A General Traffic Flow Prediction Approach Based on Spatial-Temporal Graph Attention

Cong Tang, Jingru Sun, Yichuang Sun, Mu Peng, Nianfei Gan

Research output: Contribution to journalArticlepeer-review

1 Citation (Scopus)
94 Downloads (Pure)

Abstract

Accurate and reliable traffic flow prediction is critical to the safe and stable deployment of intelligent transportation systems. However, it is very challenging due to the complex spatial and temporal dependence of traffic flows. Most existing works require the information of the traffic network structure and human intervention to model the spatial-temporal association of traffic data, resulting in low generality of the model and unsatisfactory prediction performance. In this paper, we propose a general spatial-temporal graph attention based dynamic graph convolutional network (GAGCN) model to predict traffic flow. GAGCN uses the graph attention networks to extract the spatial associations among nodes hidden in the traffic feature data automatically which can be dynamically adjusted over time. And then the graph convolution network is adjusted based on the spatial associations to extract the spatial features of the road network. Notably, the information of road network structure and human intervention are not required in GAGCN. The forecasting accuracy and the generality are evaluated with two real-world traffic datasets. Experimental results indicate that our GAGCN surpasses the state-of-the-art baselines on one of the two datasets.

Original languageEnglish
Article number9173702
Pages (from-to)153731-153741
Number of pages11
JournalIEEE Access
Volume8
Early online date21 Aug 2020
DOIs
Publication statusPublished - 2020

Keywords

  • Traffic flow forecasting
  • dynamic spatial-Temporal
  • graph attention networks
  • graph convolutional network

Fingerprint

Dive into the research topics of 'A General Traffic Flow Prediction Approach Based on Spatial-Temporal Graph Attention'. Together they form a unique fingerprint.

Cite this