FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4307287746> ?p ?o ?g. }

• W4307287746 endingPage "103924" @default.
• W4307287746 startingPage "103924" @default.
• W4307287746 abstract "• Develop highly accurate machine learning models and provide their explanations to facilitate decision making in maritime transport policy. • Use factors directly from or derived from current ship selection method in Asia Pacific region to enhance model explainability and applicability. • Provide consistent explanation and comprehensive analysis of the prediction for individual ships based on SHAP method. • Extent the local SHAP method to a near linear-form global surrogate model in a white-box manner to disclose the decision process of the black-box prediction model. Port state control is the safeguard of maritime transport achieved by inspecting foreign visiting ships and supervising them to rectify the non-compliances detected. One key issue faced by port authorities is to identify ships of higher risk accurately. This study aims to address the ship selection issue by first developing two data-driven ship risk prediction frameworks using features the same as or derived from the current ship selection scheme. Both frameworks are empirically shown to be more efficient than the current ship selection method. Like existing ship risk prediction models, the proposed frameworks are of black-box nature whose working mechanism is opaque. To improve model explainability, local explanation of the prediction of individual ships by the Shapley additive explanations (SHAP) is provided. Furthermore, we innovatively extend the local SHAP model to a near linear-form global surrogate model which is fully-explainable. This demonstrates that the behavior of black-box data-driven models can be as interpretable as white-box models while retaining their prediction accuracy. Numerical experiments demonstrate that the white-box global surrogate models can accurately show the behavior of the original black-box models, shedding light on model validation, fairness verification, and prediction explanation. This study makes the very first attempt in the maritime transport area to quantitatively explain the rationale of black-box prediction models from both local and global perspectives, which facilitates the application of data-driven models and promotes the digital transformation of the traditional shipping industry." @default.
• W4307287746 created "2022-10-31" @default.
• W4307287746 creator A5024001075 @default.
• W4307287746 creator A5068873789 @default.
• W4307287746 creator A5070050188 @default.
• W4307287746 creator A5081098041 @default.
• W4307287746 creator A5081977619 @default.
• W4307287746 date "2022-12-01" @default.
• W4307287746 modified "2023-10-15" @default.
• W4307287746 title "Efficient and explainable ship selection planning in port state control" @default.
• W4307287746 cites W1569958708 @default.
• W4307287746 cites W2053531563 @default.
• W4307287746 cites W2058349358 @default.
• W4307287746 cites W2106100548 @default.
• W4307287746 cites W2111411556 @default.
• W4307287746 cites W2122065846 @default.
• W4307287746 cites W2132397241 @default.
• W4307287746 cites W2203167467 @default.
• W4307287746 cites W2339777171 @default.
• W4307287746 cites W2570113925 @default.
• W4307287746 cites W2584924584 @default.
• W4307287746 cites W2587802550 @default.
• W4307287746 cites W2890105502 @default.
• W4307287746 cites W2891503716 @default.
• W4307287746 cites W2910705748 @default.
• W4307287746 cites W2914489277 @default.
• W4307287746 cites W2965845987 @default.
• W4307287746 cites W2968389258 @default.
• W4307287746 cites W2973461188 @default.
• W4307287746 cites W2981731882 @default.
• W4307287746 cites W2991195848 @default.
• W4307287746 cites W2996061341 @default.
• W4307287746 cites W3006107677 @default.
• W4307287746 cites W3008864638 @default.
• W4307287746 cites W3012526137 @default.
• W4307287746 cites W3014284639 @default.
• W4307287746 cites W3034912846 @default.
• W4307287746 cites W3047386363 @default.
• W4307287746 cites W3049345218 @default.
• W4307287746 cites W3085866332 @default.
• W4307287746 cites W3092263114 @default.
• W4307287746 cites W3094450891 @default.
• W4307287746 cites W3101981467 @default.
• W4307287746 cites W3107179788 @default.
• W4307287746 cites W3111335524 @default.
• W4307287746 cites W3122572291 @default.
• W4307287746 cites W3134250586 @default.
• W4307287746 cites W3135455864 @default.
• W4307287746 cites W3137266700 @default.
• W4307287746 cites W3138587273 @default.
• W4307287746 cites W3157548172 @default.
• W4307287746 cites W3158002759 @default.
• W4307287746 cites W3162666924 @default.
• W4307287746 cites W3165196004 @default.
• W4307287746 cites W3183015861 @default.
• W4307287746 cites W3187917979 @default.
• W4307287746 cites W3209369922 @default.
• W4307287746 cites W3213630550 @default.
• W4307287746 doi "https://doi.org/10.1016/j.trc.2022.103924" @default.
• W4307287746 hasPublicationYear "2022" @default.
• W4307287746 type Work @default.
• W4307287746 citedByCount "1" @default.
• W4307287746 countsByYear W43072877462023 @default.
• W4307287746 crossrefType "journal-article" @default.
• W4307287746 hasAuthorship W4307287746A5024001075 @default.
• W4307287746 hasAuthorship W4307287746A5068873789 @default.
• W4307287746 hasAuthorship W4307287746A5070050188 @default.
• W4307287746 hasAuthorship W4307287746A5081098041 @default.
• W4307287746 hasAuthorship W4307287746A5081977619 @default.
• W4307287746 hasConcept C11413529 @default.
• W4307287746 hasConcept C119599485 @default.
• W4307287746 hasConcept C127413603 @default.
• W4307287746 hasConcept C154945302 @default.
• W4307287746 hasConcept C2775924081 @default.
• W4307287746 hasConcept C32802771 @default.
• W4307287746 hasConcept C41008148 @default.
• W4307287746 hasConcept C42475967 @default.
• W4307287746 hasConcept C48103436 @default.
• W4307287746 hasConcept C81917197 @default.
• W4307287746 hasConceptScore W4307287746C11413529 @default.
• W4307287746 hasConceptScore W4307287746C119599485 @default.
• W4307287746 hasConceptScore W4307287746C127413603 @default.
• W4307287746 hasConceptScore W4307287746C154945302 @default.
• W4307287746 hasConceptScore W4307287746C2775924081 @default.
• W4307287746 hasConceptScore W4307287746C32802771 @default.
• W4307287746 hasConceptScore W4307287746C41008148 @default.
• W4307287746 hasConceptScore W4307287746C42475967 @default.
• W4307287746 hasConceptScore W4307287746C48103436 @default.
• W4307287746 hasConceptScore W4307287746C81917197 @default.
• W4307287746 hasFunder F4320321001 @default.
• W4307287746 hasFunder F4320321592 @default.
• W4307287746 hasFunder F4320337111 @default.
• W4307287746 hasLocation W43072877461 @default.
• W4307287746 hasOpenAccess W4307287746 @default.
• W4307287746 hasPrimaryLocation W43072877461 @default.
• W4307287746 hasRelatedWork W1977435898 @default.
• W4307287746 hasRelatedWork W1990422213 @default.
• W4307287746 hasRelatedWork W2012485387 @default.

• next