Attention-based dynamic spatial-temporal graph convolutional networks for traffic speed forecasting. (15th October 2022)

• Record Type: Journal Article
• Authors: Zhao, Jianli; Liu, Zhongbo; Sun, Qiuxia; Li, Qing; Jia, Xiuyan; Zhang, Rumeng
• Is Part Of: Expert systems with applications. Volume 204(2022)
• Publication Date: 2022-10-15
• Subjects: Traffic speed forecast -- GCN -- Dynamic spatial–temporal correlations -- Attention mechanism; Expert systems (Computer science) -- Periodicals; Systèmes experts (Informatique) -- Périodiques; Electronic journals; 006.33
• DOI: 10.1016/j.eswa.2022.117511
• Languages: English
• ISSNs: 0957-4174

Abstract

Highlights: A novel GCN-based traffic prediction model is proposed. The model enables dynamic spatial–temporal modeling of traffic data. This model has superior long-term forecasting capability. Hidden spatial relationships in traffic data were captured. Abstract: In recent years, spatial–temporal graph modeling based on graph convolutional neural networks (GCN) has become an effective method for mining spatial–temporal dependencies in traffic forecasting research. However, existing studies lack the capability of dynamic spatial–temporal modeling of traffic speeds. Furthermore, long-term forecasting is difficult because of the diversity of traffic conditions. In addition, traditional studies capture only the features of fixed graph structures, which do not reflect real spatial dependence. To address these challenges, this study proposes a novel attention-based dynamic spatial–temporal graph convolutional network (ADSTGCN) model. ADSTGCN mainly consists of multiple dynamic spatial–temporal blocks, each of which contains three modules: 1) a dynamic adjustment module to model the dynamic spatial–temporal correlations of traffic speed, 2) a gated dilated convolution module to mine long-term dependencies, and 3) a spatial convolution module to capture hidden spatial dependencies. Experiments on three public traffic datasets demonstrated the good performance of the model.