EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Integrated spatial-temporal feature alignment with graph convolutional and gated recurrent networks for traffic flow prediction

Karimeh Ibrahim Ata iD, Mohd Khair Hassan iD, Syed Abdul Rahman Al-Haddad iD, Thamer Alquthami, Ribhan Zafira Abdul Rahman, Sameer Alani, Md Azizul Hoque iD

PLOS One · 28.04.2026 · 21 (4) · e0337661

DOI: 10.1371/journal.pone.0337661 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PLOS One, online erschienen am 28.04.2026. Verfasst von Karimeh Ibrahim Ata und 6 weiteren Autor:innen. Beteiligte Einrichtung: Artificial Intelligence and Sensing Technologies (AIST) Research Center, University of Tabuk, Tabuk, Saudi Arabia. Hauptthemen laut MEDLINE: Transportation. Die Arbeit nennt 42 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: RDIA.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Accurate traffic flow prediction is essential for Intelligent Transportation Systems (ITS), yet capturing the complex spatiotemporal relationships within traffic data remains challenging due to dynamic traffic patterns and the non-Euclidean structure of road networks. Existing models struggle to adapt in real time, limiting their prediction accuracy and reliability. This study introduces the Spatiotemporal Feature Alignment with Graph Convolutional and Gated Recurrent Unit (STF-GGRU) model to address these limitations. By integrating a novel Integrated Spatiotemporal Feature Alignment (ISTFA) module, which combines Dynamic K-Nearest Neighbor (D-KNN) and Centered Kernel Alignment (CKA), the model dynamically captures critical spatial and temporal interactions. The STF-GGRU model achieves superior prediction accuracy, with RMSE values of 27.18 and 11.1 on the PeMSD4 and PeMSD8 datasets, outperforming traditional methods such as ARIMA, GRU, LSTM, and advanced neural models. These results demonstrate STF-GGRU’s potential for robust, real-time traffic predictions, marking a significant advancement in ITS capabilities.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

TransportationGraph Neural NetworksPrediction AlgorithmsAlgorithmsRecurrent Neural NetworksHumans

Autor:innen und Institutionen

  • Artificial Intelligence and Sensing Technologies (AIST) Research Center, University of Tabuk, Tabuk, Saudi Arabia.
  • Department of Computer Engineering, Faculty of Computers and Information Technology, University of Tabuk, Tabuk, Saudi Arabia.
  • Department of Electrical and Electronic Engineering, Faculty of Engineering, University Putra Malysia, UPM Serdang, Selangor Darul Ehsan, Malaysia.
  • Department of Computer and Communication Systems Engineering, Faculty of Engineering, University Putra Malysia, UPM Serdang, Selangor Darul Ehsan, Malaysia.
  • Department of Electrical and Computer Engineering, King Abdulaziz University, Jeddah, Saudi Arabia.
  • Electronic Computer Center, University of Anbar, Iraq.

ORCID-Profile: Karimeh Ibrahim Ata, Mohd Khair Hassan, Syed Abdul Rahman Al-Haddad, Md Azizul Hoque

Förderung

  • RDIA

Zitieren

APA

Ata, K. I., Hassan, M. K., Al-Haddad, S. A. R., Alquthami, T., Rahman, R. Z. A., Alani, S., & Hoque, M. A. (2026). Integrated spatial-temporal feature alignment with graph convolutional and gated recurrent networks for traffic flow prediction. PLOS One, 21(4), e0337661. https://doi.org/10.1371/journal.pone.0337661

Vancouver

Ata KI, Hassan MK, Al-Haddad SAR, Alquthami T, Rahman RZA, Alani S, et al. Integrated spatial-temporal feature alignment with graph convolutional and gated recurrent networks for traffic flow prediction. PLOS One. 2026;21(4):e0337661. doi:10.1371/journal.pone.0337661

BibTeX
@article{Ata2026,
  author = {Ata, Karimeh Ibrahim and Hassan, Mohd Khair and Al-Haddad, Syed Abdul Rahman and Alquthami, Thamer and Rahman, Ribhan Zafira Abdul and Alani, Sameer and Hoque, Md Azizul},
  title = {Integrated spatial-temporal feature alignment with graph convolutional and gated recurrent networks for traffic flow prediction},
  journal = {PLOS One},
  year = {2026},
  volume = {21},
  number = {4},
  pages = {e0337661},
  doi = {10.1371/journal.pone.0337661}
}
Kostenlos starten →