Matches in SemOpenAlex for { <https://semopenalex.org/work/W4384404736> ?p ?o ?g. }
Showing items 1 to 78 of
78
with 100 items per page.
- W4384404736 endingPage "110584" @default.
- W4384404736 startingPage "110584" @default.
- W4384404736 abstract "Neural networks (NN) have spurred significant interest in automating machine condition monitoring, with many recent studies focusing on networks that take raw diagnostic signals as input. However, the complexity of these NNs has raised concerns about their physical justification and trustworthiness. Although explainable artificial intelligence (XAI) has developed promising tools to address these issues, the nature and size of raw diagnostic inputs have limited the effectiveness of XAI techniques in condition monitoring. This paper proposes a novel approach combining domain transformation and discretisation techniques with the XAI technique of Shapely value additive explanation (SHAP). This methodology allows the input domain for the network to remain in the original time-domain, while the explanation domain can be chosen as frequency or time–frequency and its discretisation adapted to the specific diagnostic case. This flexibility makes networks trained on raw signals more interpretable, while the controllable domain discretisation facilitates the implementation of XAI with manageable computational costs. The proposed methodology is tested on numerical cases and experimental signals, including the UNSW gear-wear and CWRU bearing-fault datasets. This enhancement of XAI is applicable to common black-box classifiers, providing researchers with an effective tool to give physical justification to their models and bolster trust in AI for machine condition monitoring applications." @default.
- W4384404736 created "2023-07-16" @default.
- W4384404736 creator A5066866405 @default.
- W4384404736 creator A5078484623 @default.
- W4384404736 date "2023-10-01" @default.
- W4384404736 modified "2023-09-26" @default.
- W4384404736 title "Explaining deep neural networks processing raw diagnostic signals" @default.
- W4384404736 cites W1787224781 @default.
- W4384404736 cites W2069962935 @default.
- W4384404736 cites W2129888542 @default.
- W4384404736 cites W2944474187 @default.
- W4384404736 cites W3009370740 @default.
- W4384404736 cites W3022386145 @default.
- W4384404736 cites W3039300052 @default.
- W4384404736 cites W3094627074 @default.
- W4384404736 cites W3102564565 @default.
- W4384404736 cites W4226071416 @default.
- W4384404736 cites W4280512960 @default.
- W4384404736 cites W4289890312 @default.
- W4384404736 doi "https://doi.org/10.1016/j.ymssp.2023.110584" @default.
- W4384404736 hasPublicationYear "2023" @default.
- W4384404736 type Work @default.
- W4384404736 citedByCount "0" @default.
- W4384404736 crossrefType "journal-article" @default.
- W4384404736 hasAuthorship W4384404736A5066866405 @default.
- W4384404736 hasAuthorship W4384404736A5078484623 @default.
- W4384404736 hasBestOaLocation W43844047361 @default.
- W4384404736 hasConcept C105795698 @default.
- W4384404736 hasConcept C119857082 @default.
- W4384404736 hasConcept C124101348 @default.
- W4384404736 hasConcept C127313418 @default.
- W4384404736 hasConcept C132964779 @default.
- W4384404736 hasConcept C134306372 @default.
- W4384404736 hasConcept C154945302 @default.
- W4384404736 hasConcept C165205528 @default.
- W4384404736 hasConcept C175551986 @default.
- W4384404736 hasConcept C199360897 @default.
- W4384404736 hasConcept C2780598303 @default.
- W4384404736 hasConcept C33923547 @default.
- W4384404736 hasConcept C36503486 @default.
- W4384404736 hasConcept C41008148 @default.
- W4384404736 hasConcept C50644808 @default.
- W4384404736 hasConcept C73000952 @default.
- W4384404736 hasConceptScore W4384404736C105795698 @default.
- W4384404736 hasConceptScore W4384404736C119857082 @default.
- W4384404736 hasConceptScore W4384404736C124101348 @default.
- W4384404736 hasConceptScore W4384404736C127313418 @default.
- W4384404736 hasConceptScore W4384404736C132964779 @default.
- W4384404736 hasConceptScore W4384404736C134306372 @default.
- W4384404736 hasConceptScore W4384404736C154945302 @default.
- W4384404736 hasConceptScore W4384404736C165205528 @default.
- W4384404736 hasConceptScore W4384404736C175551986 @default.
- W4384404736 hasConceptScore W4384404736C199360897 @default.
- W4384404736 hasConceptScore W4384404736C2780598303 @default.
- W4384404736 hasConceptScore W4384404736C33923547 @default.
- W4384404736 hasConceptScore W4384404736C36503486 @default.
- W4384404736 hasConceptScore W4384404736C41008148 @default.
- W4384404736 hasConceptScore W4384404736C50644808 @default.
- W4384404736 hasConceptScore W4384404736C73000952 @default.
- W4384404736 hasLocation W43844047361 @default.
- W4384404736 hasOpenAccess W4384404736 @default.
- W4384404736 hasPrimaryLocation W43844047361 @default.
- W4384404736 hasRelatedWork W2961085424 @default.
- W4384404736 hasRelatedWork W3003265541 @default.
- W4384404736 hasRelatedWork W3005925217 @default.
- W4384404736 hasRelatedWork W4246751904 @default.
- W4384404736 hasRelatedWork W4286629047 @default.
- W4384404736 hasRelatedWork W4287871663 @default.
- W4384404736 hasRelatedWork W4306321456 @default.
- W4384404736 hasRelatedWork W4306674287 @default.
- W4384404736 hasRelatedWork W4323546569 @default.
- W4384404736 hasRelatedWork W4224009465 @default.
- W4384404736 hasVolume "200" @default.
- W4384404736 isParatext "false" @default.
- W4384404736 isRetracted "false" @default.
- W4384404736 workType "article" @default.