Fusing XGBoost and SHAP Models for Maritime Accident Prediction and Causality Interpretability Analysis

In order to prevent safety risks, control marine accidents and improve the overall safety of marine navigation, this study established a marine accident prediction model. The influences of management characteristics, environmental characteristics, personnel characteristics, ship characteristics, pil...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Veröffentlicht in:	Journal of marine science and engineering Jg. 10; H. 8; S. 1154
Hauptverfasser:	Zhang, Cheng, Zou, Xiong, Lin, Chuan
Format:	Journal Article
Sprache:	Englisch
Veröffentlicht:	Basel MDPI AG 01.08.2022
Schlagworte:	Accident prevention Algorithms Casualties causal analysis Climate change Coronaviruses COVID-19 Crew Environmental management extreme gradient boosting algorithm Human error interpretable machine learning Machine learning Marine accidents maritime accidents Maritime safety Navigation Pilotage Ports Prediction models Probability Risk Risk factors risk prediction Safety Ship accidents & safety Shipping Surface navigation Traffic accidents & safety China Zhejiang China
ISSN:	2077-1312, 2077-1312
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Schreiben Sie den ersten Kommentar!