|
|
基于注意力机制的CNN-BiGRU的短时交通流预测
|
Abstract:
短时交通流预测是实现道路交通管理和指导的基础，对道路通行能力、交通安全等具有重要的实际意义。提出一种基于注意力机制的卷积神经网络和双向门控循环单元神经网络相结合的深度学习交通流预测模型。采用卷积神经网络（CNN）提取交通流的空间特征。利用双向门控循环单元（BiGRU）从前向和后向传播中都获取信息，充分提取交通流的时间相关特征。引入注意力机制，将交通流最重要的特征得到了最大限度的保留，以此来提升CNN和BiGRU网络的特征提取效果，达到提升模型的预测精度的目的。在真实数据集上的对比实验和消融实验结果都表明：基于注意力机制的CNN-BIGRU的短时交通流预测模型能够有效捕获交通流的动态时空特征，具有良好的预测性能。
Short-term traffic flow prediction is the basis of road traffic management and guidance, and has important practical significance for road capacity and traffic safety, and so on. A short-term traffic flow prediction based on CNN-BiGRU-Attention (CNN and BiGRU network based on attention mechanism) model is proposed. The Convolutional Neural Networks (CNN) have been employed to extract the spatial features of the traffic flow. The Bidirectional Gated Recurrent Unit (BiGRU) is exploited to obtain information from both forward and backward propagation, and then fully capture tem-poral dependencies of the traffic flow. The attention mechanism is employed to maximize the retention of the most important features of the traffic flow, so as to improve the feature extraction effect of CNN and BiGRU networks, and achieve the purpose of improving the prediction accuracy of the model. The results of comparison experiments and ablation experiments on the real data set show that the short-term traffic flow prediction model of CNN-BIGRU based on the attention mechanism can effectively capture the dynamic spatio-temporal characteristics of traffic flow, and has good prediction performance.
| [1] | Liu, Z.M. and Yu, L. (2020) Stay or Leave? The Role of Air Pollution in Urban Migration Choices. Ecological Economics, 177, Article ID: 106780. https://doi.org/10.1016/j.ecolecon.2020.106780 |
| [2] | Rudolph, F. and Matrai, T. (2018) Congestion from a Multimodal Perspective. Periodica Polytechnica Transportation Engineering, 46, 215-221. https://doi.org/10.3311/PPtr.12048 |
| [3] | Fusco, G., Colombroni, C. and Isaenko, N. (2016) Short-Term Speed Predictions Exploiting Big Data on Large Urban Road Networks. Transportation Research Part C Emerging Technologies, 73, 183-201.
https://doi.org/10.1016/j.trc.2016.10.019 |
| [4] | Oh, S., Byon, Y.J., Jang, K. and Yeo, H. (2018) Short-Term Travel Time Prediction on Highway: A Review on Model Based Approach. KSCE Journal of Civil Engineering, 22, 298-310. https://doi.org/10.1007/s12205-017-0535-8 |
| [5] | Zhang, K., Xie, C., Wang, Y., Miguel ángel, S., Nguyen, T.M.T., Zhao, Q., et al. (2021) Hybrid Short-Term Traffic Forecasting Architecture and Mechanisms for Reservation-Based Cooperative ITS. Journal of Systems Architecture, 117, Article ID: 102101. https://doi.org/10.1016/j.sysarc.2021.102101 |
| [6] | Zhang, Y., Zhang, Y.L. and Haghani, A. (2014) A Hybrid Short-Term Traffic Flow Forecasting Method Based on Spectral Analysis and Statistical Volatility Model. Transporta-tion Research Part C Emerging Technologies, 43, 65-78.
https://doi.org/10.1016/j.trc.2013.11.011 |
| [7] | 李文勇, 李俊卓, 王涛. 基于Box-Cox指数变换改进的ARIMA模型交通流预测方法[J]. 武汉理工大学学报(交通科学与工程版), 2020, 44(6): 974-977. |
| [8] | 周晓, 唐宇舟, 刘强. 基于卡尔曼滤波的道路平均速度预测模型研究[J]. 浙江工业大学学报, 2020, 48(4): 392-396+404. |
| [9] | Zhu, Z., Peng, B., Xiong, C.F. and Zhang, L. (2016) Short-Term Traffic Flow Prediction with Linear Conditional Gaussian Bayesian Network. Journal of Advanced Transportation, 50, 1111-1123. https://doi.org/10.1002/atr.1392 |
| [10] | Ryu, U., Wang, J., Kim, T., Kwak, S. and Juhyok, U. (2018) Construction of Traffic State Vector Using Mutual Information for Short-Term Traffic Flow Prediction. Transportation Research Part C: Emerging Technologies, 96, 55-71.
