登录 | 注册

nempress期刊网

专业期刊出版平台

首页 / 期刊 / 《计算机科学与应用》 / 2025年第4期 / 基于深度学习的城市交通流量预测模型研究

基于深度学习的城市交通流量预测模型研究

Research on Urban Traffic Flow Prediction Model Based on Deep Learning

计算机科学
原创研究
同行评议

作者

张明辉1, 李伟1, 王晓东2

单位

1北京交通大学 计算机与信息技术学院

2中国科学院 计算技术研究所

期刊信息

《计算机科学与应用》2025年第4期 pp.45-58

DOI

10.1234/jcsa.2025.04.001

日期

收稿: 2024-12-15 | 修订: 2025-02-10 | 出版: 2025-04-15

86
引用次数
2,356
浏览
892
下载
下载 PDF

摘要

随着城市化进程的加速和智能交通系统的发展，准确预测城市交通流量对于缓解交通拥堵、优化交通管理具有重要意义。传统的交通流量预测方法难以有效捕捉交通数据的复杂时空依赖关系。本研究提出了一种基于深度学习的城市交通流量预测模型，该模型融合了长短期记忆网络（LSTM）和图卷积网络（GCN）的优势，能够同时建模交通数据的时间动态性和空间相关性。我们设计了一种新的时空注意力机制，用于自适应地捕捉不同时间段和不同路段之间的相互影响。此外，本研究还整合了多源数据，包括历史交通流量、道路网络拓扑、天气条件和社会活动等，以提高预测的准确性和鲁棒性。在北京市真实交通数据集上的实验结果表明，与现有方法相比，本模型在预测准确度上平均提高了18.7%，在处理突发事件和异常交通状况时表现尤为突出。本研究为智能交通系统的决策支持提供了有效工具，对于城市交通管理和规划具有重要的应用价值。

Abstract

With the acceleration of urbanization and the development of intelligent transportation systems, accurate prediction of urban traffic flow is of great significance for alleviating traffic congestion and optimizing traffic management. Traditional traffic flow prediction methods struggle to effectively capture the complex spatio-temporal dependencies in traffic data. This study proposes a deep learning-based urban traffic flow prediction model that integrates the advantages of Long Short-Term Memory networks (LSTM) and Graph Convolutional Networks (GCN), capable of simultaneously modeling the temporal dynamics and spatial correlations of traffic data. We design a novel spatio-temporal attention mechanism to adaptively capture the mutual influence between different time periods and different road segments. In addition, this study also integrates multi-source data, including historical traffic flow, road network topology, weather conditions, and social activities, to improve the accuracy and robustness of prediction. Experimental results on a real traffic dataset in Beijing show that compared with existing methods, our model improves prediction accuracy by an average of 18.7%, with particularly outstanding performance in handling emergencies and abnormal traffic conditions. This research provides an effective tool for decision support in intelligent transportation systems and has important application value for urban traffic management and planning.

