Abstract
Traffic speed prediction plays a significant role in the intelligent traffic system (ITS). However, due to the complex spatial-temporal correlations of traffic data, it is very challenging to predict traffic speed timely and accurately. The traffic speed renders not only short-term neighboring and multiple long-term periodic dependencies in the temporal dimension but also local and global dependencies in the spatial dimension. To address this problem, we propose a novel deep-learning-based model, Global Spatial-Temporal Graph Convolutional Network (GSTGCN), for urban traffic speed prediction. The model consists of three spatial-temporal components with the same structure and an external component. The three spatial-temporal components are used to model the recent, daily-periodic, and weekly-periodic spatial-temporal correlations of the traffic data, respectively. More specifically, each spatial-temporal component consists of a dynamic temporal module and a global correlated spatial module. The former contains multiple residual blocks which are stacked by dilated casual convolutions, while the latter contains a localized graph convolution and a global correlated mechanism. The external component is used to extract the effect of external factors, such as holidays and weather conditions, on the traffic speed. Experimental results on two real-world traffic datasets have demonstrated that the proposed GSTGCN outperforms the state-of-the-art baselines.
Highlights
Traffic speed prediction is an important part of the Intelligent Transportation System (ITS).Accurate and timely traffic prediction can assist in real-time dynamic traffic light control [1] and urban road planning, which will help alleviate the huge congestion problem as well as improve the safety and convenience of public transportation
To capture the dynamic complex spatial-temporal correlations more effectively, we propose a novel global spatial-temporal graph convolutional network called Global Spatial-Temporal Graph Convolutional Network (GSTGCN) to predict urban traffic speed, which consists of three independent spatial-temporal components with the same structure and one external component
Compared to DCRNN, STGCN, ST-MetaNet, and Graph WaveNet, GSTGCN has a great advantage in long-term prediction with a slower error growth rate and achieves the best prediction accuracy on all metrics and both two datasets
Summary
Traffic speed prediction is an important part of the Intelligent Transportation System (ITS). Accurate and timely traffic prediction can assist in real-time dynamic traffic light control [1] and urban road planning, which will help alleviate the huge congestion problem as well as improve the safety and convenience of public transportation. Traffic control in advance can prevent traffic paralysis, pedaling, and other events. Traffic speed prediction aims to predict future traffic speed based on a series of historical traffic speed observations. The three key complex factors affecting traffic speed are as follows: Factor 1: Global Spatial Dependencies. Given the road network and sensors, the spatial correlations over different nodes on the traffic network are both local and global
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
