EUVIMEDEUVIMED entdecken
Crossref

2F-TP: Learning Flexible Spatiotemporal Dependency for Flexible Traffic Prediction

Jie Zhao, Chao Chen, Chengwu Liao, Hongyu Huang, Jie Ma, Huayan Pu, Jun Luo, Tao Zhu, Shilong Wang

IEEE Transactions on Intelligent Transportation Systems · 2023-12 · 24 (12) · 15379-15391

DOI: 10.1109/tits.2022.3146899 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Intelligent Transportation Systems, 2023-12. Verfasst von Jie Zhao und 8 weiteren Autor:innen. Die Arbeit wurde bisher 26-mal zitiert (Crossref) und nennt 41 Literaturangaben. Gefördert von: National Natural Science Foundation of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Accurate traffic prediction is a critical yet challenging task in Intelligent Transportation Systems, benefiting a variety of smart services, e.g., route planning and traffic management. Although extensive efforts have been devoted to this problem, it is still not well solved due to the flexible dependency within traffic data along both spatial and temporal dimensions. In this paper, we explore the flexibility from three aspects, namely the time-varying local spatial dependency, the dynamic temporal dependency, and the global spatial dependency. Then we propose a novel Dual Graph Gated Recurrent Neural Network (DG2RNN) to effectively model all these dependencies and offer flexible (multi-step) predictions for future traffic flow. Specifically, we design a Dual Graph Convolution Module to capture the local spatial dependency from two perspectives, namely road distance and adaptive correlation. To model the dynamic temporal dependency, we firstly develop a Bidirectional Gated Recurrent Layer to capture the forward and backward sequential contexts of historical traffic flow, then combine the derived hidden states with their various contributions learned by a temporal attention mechanism. Besides, we further design a spatial attention mechanism to learn the latent global spatial dependency among all locations to facilitate the prediction. Extensive experiments on three types of real-world traffic datasets demonstrate that our model outperforms state-of-the-arts. Results also show our model has more stable performance for the flexible prediction with varying prediction horizons.

Förderung

  • National Natural Science Foundation of China

Zitieren

APA

Zhao, J., Chen, C., Liao, C., Huang, H., Ma, J., Pu, H., Luo, J., Zhu, T., & Wang, S. (2023). 2F-TP: Learning Flexible Spatiotemporal Dependency for Flexible Traffic Prediction. IEEE Transactions on Intelligent Transportation Systems, 24(12), 15379-15391. https://doi.org/10.1109/tits.2022.3146899

Vancouver

Zhao J, Chen C, Liao C, Huang H, Ma J, Pu H, et al. 2F-TP: Learning Flexible Spatiotemporal Dependency for Flexible Traffic Prediction. IEEE Transactions on Intelligent Transportation Systems. 2023;24(12):15379-15391. doi:10.1109/tits.2022.3146899

BibTeX
@article{Zhao2023,
  author = {Zhao, Jie and Chen, Chao and Liao, Chengwu and Huang, Hongyu and Ma, Jie and Pu, Huayan and Luo, Jun and Zhu, Tao and Wang, Shilong},
  title = {2F-TP: Learning Flexible Spatiotemporal Dependency for Flexible Traffic Prediction},
  journal = {IEEE Transactions on Intelligent Transportation Systems},
  year = {2023},
  volume = {24},
  number = {12},
  pages = {15379--15391},
  doi = {10.1109/tits.2022.3146899}
}
Kostenlos starten →