基于下采样交互时空注意力网络的交通流量预测
Traffic Flow Prediction Based on Downsampled Interactive Spatio-Temporal Attention Network
DOI: 10.12677/mos.2024.134371, PDF,    科研立项经费支持
作者: 季熙来*, 黄雨彤, 张爱华：南京邮电大学理学院，江苏 南京；冷 爽：南京邮电大学计算机学院，江苏 南京
关键词: 交通流量预测；下采样交互；注意力机制；节点嵌入；Traffic Flow Prediction； Down-Sampling Interaction； Attention Mechanism； Node Embedding
摘要: 准确预测交通流量对于缓解城市交通和线路规划具有至关重要意义。为了解决现有交通流量预测模型在处理时间序列相关性及长期依赖捕获方面的不足，提出了一种基于下采样交互时空注意力网络(Downsampled Interactive Spatio-Temporal Attention Network, DISTAN)的交通流量预测模型。该模型首先结合静态道路空间拓扑结构和时间信息，通过节点嵌入和独热编码构建时空嵌入。然后，在编码层采用下采样交互式学习结构以及注意力机制，以综合局部和全局信息。在解码层，增加过去和当前预测偏差的正则化损失函数，以防止过拟合。最后，通过在四个真实世界数据集上的性能测试，证明了提出的DISTAN的有效性和优越性。
Abstract: To address the limitations of existing traffic flow prediction models in handling time series correlations and long-term dependencies, we propose a downsampled interactive spatiotemporal attention network (DISTAN) to predict traffic flow. It begins with node embedding and one-hot encoding based on static spatial topology and temporal information to construct spatiotemporal embeddings. The encoded sequences are then processed with a downsampled interactive learning structure and attention mechanism to capture local and global information. To prevent overfitting, the decoding layer includes a regularization of the loss function using the deviation between past and current predictions. Test on four real-world datasets, the effectiveness and superiority of the proposed DISTAN is confirmed.
文章引用：季熙来, 黄雨彤, 冷爽, 张爱华. 基于下采样交互时空注意力网络的交通流量预测[J]. 建模与仿真, 2024, 13(4): 4090-4103. https://doi.org/10.12677/mos.2024.134371

