020 IEEE International Geoscience and Remote Sensing Symposium, 2020: 148-155.
[24] GENG X, LI Y, WANG L, et al. Spatiotemporal multi-graph convolution network for ride-hailing demand forecasting[C]//Proceedings of the AAAI conference on artificial intelligence. 2019, 33(01): 3656-3663.
[25] CUI Z, HENRICKSON K, KE R, et al. Traffic graph convolutional recurrent neural network: A deep learning framework for network-scale traffic learning and forecasting[J]. IEEE Transactions on Intelligent Transportation Systems, 2019, 21(11): 4883-4894