DMSTG: Dynamic Multiview Spatio-Temporal Networks for Traffic Forecasting
IEEE Transactions on Mobile Computing · 2024-06 · 23 (6) · 6865-6880
DOI: 10.1109/tmc.2023.3328038 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Mobile Computing, 2024-06. Verfasst von Zulong Diao und 8 weiteren Autor:innen. Die Arbeit wurde bisher 24-mal zitiert (Crossref) und nennt 71 Literaturangaben. Gefördert von: National Natural Science Foundation of China, National Science Fund for Distinguished Young Scholars.
Abstract (Originalsprache)
Traffic sensor networks are widely applied in smart cities to monitor traffic in real-time. Exploiting such data to forecast future traffic conditions has the potential to enhance the decision-making capabilities of intelligent transportation systems, which attracts widespread attention from both industries and academia. Among them, network-wide prediction based on graph convolutional neural networks(GCN) has become mainstream. It models the spatial dependencies of sensors in a graph with a pre-defined Laplacian matrix. However, understanding spatio-temporal traffic patterns is quite challenging as there is a huge difference in terms of traffic patterns during different periods or in different regions. In addition, the actual data collected can be polluted due to unavoidable data loss from severe communication conditions or sensor failures. Considering these issues, we propose a novel dynamic multiview spatial-temporal prediction framework which takes into consideration various factors, including local/global, short/long term spatio-temporal dependencies and their dynamic changes. We creatively design two different modules to comprehensively perceive the changes in traffic patterns. We first propose a dynamic learning module based on our theoretical derivation to estimate the Laplacian matrix of the graph for GCN timely. We also design a self-attention based module to dynamically assign a weight to each part in traffic data. The spatio-temporal features from multiple views are deeply fused by a feature fusion module. The forecasting performance is evaluated with 5 real-time traffic datasets. Experiment results demonstrate that our framework can consistently outperform the state-of-the-art baselines and be more robust under noisy environments.
Förderung
- National Natural Science Foundation of China
- National Science Fund for Distinguished Young Scholars
Zitieren
APA
Diao, Z., Wang, X., Zhang, D., Xie, G., Chen, J., Pei, C., Meng, X., Xie, K., & Zhang, G. (2024). DMSTG: Dynamic Multiview Spatio-Temporal Networks for Traffic Forecasting. IEEE Transactions on Mobile Computing, 23(6), 6865-6880. https://doi.org/10.1109/tmc.2023.3328038
Vancouver
Diao Z, Wang X, Zhang D, Xie G, Chen J, Pei C, et al. DMSTG: Dynamic Multiview Spatio-Temporal Networks for Traffic Forecasting. IEEE Transactions on Mobile Computing. 2024;23(6):6865-6880. doi:10.1109/tmc.2023.3328038
BibTeX
@article{Diao2024,
author = {Diao, Zulong and Wang, Xin and Zhang, Dafang and Xie, Gaogang and Chen, Jianguo and Pei, Changhua and Meng, Xuying and Xie, Kun and Zhang, Guangxing},
title = {DMSTG: Dynamic Multiview Spatio-Temporal Networks for Traffic Forecasting},
journal = {IEEE Transactions on Mobile Computing},
year = {2024},
volume = {23},
number = {6},
pages = {6865--6880},
doi = {10.1109/tmc.2023.3328038}
}
EUVIMED