EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

PT-TDGCN: Pre-Trained Trend-Aware Dynamic Graph Convolutional Network for Traffic Flow Prediction

Hanqing Yang, Sen Wei, Yuanqing Wang

Sensors · 03.11.2025 · 25 (21) · 6709

DOI: 10.3390/s25216709 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 03.11.2025. Verfasst von Hanqing Yang und 2 weiteren Autor:innen. Beteiligte Einrichtung: Department of Traffic Engineering, College of Transportation Engineering, Chang'an University, Xi'an 710064, China. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 59 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Accurate traffic flow prediction is vital for intelligent transportation systems, yet strong spatiotemporal coupling and multi-scale dynamics make modelling difficult. Existing methods often rely on static adjacency and short input windows, limiting adaptation to time-varying spatial relations and long-term patterns. To address these issues, we propose the Pre-trained Trend-aware Dynamic Graph Convolutional Network (PT-TDGCN), a two-stage framework. In the pre-training stage, a Transformer-based masked autoencoder learns segment-level temporal representations from historical sequences. In the prediction stage, three designs are integrated: (1) dynamic graph learning parameterized by tensor decomposition; (2) convolutional trend-aware attention that adds 1D convolutions to capture local trends while preserving global context; and (3) spatial graph convolution combined with lightweight fusion projection for aligning pre-trained, spatial, and temporal representations. Extensive experiments on four real-world datasets demonstrated that PT-TDGCN consistently outperformed 14 baseline models, achieving superior predictive accuracy and robustness.

Schlagwörter

Stichwörter der Autor:innen

convolutional trend-aware attentiondynamic graphpre-trainingtraffic flow prediction

Autor:innen und Institutionen

  • Department of Traffic Engineering, College of Transportation Engineering, Chang'an University, Xi'an 710064, China.

Zitieren

APA

Yang, H., Wei, S., & Wang, Y. (2025). PT-TDGCN: Pre-Trained Trend-Aware Dynamic Graph Convolutional Network for Traffic Flow Prediction. Sensors, 25(21), 6709. https://doi.org/10.3390/s25216709

Vancouver

Yang H, Wei S, Wang Y. PT-TDGCN: Pre-Trained Trend-Aware Dynamic Graph Convolutional Network for Traffic Flow Prediction. Sensors. 2025;25(21):6709. doi:10.3390/s25216709

BibTeX
@article{Yang2025,
  author = {Yang, Hanqing and Wei, Sen and Wang, Yuanqing},
  title = {PT-TDGCN: Pre-Trained Trend-Aware Dynamic Graph Convolutional Network for Traffic Flow Prediction},
  journal = {Sensors},
  year = {2025},
  volume = {25},
  number = {21},
  pages = {6709},
  doi = {10.3390/s25216709}
}
Kostenlos starten →