江苏龙网

  1. 首页 > 资讯 > 科技 > >

|混合时空图卷积网络：利用导航数据改进交通预测效果 | KDD 2020( 六 )


|混合时空图卷积网络：利用导航数据改进交通预测效果 | KDD 2020
本文插图

图 11 ETA预测结果的展示
|混合时空图卷积网络：利用导航数据改进交通预测效果 | KDD 2020
本文插图

结论
本文中 ， 我们提出了一种新的用于通行时间预测的深度学习框架：混合时空图卷积网络（H-STGCN） ， 该框架利用从导航数据中推演出的计划中交通流量提升模型效果 。 我们设计了域转换器 ， 以此整合异质模态的交通流量特征 。 我们设计了复合邻接矩阵使得图卷积层能够更好地捕捉路段间的接近性 。 在真实场景数据集上进行的实验证实H-STGCN和对标的模型相比取得了显著更优的效果 ， 在突发拥堵的预测上优势尤为明显 。 这一框架提供了一种将物理知识嵌入数据驱动模型的新范式 ， 可以较容易地推广应用于一般的时空预测任务当中 。
主要参考文献
[1] Yaguang Li, Rose Yu, Cyrus Shahabi, and Yan Liu. 2018. Diffusion convolutional recurrent neural network: Data-driven traffic forecasting.
[2] YishengLv, YanjieDuan, WenwenKang, Zhengxi Li, Fei-Yue Wang, etal. 2015. Traffic flow prediction with big data: A deep learning approach. IEEE Trans. Intelligent Transportation Systems 16, 2 (2015), 865–873.
[3] Bing Yu, Haoteng Yin, and Zhanxing Zhu. 2018. Spatio-Temporal Graph Convolutional Neural Network: A Deep Learning Framework for Traffic Forecasting. In Proceedings of the 27th International Joint Conference on Artificial Intelligence (IJCAI).
[4] JingruiHe, WeiShen, Phani Divakaruni, Laura Wynter, and Rick Lawrence. 2013. Improving Traffic Prediction with Tweet Semantics. In Proceedings of the 23rd International Joint Conference on Artificial Intelligence (IJCAI). 1387–1393.
[5] Binbing Liao, Jingqing Zhang, Chao Wu, Douglas McIlwraith, Tong Chen, Shengwen Yang, Yike Guo, and Fei Wu. 2018. Deep Sequence Learning with Auxiliary Information for Traffic Prediction. In Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining. ACM.
[6] Yaguang Li, Rose Yu, Cyrus Shahabi, and Yan Liu. 2018. Diffusion convolutional recurrent neural network: Data-driven traffic forecasting.
[7] Bing Yu, Haoteng Yin, and Zhanxing Zhu. 2018. Spatio-Temporal Graph Convolutional Neural Network: A Deep Learning Framework for Traffic Forecasting. In Proceedings of the 27th International Joint Conference on Artificial Intelligence (IJCAI).
[8] Moshe Ben-Akiva, Michel Bierlaire, Haris Koutsopoulos, and Rabi Mishalani. 1998. DynaMIT: A simulation-based system for traffic prediction. In DACCORD Short Term Forecasting Workshop. Delft, The Netherlands, 1–12.
[9] Wei, H., Zheng, G., Yao, H. and Li, Z., 2018. Intellilight: A reinforcement learning approach for intelligent traffic light control. In Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining.
[10] https://en.wikipedia.org/wiki/Congestion_pricing
|混合时空图卷积网络：利用导航数据改进交通预测效果 | KDD 2020
本文插图


推荐阅读


上一篇：|科学家发现维持脾脏红髓巨噬细胞的微环境

下一篇：微导流|ios企业签名可以直接签名吗？