KST-GCN: A Knowledge-Driven Spatial-Temporal Graph Convolutional Network for Traffic Forecasting

While considering the spatial and temporal features of traffic, capturing the impacts of various external factors on travel is an essential step towards achieving accurate traffic forecasting. However, existing studies seldom consider external factors or neglect the effect of the complex correlation...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Veröffentlicht in:	IEEE transactions on intelligent transportation systems 2022-09, Vol.23 (9), p.15055-15065
Hauptverfasser:	Zhu, Jiawei, Han, Xing, Deng, Hanhan, Tao, Chao, Zhao, Ling, Wang, Pu, Lin, Tao, Li, Haifeng
Format:	Artikel
Sprache:	eng
Schlagworte:	Ablation Artificial neural networks Computer networks Correlation Data models Forecasting Graphs Knowledge representation Mathematical models multisource spatial-temporal data Networks Perturbation methods Predictive models Roads Semantics Source code spatial-temporal graph convolutional networks Traffic flow forecasting Traffic information
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Schreiben Sie den ersten Kommentar!