PDG2Seq: Periodic Dynamic Graph to Sequence Model for Traffic Flow Prediction
Neural Networks · 2025-03 · 183 · 106941
DOI: 10.1016/j.neunet.2024.106941 ↗Kurz gefasst
Fachartikel in der Zeitschrift Neural Networks, 2025-03. Verfasst von Jin Fan und 4 weiteren Autor:innen. Beteiligte Einrichtung: Hangzhou Dianzi University, Hangzhou, China; Zhejiang Provincial Key Laboratory of Industrial Internet in Discrete Industries, Hangzhou, China. Elect…. Hauptthemen laut MEDLINE: Neural Networks, Computer. Die Arbeit wurde bisher 69-mal zitiert (Crossref) und nennt 50 Literaturangaben. Gefördert von: Science and Technology Program of Zhejiang Province, Science and Technology Department of Zhejiang Province, National Natural Science Foundation of China.
Abstract (Originalsprache)
Traffic flow prediction is the foundation of intelligent traffic management systems. Current methods prioritize the development of intricate models to capture spatio-temporal correlations, yet they often neglect the exploitation of latent features within traffic flow. Firstly, the correlation among different road nodes exhibits dynamism rather than remaining static. Secondly, traffic data exhibits evident periodicity, yet current research lacks the exploration and utilization of periodic features. Lastly, current models typically rely solely on historical data for modeling, resulting in the limitation of accurately capturing future trend changes in traffic flow. To address these findings, this paper proposes a Periodic Dynamic Graph to Sequence Model (PDG2Seq) for traffic flow prediction. PDG2Seq consists of the Periodic Feature Selection Module (PFSM) and the Periodic Dynamic Graph Convolutional Gated Recurrent Unit (PDCGRU) to further extract the spatio-temporal features of the dynamic real-time traffic. The PFSM extracts learned periodic features using time points as indices, while the PDCGRU leverages the extracted periodic features from the PFSM and dynamic features from traffic flow to generate a Periodic Dynamic Graph for extracting spatio-temporal features. In the decoding phase, PDG2Seq utilizes periodic features corresponding to the prediction target to capture future trend changes, leading to more accurate predictions. Comprehensive experiments conducted on four large-scale datasets substantiate the superiority of PDG2Seq over existing state-of-the-art baselines. Related codes are available at https://github.com/wengwenchao123/PDG2Seq.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Hangzhou Dianzi University, Hangzhou, China; Zhejiang Provincial Key Laboratory of Industrial Internet in Discrete Industries, Hangzhou, China. Electronic address: fanjin@hdu.edu.cn.
- Zhejiang University of Technology, Hangzhou, China. Electronic address: 111124120010@zjut.edu.cn.
- Hangzhou Dianzi University, Hangzhou, China. Electronic address: 20321310@hdu.edu.cn.
- Hangzhou Dianzi University, Hangzhou, China; Zhejiang Provincial Key Laboratory of Industrial Internet in Discrete Industries, Hangzhou, China. Electronic address: whf@hdu.edu.cn.
- Macquarie University, Sydney, Australia. Electronic address: jia.wu@mq.edu.au.
Förderung
- Science and Technology Program of Zhejiang Province
- Science and Technology Department of Zhejiang Province
- National Natural Science Foundation of China
Zitieren
APA
Fan, J., Weng, W., Chen, Q., Wu, H., & Wu, J. (2025). PDG2Seq: Periodic Dynamic Graph to Sequence Model for Traffic Flow Prediction. Neural Networks, 183, 106941. https://doi.org/10.1016/j.neunet.2024.106941
Vancouver
Fan J, Weng W, Chen Q, Wu H, Wu J. PDG2Seq: Periodic Dynamic Graph to Sequence Model for Traffic Flow Prediction. Neural Networks. 2025;183:106941. doi:10.1016/j.neunet.2024.106941
BibTeX
@article{Fan2025,
author = {Fan, Jin and Weng, Wenchao and Chen, Qikai and Wu, Huifeng and Wu, Jia},
title = {PDG2Seq: Periodic Dynamic Graph to Sequence Model for Traffic Flow Prediction},
journal = {Neural Networks},
year = {2025},
volume = {183},
pages = {106941},
doi = {10.1016/j.neunet.2024.106941}
}
EUVIMED