https://doi.org/10.1016/j.trc.2018.09.015 |
| [11] | Tang, J., Chen, X., Hu, Z., Zong, F., Han, C. and Li, L. (2019) Traffic Flow Prediction Based on Combination of Support Vector Machine and Data Denoising Schemes. Physical A: Statistica Mechanics and Its Applications, 534, Article ID: 120642. https://doi.org/10.1016/j.physa.2019.03.007 |
| [12] | Xie, P., Li, T.R., Liu, J., Du, S., Yang, X. and Zhang, J. (2020) Urban Flow Prediction from Spatiotemporal Data Using Machine Learning: A Survey. Information Fusion, 59, 1-12. https://doi.org/10.1016/j.inffus.2020.01.002 |
| [13] | 杜圣东, 李天瑞, 杨燕, 等. 一种基于序列到序列时空注意力学习的交通流预测模型[J]. 计算机研究与发展, 2020, 57(8): 1715-1728. |
| [14] | 卢生巧, 黄中祥, 等. 基于深度学习的短时交通流预测模型[J]. 交通科学与工程2020, 36(3): 74-80. |
| [15] | 陆文琦, 芮一康, 冉斌, 等. 智能网联环境下基于混合深度学习的交通流预测模型[J]. 交通运输系统工程与信息, 2020, 20(3): 47-53. |
| [16] | 王博文, 王景升, 等. 基于长短时记忆网络的Encoder-Decoder多步交通流预测模型[J]. 重庆大学学报, 2021, 44(11): 71-80. |
| [17] | 潘卫鹏, 郭唐仪, 等. 基于图注意力卷积网络的短时交通流预测[C]//世界交通运输工程技术论坛（WTC2021）论文集(上). 北京: 人民交通出版社, 2021: 2495-2500. |
| [18] | Ye, J.X., Zhao, J., Ye, K.J. and Xu, C.Z. (2020) How to Build a Graph-Based Deep Learning Archi-tecture in Traffic Domain: A Survey. IEEE Transactions on Intelligent Transportation Systems, 99, 1-21.
https://doi.org/10.1109/TITS.2020.3043250 |
| [19] | Seng, D., Lv, F., Ling, Z., Shi, X. and Fang, Q. (2021) Forecasting Traffic Flows in Irregular Regions with Multi-Graph Convolutional Network and Gated Recurrent Unit. Frontiers of Information Technology & Electronic Engineering, 22, 1179-1193. https://doi.org/10.1631/FITEE.2000243 |
| [20] | Peng, H., Du, B., Liu, M., Liu, M., Ji, S., Wang, S., et al. (2021) Dynamic Graph Convolutional Network for Long-Term Traffic Flow Prediction with Reinforcement Learning. Information Sciences, 578, 401-416.
https://doi.org/10.1016/j.ins.2021.07.007 |
| [21] | Jiang, Z.B., Fan, W., Liu, W., Zhu, B. and Gu, J. (2018) Reinforcement Learning Approach for Coordinated Passenger Inflow Control of Urban Rail Transit in Peak Hours. Transportation Research Part C Emerging: Technologies, 88, 1-16.
https://doi.org/10.1016/j.trc.2018.01.008 |
| [22] | 邱锡鹏. 神经网络与深度学习[M]. 北京: 机械工业出版社, 2021: 193-196. |
| [23] | Cho, K., Merrienboer, B.V., Gulcehre, C., Bahdanau, D., Bougares, F., Schwenk, H., et al. (2014) Learning Phrase Representations Using RNN Encoder-Decoder for Statistical Machine Translation. arXiv:1406.1078.
https://arxiv.org/abs/1406.1078 |
