EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Dynamic Spatio-Temporal Graph Fusion Convolutional Network for Urban Traffic Prediction

Haodong Ma, Xizhong Qin, Yuan Jia, Junwei Zhou

Applied Sciences · 16.08.2023 · 13 (16) · 9304

DOI: 10.3390/app13169304 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Applied Sciences, online erschienen am 16.08.2023. Verfasst von Haodong Ma und 3 weiteren Autor:innen. Die Arbeit wurde bisher 8-mal zitiert (Crossref) und nennt 39 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Major Science and Technology Special Projects of Xinjiang Uygur Autonomous Region.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Urban traffic prediction is essential for intelligent transportation systems. However, traffic data often exhibit highly complex spatio-temporal correlations, posing challenges for accurate forecasting. Graph neural networks have demonstrated an outstanding ability in capturing spatial correlations and are now extensively applied to traffic prediction. However, many graph-based methods neglect the dynamic spatial features between road segments and the continuity of spatial features across adjacent time steps, leading to subpar predictive performance. This paper proposes a Dynamic Spatio-Temporal Graph Fusion Convolutional Network (DSTGFCN) to enhance the accuracy of traffic prediction. Specifically, we designed a dynamic graph fusion module without prior road spatial information, which extracts dynamic spatial information among roads from observed data. Subsequently, we fused the dynamic spatial features of the current time step and adjacent time steps to generate a dynamic graph for each time step. The graph convolutional gated recurrent network was employed to model the spatio-temporal correlations jointly. Additionally, residual connections were added to the model to enhance the ability to extract long-term temporal relationships. Finally, we conducted experiments on six publicly available traffic datasets, and the results demonstrated that DSTGFCN outperforms the baseline models with state-of-the-art predictive performance.

Förderung

  • Major Science and Technology Special Projects of Xinjiang Uygur Autonomous Region

Zitieren

APA

Ma, H., Qin, X., Jia, Y., & Zhou, J. (2023). Dynamic Spatio-Temporal Graph Fusion Convolutional Network for Urban Traffic Prediction. Applied Sciences, 13(16), 9304. https://doi.org/10.3390/app13169304

Vancouver

Ma H, Qin X, Jia Y, Zhou J. Dynamic Spatio-Temporal Graph Fusion Convolutional Network for Urban Traffic Prediction. Applied Sciences. 2023;13(16):9304. doi:10.3390/app13169304

BibTeX
@article{Ma2023,
  author = {Ma, Haodong and Qin, Xizhong and Jia, Yuan and Zhou, Junwei},
  title = {Dynamic Spatio-Temporal Graph Fusion Convolutional Network for Urban Traffic Prediction},
  journal = {Applied Sciences},
  year = {2023},
  volume = {13},
  number = {16},
  pages = {9304},
  doi = {10.3390/app13169304}
}
Kostenlos starten →