EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

A joint multi-model machine learning prediction approach based on confidence for ship stability

Chaicheng Jiang, Xianbo Xiang, Gong Xiang

Complex & Intelligent Systems · 2024-06 · 10 (3) · 3873-3890

DOI: 10.1007/s40747-024-01363-w ↗

Kurz gefasst

Fachartikel in der Zeitschrift Complex & Intelligent Systems, online erschienen am 27.02.2024. Verfasst von Chaicheng Jiang und 2 weiteren Autor:innen. Die Arbeit wurde bisher 10-mal zitiert (Crossref) und nennt 56 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, Hubei Provincial Natural Science Foundation for Innovation Groups.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Since the traditional ship stability failure probability assessment method has many input parameters and cumbersome intermediate calculation process, this paper proposes a joint multi-model machine learning prediction method based on confidence. The method calculates the confidence of each machine learning model for the current prediction result, selects the top n models among them, and takes the average of their prediction results as the output. The confidence is calculated by a method inspired by semi-supervised learning. To reduce the number of ship features that need to be input for assessment, a sensitivity analysis is used to reject irrelevant features. Eight machine learning models that have good performance and are widely used in other fields, including Radial Basis Function Neural Network, Random Forest, eXtreme Gradient Boosting, and so on, are used as component learners in this study. The hyperparameters of each model are obtained by cross-validation and grid search. The advancedness of the proposed method is verified by comparing it with other models on a small self-built ship stability failure probability dataset. By conducting experiments that simply average the results of the component learners, it is confirmed that simple superposition different models does not necessarily improve the accuracy. At the same time, after pre-processing the input features in different ways, the comparison of the prediction performance was conducted, and the experimental results showed that the proposed method is not affected by the way the input features are preprocessed and therefore has some robustness.

Förderung

  • National Natural Science Foundation of China
  • Hubei Provincial Natural Science Foundation for Innovation Groups

Zitieren

APA

Jiang, C., Xiang, X., & Xiang, G. (2024). A joint multi-model machine learning prediction approach based on confidence for ship stability. Complex & Intelligent Systems, 10(3), 3873-3890. https://doi.org/10.1007/s40747-024-01363-w

Vancouver

Jiang C, Xiang X, Xiang G. A joint multi-model machine learning prediction approach based on confidence for ship stability. Complex & Intelligent Systems. 2024;10(3):3873-3890. doi:10.1007/s40747-024-01363-w

BibTeX
@article{Jiang2024,
  author = {Jiang, Chaicheng and Xiang, Xianbo and Xiang, Gong},
  title = {A joint multi-model machine learning prediction approach based on confidence for ship stability},
  journal = {Complex & Intelligent Systems},
  year = {2024},
  volume = {10},
  number = {3},
  pages = {3873--3890},
  doi = {10.1007/s40747-024-01363-w}
}
Kostenlos starten →