参考文献

[1] 王建, 李明, 张华. 中国城市交通拥堵经济损失评估研究[J]. 交通运输系统工程与信息, 2023, 23(5): 156-165.
[2] Box G E P, Jenkins G M, Reinsel G C, et al. Time series analysis: forecasting and control[M]. John Wiley & Sons, 2015.
[3] Okutani I, Stephanedes Y J. Dynamic prediction of traffic volume through Kalman filtering theory[J]. Transportation Research Part B: Methodological, 1984, 18(1): 1-11.
[4] Wu C H, Ho J M, Lee D T. Travel-time prediction with support vector regression[J]. IEEE Transactions on Intelligent Transportation Systems, 2004, 5(4): 276-281.
[5] Leshem G, Ritov Y. Traffic flow prediction using adaboost algorithm with random forests as a weak learner[J]. World Academy of Science, Engineering and Technology, 2007, 19: 193-198.
[6] Hochreiter S, Schmidhuber J. Long short-term memory[J]. Neural computation, 1997, 9(8): 1735-1780.
[7] Kipf T N, Welling M. Semi-supervised classification with graph convolutional networks[C]//International Conference on Learning Representations (ICLR), 2017.
[8] Li Y, Yu R, Shahabi C, et al. Diffusion convolutional recurrent neural network: Data-driven traffic forecasting[C]//International Conference on Learning Representations (ICLR), 2018.
[9] 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. 2018: 3634-3640.
[10] Guo S, Lin Y, Feng N, et al. Attention based spatial-temporal graph convolutional networks for traffic flow forecasting[C]//Proceedings of the AAAI Conference on Artificial Intelligence. 2019, 33(01): 922-929.
[11] Zheng C, Fan X, Wang C, et al. GMAN: A graph multi-attention network for traffic prediction[C]//Proceedings of the AAAI Conference on Artificial Intelligence. 2020, 34(01): 1234-1241.
[12] Wu Z, Pan S, Chen F, et al. A comprehensive survey on graph neural networks[J]. IEEE Transactions on Neural Networks and Learning Systems, 2020, 32(1): 4-24.
[13] Vaswani A, Shazeer N, Parmar N, et al. Attention is all you need[C]//Advances in neural information processing systems. 2017: 5998-6008.
[14] Zhang J, Zheng Y, Qi D. Deep spatio-temporal residual networks for citywide crowd flows prediction[C]//Proceedings of the AAAI Conference on Artificial Intelligence. 2017, 31(1).
[15] Yao H, Tang X, Wei H, et al. Revisiting spatial-temporal similarity: A deep learning framework for traffic prediction[C]//Proceedings of the AAAI Conference on Artificial Intelligence. 2019, 33(01): 5668-5675.
[16] 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.
[17] Chen C, Li K, Teo S G, et al. Gated residual recurrent graph neural networks for traffic prediction[C]//Proceedings of the AAAI Conference on Artificial Intelligence. 2019, 33(01): 485-492.
[18] Fang S, Zhang Q, Meng G, et al. GSTNET: Global spatial-temporal network for traffic flow prediction[C]//Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence. 2019: 10-16.
[19] Wang X, Chen C, Min Y, et al. Efficient metropolitan traffic prediction based on graph recurrent neural network[J]. arXiv preprint arXiv:1811.00740, 2018.
[20] Lv Z, Qin L, Xing C, et al. SDGCN: Sequential dynamic graph convolutional network for traffic flow prediction[J]. IEEE Transactions on Intelligent Transportation Systems, 2022, 23(8): 12281-12291.
[21] Xu M, Dai W, Liu C, et al. Spatial-temporal transformer networks for traffic flow forecasting[J]. arXiv preprint arXiv:2001.02908, 2020.
[22] Bai L, Yao L, Li C, et al. Adaptive graph convolutional recurrent network for traffic forecasting[C]//Advances in Neural Information Processing Systems. 2020, 33: 17804-17815.
[23] Jiang W, Luo J. Graph neural network for traffic forecasting: A survey[J]. Expert Systems with Applications, 2022, 207: 117921.
[24] Kingma D P, Ba J. Adam: A method for stochastic optimization[C]//International Conference on Learning Representations (ICLR), 2015.
[25] Srivastava N, Hinton G, Krizhevsky A, et al. Dropout: a simple way to prevent neural networks from overfitting[J]. The Journal of Machine Learning Research, 2014, 15(1): 1929-1958.
[26] Zheng Y, Capra L, Wolfson O, et al. Urban computing: concepts, methodologies, and applications[J]. ACM Transactions on Intelligent Systems and Technology (TIST), 2014, 5(3): 1-55.
[27] Zheng Y. Methodologies for cross-domain data fusion: An overview[J]. IEEE Transactions on Big Data, 2015, 1(1): 16-34.
[28] Liang Y, Ke S, Zhang J, et al. GeoMAN: Multi-level attention networks for geo-sensory time series prediction[C]//Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence. 2018: 3428-3434.
[29] Pan Z, Liang Y, Wang W, et al. Urban traffic prediction from spatio-temporal data using deep meta learning[C]//Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining. 2019: 1720-1730.
[30] Wang D, Zhang J, Cao W, et al. When will you arrive? Estimating travel time based on deep neural networks[C]//Proceedings of the AAAI Conference on Artificial Intelligence. 2018, 32(1).