Early warning method and system based on short-time road condition prediction algorithm

The invention provides an early warning method and system based on a short-time road condition prediction algorithm, and the method comprises the steps: firstly obtaining traffic data, carrying out the preprocessing, building an ST-GCN model according to the preprocessed data through employing the s...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: LIU TIANPENG, LI CHANGLIANG, JIA BAIQIANG
Format: Patent
Sprache:chi ; eng
Schlagworte:
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:The invention provides an early warning method and system based on a short-time road condition prediction algorithm, and the method comprises the steps: firstly obtaining traffic data, carrying out the preprocessing, building an ST-GCN model according to the preprocessed data through employing the short-time road condition prediction algorithm, training the built ST-GCN model, obtaining an optimal ST-GCN model, and carrying out the early warning of the optimal ST-GCN model. The method comprises the following steps of: predicting an average vehicle speed according to an optimal ST-GCN model, establishing an evaluation index according to an actual average vehicle speed and the predicted average vehicle speed, evaluating the ST-GCN model by adopting a comparison model according to the evaluation index, verifying the ST-GCN model as an optimal model, and finally, predicting the average vehicle speed according to the average vehicle speed predicted by the ST-GCN model verified as the optimal model. According to th