Hierarchical Traffic Flow Prediction Based on Spatial-Temporal Graph Convolutional Network
Hierarchical Traffic Flow Prediction Based on Spatial-Temporal Graph Convolutional Network
复制标题
基于时空图卷积网络的分层交通流预测
DOI：
10.1109/tits.2022.3148105
复制
发表时间：
2022
影响因子：
8.5
通讯作者：
Liuqing Yang
中科院分区：
文献类型：
--
作者：
Hanqiu Wang;Rongqing Zhang;Xiang Cheng;Liuqing Yang
近年来，交通流预测因其能为交通管理或驾驶规划提供有效的指导，提高交通安全和效率而受到学术界和工业界的广泛关注。但由于实际道路时空相关性的复杂性和交叉口监控设备的局限性，时空交通流预测仍存在许多挑战。在本文中，我们提出了一种新的分层交通流预测协议的基础上的时空图卷积网络（ST-GCN），它结合了空间和时间依赖的交叉口交通，以实现更准确的交通流预测。与现有的工作不同，我们提出的协议与相邻相似算法也可以有效地预测交通流量的交叉口没有历史数据。基于青岛市实际交通数据的实验表明，我们提出的基于ST-GCN的交通流预测协议优于最先进的基线模型。对于没有历史数据的交叉口，也能获得较好的预测精度。
In recent years, traffic flow prediction has attracted more and more interest from both academia and industry since such information can provide effective guidance for traffic management or driving planning and enhance traffic safety and efficiency. But due to the complicated spatial-temporal dependence in actual roads and the limitation of intersection monitoring equipment, there are still many challenges in spatial-temporal traffic flow prediction. In this paper, we propose a novel hierarchical traffic flow prediction protocol based on spatial-temporal graph convolutional network (ST-GCN), which incorporates both spatial and temporal dependence of intersection traffic to achieve a more accurate traffic flow prediction. Different from existing works, our proposed protocol with the Adjacent-Similar algorithm can also effectively predict the traffic flow of the intersections without historical data. Experiments based on practical traffic data of the city of Qingdao, China demonstrate that our proposed ST-GCN-based traffic flow prediction protocol outperforms the state-of-the-art baseline models. Moreover, as for the intersections without historical data, we can also obtain a good prediction accuracy.