FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4386893047> ?p ?o ?g. }

• W4386893047 endingPage "121670" @default.
• W4386893047 startingPage "121670" @default.
• W4386893047 abstract "Interpretability of neural networks aims at the development of models that can give information to the end-user about its inner workings and/or predictions, while keeping the high levels of performance of neural networks. In the context of fault diagnosis, interpretability is necessary for bias detection, model debugging and building trust. This is particularly relevant in the field due to the frequent applications in safety-critical systems, in which an undetected failure can result in highly detrimental outcomes. In this paper, a novel interpretable neural network model is proposed, referred to as Feature Selection and Sparse Counterfactual Generation (FS-SCF) network. It is a multi-task neural network divided into two branches: one for fault diagnosis and feature selection, and one for counterfactual generation. Thus, the model can be interpreted in terms of what are the most relevant features, and the obtained individual predictions are interpreted through counterfactuals. Also, the generated counterfactuals are used to evaluate necessity and sufficiency of each feature. The obtained rankings are then compared to the ranking obtained through the feature selection technique. The proposed approach is tested in two case studies with real data from the industry. Results show that the proposed neural network is able to achieve high levels of performance for fault diagnosis, generate interpretable counterfactuals, and determine the importance of each feature according to a criterion similar to both necessity and sufficiency." @default.
• W4386893047 created "2023-09-21" @default.
• W4386893047 creator A5017862049 @default.
• W4386893047 creator A5045148687 @default.
• W4386893047 creator A5065766621 @default.
• W4386893047 date "2024-03-01" @default.
• W4386893047 modified "2023-09-27" @default.
• W4386893047 title "FS-SCF Network: Neural Network Interpretability Based on Counterfactual Generation and Feature Selection for Fault Diagnosis" @default.
• W4386893047 cites W1500895378 @default.
• W4386893047 cites W1557021954 @default.
• W4386893047 cites W2064675550 @default.
• W4386893047 cites W2084341220 @default.
• W4386893047 cites W2096908543 @default.
• W4386893047 cites W2115424804 @default.
• W4386893047 cites W2118561568 @default.
• W4386893047 cites W2149636129 @default.
• W4386893047 cites W2156483112 @default.
• W4386893047 cites W2165558283 @default.
• W4386893047 cites W2282821441 @default.
• W4386893047 cites W2403749440 @default.
• W4386893047 cites W2488041515 @default.
• W4386893047 cites W2909392392 @default.
• W4386893047 cites W2911964244 @default.
• W4386893047 cites W2945295328 @default.
• W4386893047 cites W2945976633 @default.
• W4386893047 cites W2996764908 @default.
• W4386893047 cites W3027554678 @default.
• W4386893047 cites W3092961465 @default.
• W4386893047 cites W3099331386 @default.
• W4386893047 cites W3100533721 @default.
• W4386893047 cites W3128426437 @default.
• W4386893047 cites W3158630730 @default.
• W4386893047 cites W3186135811 @default.
• W4386893047 cites W3198247281 @default.
• W4386893047 cites W3201301146 @default.
• W4386893047 cites W3202810143 @default.
• W4386893047 cites W3215196515 @default.
• W4386893047 cites W4200125478 @default.
• W4386893047 cites W4289868147 @default.
• W4386893047 cites W4361294415 @default.
• W4386893047 doi "https://doi.org/10.1016/j.eswa.2023.121670" @default.
• W4386893047 hasPublicationYear "2024" @default.
• W4386893047 type Work @default.
• W4386893047 citedByCount "0" @default.
• W4386893047 crossrefType "journal-article" @default.
• W4386893047 hasAuthorship W4386893047A5017862049 @default.
• W4386893047 hasAuthorship W4386893047A5045148687 @default.
• W4386893047 hasAuthorship W4386893047A5065766621 @default.
• W4386893047 hasConcept C108650721 @default.
• W4386893047 hasConcept C111472728 @default.
• W4386893047 hasConcept C119857082 @default.
• W4386893047 hasConcept C124101348 @default.
• W4386893047 hasConcept C127313418 @default.
• W4386893047 hasConcept C138885662 @default.
• W4386893047 hasConcept C148483581 @default.
• W4386893047 hasConcept C151730666 @default.
• W4386893047 hasConcept C154945302 @default.
• W4386893047 hasConcept C165205528 @default.
• W4386893047 hasConcept C175551986 @default.
• W4386893047 hasConcept C2776401178 @default.
• W4386893047 hasConcept C2779343474 @default.
• W4386893047 hasConcept C2781067378 @default.
• W4386893047 hasConcept C41008148 @default.
• W4386893047 hasConcept C41895202 @default.
• W4386893047 hasConcept C50644808 @default.
• W4386893047 hasConcept C71889745 @default.
• W4386893047 hasConcept C86803240 @default.
• W4386893047 hasConceptScore W4386893047C108650721 @default.
• W4386893047 hasConceptScore W4386893047C111472728 @default.
• W4386893047 hasConceptScore W4386893047C119857082 @default.
• W4386893047 hasConceptScore W4386893047C124101348 @default.
• W4386893047 hasConceptScore W4386893047C127313418 @default.
• W4386893047 hasConceptScore W4386893047C138885662 @default.
• W4386893047 hasConceptScore W4386893047C148483581 @default.
• W4386893047 hasConceptScore W4386893047C151730666 @default.
• W4386893047 hasConceptScore W4386893047C154945302 @default.
• W4386893047 hasConceptScore W4386893047C165205528 @default.
• W4386893047 hasConceptScore W4386893047C175551986 @default.
• W4386893047 hasConceptScore W4386893047C2776401178 @default.
• W4386893047 hasConceptScore W4386893047C2779343474 @default.
• W4386893047 hasConceptScore W4386893047C2781067378 @default.
• W4386893047 hasConceptScore W4386893047C41008148 @default.
• W4386893047 hasConceptScore W4386893047C41895202 @default.
• W4386893047 hasConceptScore W4386893047C50644808 @default.
• W4386893047 hasConceptScore W4386893047C71889745 @default.
• W4386893047 hasConceptScore W4386893047C86803240 @default.
• W4386893047 hasFunder F4320322025 @default.
• W4386893047 hasFunder F4320331146 @default.
• W4386893047 hasLocation W43868930471 @default.
• W4386893047 hasOpenAccess W4386893047 @default.
• W4386893047 hasPrimaryLocation W43868930471 @default.
• W4386893047 hasRelatedWork W2964417775 @default.
• W4386893047 hasRelatedWork W3085152052 @default.
• W4386893047 hasRelatedWork W3163334550 @default.
• W4386893047 hasRelatedWork W4220972794 @default.
• W4386893047 hasRelatedWork W4281786807 @default.
• W4386893047 hasRelatedWork W4318465050 @default.
• W4386893047 hasRelatedWork W4321504685 @default.

• next