A Novel Attention-Based Dynamic Multi-Graph Spatial-Temporal Graph Neural Network Model for Traffic Prediction

Traffic flow prediction is a non-negligible part of intelligent transportation and mobility. Unfortunately, the unique non-linearity and complex spatial-ST-correlation of transport flow data suggest considerable challenges in prediction. The dynamic interaction of multiple spatial relations greatly...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Veröffentlicht in:	IEEE transactions on emerging topics in computational intelligence Jg. 9; H. 2; S. 1910 - 1923
Hauptverfasser:	Diao, Chunyan, Zhang, Dafang, Liang, Wei, Jiang, Man, Li, Kuanching
Format:	Journal Article
Sprache:	Englisch
Veröffentlicht:	Piscataway IEEE 01.04.2025 The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Schlagworte:	Algorithm design and analysis Algorithms attention mechanism Attention mechanisms Computational modeling Convolution Correlation Data models Feature extraction Graph conventional network Graph convolutional networks Graph neural networks multi-graph Prediction models Predictive models Road traffic Semantics spatial-temporal system Spatiotemporal phenomena Traffic flow traffic prediction
ISSN:	2471-285X, 2471-285X
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Schreiben Sie den ersten Kommentar!