School of Electronic Engineering, Beijing University of Posts and Telecommunications, Beijing 100876, China.
Beijing Key Laboratory of Mobile Computing and Pervasive Device, Institute of Computing Technology, Chinese Academy of Sciences, Beijing 100190, China.
Comput Intell Neurosci. 2021 Dec 23;2021:9134942. doi: 10.1155/2021/9134942. eCollection 2021.
Predicting traffic data on traffic networks is essential to transportation management. It is a challenging task due to the complicated spatial-temporal dependency. The latest studies mainly focus on capturing temporal and spatial dependencies with spatially dense traffic data. However, when traffic data become spatially sparse, existing methods cannot capture sufficient spatial correlation information and thus fail to learn the temporal periodicity sufficiently. To address these issues, we propose a novel deep learning framework, Multi-component Spatial-Temporal Graph Attention Convolutional Networks (MSTGACN), for traffic prediction, and we successfully apply it to predicting traffic flow and speed with spatially sparse data. MSTGACN mainly consists of three independent components to model three types of periodic information. Each component in MSTGACN combines dilated causal convolution, graph convolution layer, and the weight-shared graph attention layer. Experimental results on three real-world traffic datasets, METR-LA, PeMS-BAY, and PeMSD7-sparse, demonstrate the superior performance of our method in the case of spatially sparse data.
预测交通网络上的交通数据对于交通管理至关重要。由于复杂的时空依赖性，这是一项具有挑战性的任务。最新的研究主要集中在利用空间密集的交通数据来捕捉时间和空间依赖性。然而，当交通数据变得空间稀疏时，现有方法无法捕捉到足够的空间相关信息，因此无法充分学习时间周期性。为了解决这些问题，我们提出了一种新的深度学习框架，多分量时空图注意卷积网络（MSTGACN），用于交通预测，并成功地将其应用于具有空间稀疏数据的交通流和速度预测。MSTGACN 主要由三个独立的组件组成，用于建模三种类型的周期性信息。MSTGACN 中的每个组件都结合了扩张因果卷积、图卷积层和共享权重图注意力层。在三个真实交通数据集 METR-LA、PEMS-BAY 和 PEMS-D7-sparse 上的实验结果表明，我们的方法在空间稀疏数据情况下具有优越的性能。
