FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4285405358> ?p ?o ?g. }

• W4285405358 endingPage "108720" @default.
• W4285405358 startingPage "108720" @default.
• W4285405358 abstract "• An explanation model based on a variable neighborhood search approach was proposed. • Three model-agnostic explainable AI methods were used to interpret the black-box models. • The proposed VNS-based method provided a more predictive short-list of features. • Among the tree-based ML models, random forest was the best predictor with 0.903 AUC. • The resultant system can help policy makers to understand and mitigate injury severity risk factors. Millions of car crashes occur annually in the US, leaving tens of thousands of deaths and many more severe injuries. Thus, understanding the most impactful contributors to severe injuries in automobile crashes and mitigating their effects are of great importance in traffic safety improvement. This paper develops a hybrid framework involving predictive analytics, explainable AI, and heuristic optimization techniques to investigate and explain the injury severity risk factors in automobile crashes. First, our framework examines various machine learning models to identify the one with the best prediction performance as the base model. Then, it utilizes two popular state-of-the-art explainable AI techniques from the literature (i.e., leave-one-covariate-out and TreeExplainer) and our proposed explanation method based on the variable neighborhood search procedure to construe the importance of the variables. Finally, by applying an information fusion technique, our approach identifies a unified ranking list of the most important variables contributing to severe car crash injuries. Transportation safety planners and policymakers can use our findings to reduce the severity of car accidents, improve traffic safety, and save many lives." @default.
• W4285405358 created "2022-07-14" @default.
• W4285405358 creator A5014318887 @default.
• W4285405358 creator A5049563716 @default.
• W4285405358 creator A5053481032 @default.
• W4285405358 date "2022-10-01" @default.
• W4285405358 modified "2023-09-25" @default.
• W4285405358 title "Discovering injury severity risk factors in automobile crashes: A hybrid explainable AI framework for decision support" @default.
• W4285405358 cites W1442942538 @default.
• W4285405358 cites W1787224781 @default.
• W4285405358 cites W1821491182 @default.
• W4285405358 cites W1964885891 @default.
• W4285405358 cites W1971916086 @default.
• W4285405358 cites W2010334716 @default.
• W4285405358 cites W2023254480 @default.
• W4285405358 cites W2084341220 @default.
• W4285405358 cites W2087753833 @default.
• W4285405358 cites W2088630077 @default.
• W4285405358 cites W2090563475 @default.
• W4285405358 cites W2118022153 @default.
• W4285405358 cites W2119755537 @default.
• W4285405358 cites W2129888542 @default.
• W4285405358 cites W2132735659 @default.
• W4285405358 cites W2164878629 @default.
• W4285405358 cites W2342352817 @default.
• W4285405358 cites W2590685879 @default.
• W4285405358 cites W2738135550 @default.
• W4285405358 cites W2756624799 @default.
• W4285405358 cites W2804189068 @default.
• W4285405358 cites W2804239950 @default.
• W4285405358 cites W2888218104 @default.
• W4285405358 cites W2889046169 @default.
• W4285405358 cites W2891503716 @default.
• W4285405358 cites W2911964244 @default.
• W4285405358 cites W2943866241 @default.
• W4285405358 cites W2943891375 @default.
• W4285405358 cites W2962790223 @default.
• W4285405358 cites W2964060211 @default.
• W4285405358 cites W2999615587 @default.
• W4285405358 cites W3006399881 @default.
• W4285405358 cites W3012173658 @default.
• W4285405358 cites W3056490338 @default.
• W4285405358 cites W3080089295 @default.
• W4285405358 cites W3080447758 @default.
• W4285405358 cites W3080683975 @default.
• W4285405358 cites W3087802854 @default.
• W4285405358 cites W3113202420 @default.
• W4285405358 cites W3126272279 @default.
• W4285405358 cites W3137758634 @default.
• W4285405358 cites W3162329636 @default.
• W4285405358 cites W3179678793 @default.
• W4285405358 cites W3197260976 @default.
• W4285405358 cites W3210964472 @default.
• W4285405358 cites W4220774403 @default.
• W4285405358 cites W4225015853 @default.
• W4285405358 cites W4225381259 @default.
• W4285405358 doi "https://doi.org/10.1016/j.ress.2022.108720" @default.
• W4285405358 hasPublicationYear "2022" @default.
• W4285405358 type Work @default.
• W4285405358 citedByCount "6" @default.
• W4285405358 countsByYear W42854053582023 @default.
• W4285405358 crossrefType "journal-article" @default.
• W4285405358 hasAuthorship W4285405358A5014318887 @default.
• W4285405358 hasAuthorship W4285405358A5049563716 @default.
• W4285405358 hasAuthorship W4285405358A5053481032 @default.
• W4285405358 hasConcept C112930515 @default.
• W4285405358 hasConcept C119043178 @default.
• W4285405358 hasConcept C119857082 @default.
• W4285405358 hasConcept C134306372 @default.
• W4285405358 hasConcept C144133560 @default.
• W4285405358 hasConcept C154945302 @default.
• W4285405358 hasConcept C173801870 @default.
• W4285405358 hasConcept C182365436 @default.
• W4285405358 hasConcept C183469790 @default.
• W4285405358 hasConcept C189430467 @default.
• W4285405358 hasConcept C199360897 @default.
• W4285405358 hasConcept C3017944768 @default.
• W4285405358 hasConcept C33923547 @default.
• W4285405358 hasConcept C41008148 @default.
• W4285405358 hasConcept C45804977 @default.
• W4285405358 hasConcept C71924100 @default.
• W4285405358 hasConcept C83209312 @default.
• W4285405358 hasConcept C84525736 @default.
• W4285405358 hasConcept C99454951 @default.
• W4285405358 hasConceptScore W4285405358C112930515 @default.
• W4285405358 hasConceptScore W4285405358C119043178 @default.
• W4285405358 hasConceptScore W4285405358C119857082 @default.
• W4285405358 hasConceptScore W4285405358C134306372 @default.
• W4285405358 hasConceptScore W4285405358C144133560 @default.
• W4285405358 hasConceptScore W4285405358C154945302 @default.
• W4285405358 hasConceptScore W4285405358C173801870 @default.
• W4285405358 hasConceptScore W4285405358C182365436 @default.
• W4285405358 hasConceptScore W4285405358C183469790 @default.
• W4285405358 hasConceptScore W4285405358C189430467 @default.
• W4285405358 hasConceptScore W4285405358C199360897 @default.
• W4285405358 hasConceptScore W4285405358C3017944768 @default.
• W4285405358 hasConceptScore W4285405358C33923547 @default.
• W4285405358 hasConceptScore W4285405358C41008148 @default.

• next