EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Non-end-to-end adaptive graph learning for multi-scale temporal traffic flow prediction

Kang Xu iD, Bin Pan, MingXin Zhang, Xuan Zhang, XiaoYu Hou, JingXian Yu, ZhiZhu Lu, Xiao Zeng, QingQing Jia

PLOS One · 2025

DOI: 10.1371/journal.pone.0322145 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PLOS One, 2025. Verfasst von Kang Xu und 8 weiteren Autor:innen. Beteiligte Einrichtung: School of Artificial Intelligence and Software, LiaoNing Petrochemical University, Fushun, China. Hauptthemen laut MEDLINE: Machine Learning, Transportation. Die Arbeit nennt 26 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Innovative Research Group Project of the National Natural Science Foundation of China, Liaoning Revitalization Talents Program.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Accurate traffic flow prediction is vital for intelligent transportation systems but presents significant challenges. Existing methods, however, have the following limitations: (1) insufficient exploration of interactions across different temporal scales, which restricts effective future flow prediction; (2) reliance on predefined graph structures in graph neural networks, making it challenging to accurately model the spatial relationships in complex road networks; and (3) end-to-end training, which often results in unclear optimization directions for model parameters, thereby limiting improvements in predictive performance. To address these issues, this paper proposes a non-end-to-end adaptive graph learning algorithm capable of effectively capturing complex dependencies. The method incorporates a multi-scale temporal attention module and a multi-scale temporal convolution module to extract multi-scale information. Additionally, a novel graph learning module is designed to adaptively capture potential correlations between nodes during training. The parameters of the prediction and graph learning modules are alternately optimized, ensuring global performance improvement under locally optimal conditions. Furthermore, the graph structure is dynamically updated using a weighted summation approach.Experiments demonstrate that the proposed method significantly improves prediction accuracy on the PeMSD4 and PeMSD8 datasets. Ablation studies further validate the effectiveness of each module, and the rationality of the graph structures generated by the graph learning module is visually confirmed, showcasing excellent predictive performance.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Machine LearningTransportationAlgorithmsNeural Networks, ComputerHumans

Autor:innen und Institutionen

  • School of Artificial Intelligence and Software, LiaoNing Petrochemical University, Fushun, China.
  • College of Science, LiaoNing Petrochemical University, Fushun, China.
  • College of Information and Control Engineering, LiaoNing Petrochemical University, Fushun, China.
  • Northeast Forestry University, Heilongjiang, China.

ORCID-Profile: Kang Xu

Förderung

  • Innovative Research Group Project of the National Natural Science Foundation of China
  • Liaoning Revitalization Talents Program

Zitieren

APA

Xu, K., Pan, B., Zhang, M., Zhang, X., Hou, X., Yu, J., Lu, Z., Zeng, X., & Jia, Q. (2025). Non-end-to-end adaptive graph learning for multi-scale temporal traffic flow prediction. PLOS One. https://doi.org/10.1371/journal.pone.0322145

Vancouver

Xu K, Pan B, Zhang M, Zhang X, Hou X, Yu J, et al. Non-end-to-end adaptive graph learning for multi-scale temporal traffic flow prediction. PLOS One. 2025. doi:10.1371/journal.pone.0322145

BibTeX
@article{Xu2025,
  author = {Xu, Kang and Pan, Bin and Zhang, MingXin and Zhang, Xuan and Hou, XiaoYu and Yu, JingXian and Lu, ZhiZhu and Zeng, Xiao and Jia, QingQing},
  title = {Non-end-to-end adaptive graph learning for multi-scale temporal traffic flow prediction},
  journal = {PLOS One},
  year = {2025},
  doi = {10.1371/journal.pone.0322145}
}
Kostenlos starten →