参考文献

[1] Rahman, R., Zhang, J. and Hasan, S. (2023) A Review of Deep Learning-Based Approaches and Use Cases for Traffic Prediction. In: Dia, H., Ed., Handbook on Artificial Intelligence and Transport, Edward Elgar, 80-101. [Google Scholar] [CrossRef] 
[2] Peng, L., Liao, X., Li, T., Guo, X. and Wang, X. (2024) An Overview Based on the Overall Architecture of Traffic Forecasting. Data Science and Engineering. [Google Scholar] [CrossRef] 
[3] Alzahrani, M., Wang, Q., Liao, W., Chen, X. and Yu, W. (2024) Survey on Multi-Task Learning in Smart Transportation. IEEE Access, 12, 17023-17044. [Google Scholar] [CrossRef] 
[4] Aljuaydi, F., Wiwatanapataphee, B. and Wu, Y.H. (2023) Multivariate Machine Learning-Based Prediction Models of Freeway Traffic Flow under Non-Recurrent Events. Alexandria Engineering Journal, 65, 151-162. [Google Scholar] [CrossRef] 
[5] Milenković, M., Gligorić, M., Bojović, N. and Gligorić, Z. (2023) A Comparison between ARIMA, LSTM, ARIMA-LSTM and SSA for Cross-Border Rail Freight Traffic Forecasting: The Case of Alpine-Western Balkan Rail Freight Corridor. Transportation Planning and Technology, 47, 89-112. [Google Scholar] [CrossRef] 
[6] Dissanayake, B., Hemachandra, O., Lakshitha, N., et al. (2021) A Comparison of ARIMAX, VAR and LSTM on Multivariate Short-Term Traffic Volume Forecasting. Proceedings of the 28th Conference of the Open Innovations Association FRUCT, Moscow, 27-29 January 2021, 564-570.
[7] Zhong, W. and Du, L. (2023) Predicting Traffic Casualties Using Support Vector Machines with Heuristic Algorithms: A Study Based on Collision Data of Urban Roads. Sustainability, 15, Article 2944. [Google Scholar] [CrossRef] 
[8] Khan, A., Fouda, M.M., Do, D., Almaleh, A. and Rahman, A.U. (2023) Short-Term Traffic Prediction Using Deep Learning Long Short-Term Memory: Taxonomy, Applications, Challenges, and Future Trends. IEEE Access, 11, 94371-94391. [Google Scholar] [CrossRef] 
[9] Umar, I.K., Adamu, M., Mostafa, N., Riaz, M.S., Haruna, S.I., Hamza, M.F., et al. (2024) The State-of-the-Art in the Application of Artificial Intelligence-Based Models for Traffic Noise Prediction: A Bibliographic Overview. Cogent Engineering, 11, Article 2297508. [Google Scholar] [CrossRef] 
[10] Yu, W., Ruan, K., Tang, H. and Huang, J. (2022) Routing Hypergraph Convolutional Recurrent Network for Network Traffic Prediction. Applied Intelligence, 53, 16126-16137. [Google Scholar] [CrossRef] 
[11] Krupski, J., Graniszewski, W. and Iwanowski, M. (2021) Data Transformation Schemes for CNN-Based Network Traffic Analysis: A Survey. Electronics, 10, Article 2042. [Google Scholar] [CrossRef] 
[12] Jin, J., Rong, D., Zhang, T., Ji, Q., Guo, H., Lv, Y., et al. (2022) A GAN-Based Short-Term Link Traffic Prediction Approach for Urban Road Networks under a Parallel Learning Framework. IEEE Transactions on Intelligent Transportation Systems, 23, 16185-16196. [Google Scholar] [CrossRef] 
[13] Liu, A. and Zhang, Y. (2022) Spatial-Temporal Interactive Dynamic Graph Convolution Network for Traffic Forecasting. arXiv Preprint arXiv:2205.08689
[14] Song, C., Lin, Y., Guo, S. and Wan, H. (2020) Spatial-Temporal Synchronous Graph Convolutional Networks: A New Framework for Spatial-Temporal Network Data Forecasting. Proceedings of the Thirty-Fourth AAAI Conference on Artificial Intelligence, New York, 7-12 February 2020, 914-921. [Google Scholar] [CrossRef] 
[15] Shao, Z., Zhang, Z., Wei, W., Wang, F., Xu, Y., Cao, X., et al. (2022) Decoupled Dynamic Spatial-Temporal Graph Neural Network for Traffic Forecasting. Proceedings of the VLDB Endowment, 15, 2733-2746. [Google Scholar] [CrossRef] 
[16] Lan, S., Ma, Y., Huang, W., et al. (2022) DSTAGNN: Dynamic Spatial-Temporal Aware Graph Neural Network for Traffic Flow Fore-Casting. Proceedings of the 39th International Conference on Machine Learning, Baltimore, 17-23 July 2022, 11906-11917.
[17] Wu, Z., Pan, S., Long, G., Jiang, J., Chang, X. and Zhang, C. (2020). Connecting the Dots: Multivariate Time Series Forecasting with Graph Neural Networks. Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, Online, 6-10 July 2020, 753-763.[CrossRef] 
[18] Huang, X., Wang, J., Lan, Y., Jiang, C. and Yuan, X. (2023) MD-GCN: A Multi-Scale Temporal Dual Graph Convolution Network for Traffic Flow Prediction. Sensors, 23, Article 841. [Google Scholar] [CrossRef] [PubMed]
[19] Cao, S., Wu, L., Zhang, R., Wu, D., Cui, J. and Chang, Y. (2024) A Spatiotemporal Multiscale Graph Convolutional Network for Traffic Flow Prediction. IEEE Transactions on Intelligent Transportation Systems. [Google Scholar] [CrossRef] 
[20] Chen, C., Liu, Y., Chen, L. and Zhang, C. (2023) Bidirectional Spatial-Temporal Adaptive Transformer for Urban Traffic Flow Forecasting. IEEE Transactions on Neural Networks and Learning Systems, 34, 6913-6925. [Google Scholar] [CrossRef] [PubMed]
[21] Grover, A. and Leskovec, J. (2016) node2vec: Scalable Feature Learning for Networks. Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, San Francisco, 13-17 August 2016, 855-864. [Google Scholar] [CrossRef] [PubMed]
[22] Tang, J., Qu, M., Wang, M., Zhang, M., Yan, J. and Mei, Q. (2015) LINE: Large-Scale Information Network Embedding. Proceedings of the 24th International Conference on World Wide Web, Florence, 18-22 May 2015, 1067-1077. [Google Scholar] [CrossRef] 
[23] Panayiotou, T., Michalopoulou, M. and Ellinas, G. (2023) Survey on Machine Learning for Traffic-Driven Service Provisioning in Optical Networks. IEEE Communications Surveys & Tutorials, 25, 1412-1443. [Google Scholar] [CrossRef] 
[24] Reza Rezvan, M., Ghanbari Sorkhi, A., Pirgazi, J. and Mehdi Pourhashem Kallehbasti, M. (2024) AdvanceSplice: Integrating N-Gram One-Hot Encoding and Ensemble Modeling for Enhanced Accuracy. Biomedical Signal Processing and Control, 92, Article 106017. [Google Scholar] [CrossRef] 
[25] Li, F., Feng, J., Yan, H., Jin, G., Yang, F., Sun, F., et al. (2023) Dynamic Graph Convolutional Recurrent Network for Traffic Prediction: Benchmark and Solution. ACM Transactions on Knowledge Discovery from Data, 17, 1-21. [Google Scholar] [CrossRef] 
[26] Shuman, D.I., Narang, S.K., Frossard, P., Ortega, A. and Vandergheynst, P. (2013) The Emerging Field of Signal Processing on Graphs: Extending High-Dimensional Data Analysis to Networks and Other Irregular Domains. IEEE Signal Processing Magazine, 30, 83-98. [Google Scholar] [CrossRef] 
[27] Vaswani, A., Shazeer, N., Parmar, N., et al. (2017) Attention Is All You Need. Proceedings of the 31st Conference on Neural Information Processing Systems (NIPS 2017), Long Beach, 4-9 December 2017, 1-15.
[28] Wang, C., Tian, R., Hu, J. and Ma, Z. (2023) A Trend Graph Attention Network for Traffic Prediction. Information Sciences, 623, 275-292. [Google Scholar] [CrossRef] 

为你推荐