Matches in SemOpenAlex for { <https://semopenalex.org/work/W4288045089> ?p ?o ?g. }
Showing items 1 to 76 of
76
with 100 items per page.
- W4288045089 endingPage "108736" @default.
- W4288045089 startingPage "108736" @default.
- W4288045089 abstract "Unsupervised domain adaptation for intelligent fault diagnosis requires a well-annotated source domain to transfer knowledge to an unlabeled target domain, but the ubiquitous source label noise in realistic scenarios remains largely neglected. Recent efforts following adversarial domain adaptation attempt to learn with label noise conditioned on the classifier predictions. However, an essential flaw in the classifier capacity introduces improper adjustments to the loss function. Moreover, they treat domain-specific and domain-invariant representations as a whole, which threats the effectiveness of learning invariant representations. To address these issues, a Convolutional Kernel Aggregated Domain Adaptation (CKADA) strategy is proposed for fault knowledge transfer. Specifically, a convolutional kernel aggregated layer with domain-mixed attention weights is first designed to harness the diverse learning capacities of multiple kernels. Then, by extending such a layer to the classifier, a classification bridge layer is presented to ensure reliable predictions, based on which the side effects of label noise are further relieved through selecting and reusing source samples. Meanwhile, an additional discrimination bridge layer is constructed, which collaborates with the classification bridge layer to assist adversarial domain adaptation. Extensive experiments on three rolling bearing datasets with various types of noisy transfer tasks demonstrate the effectiveness and robustness of CKADA." @default.
- W4288045089 created "2022-07-27" @default.
- W4288045089 creator A5025038200 @default.
- W4288045089 creator A5060249465 @default.
- W4288045089 creator A5075889094 @default.
- W4288045089 date "2022-11-01" @default.
- W4288045089 modified "2023-10-15" @default.
- W4288045089 title "Convolutional kernel aggregated domain adaptation for intelligent fault diagnosis with label noise" @default.
- W4288045089 cites W2167460663 @default.
- W4288045089 cites W2782812883 @default.
- W4288045089 cites W2887782657 @default.
- W4288045089 cites W2899318073 @default.
- W4288045089 cites W2963100999 @default.
- W4288045089 cites W2979509742 @default.
- W4288045089 cites W2984810221 @default.
- W4288045089 cites W3033043953 @default.
- W4288045089 cites W3034474210 @default.
- W4288045089 cites W3042324151 @default.
- W4288045089 cites W3083630455 @default.
- W4288045089 cites W3085147781 @default.
- W4288045089 cites W3094277917 @default.
- W4288045089 cites W3126272279 @default.
- W4288045089 cites W3149607345 @default.
- W4288045089 cites W3187798812 @default.
- W4288045089 cites W3208991442 @default.
- W4288045089 cites W3213841105 @default.
- W4288045089 cites W3217291690 @default.
- W4288045089 cites W4206495689 @default.
- W4288045089 cites W4210685411 @default.
- W4288045089 cites W4212968486 @default.
- W4288045089 doi "https://doi.org/10.1016/j.ress.2022.108736" @default.
- W4288045089 hasPublicationYear "2022" @default.
- W4288045089 type Work @default.
- W4288045089 citedByCount "10" @default.
- W4288045089 countsByYear W42880450892022 @default.
- W4288045089 countsByYear W42880450892023 @default.
- W4288045089 crossrefType "journal-article" @default.
- W4288045089 hasAuthorship W4288045089A5025038200 @default.
- W4288045089 hasAuthorship W4288045089A5060249465 @default.
- W4288045089 hasAuthorship W4288045089A5075889094 @default.
- W4288045089 hasConcept C119857082 @default.
- W4288045089 hasConcept C150899416 @default.
- W4288045089 hasConcept C153180895 @default.
- W4288045089 hasConcept C154945302 @default.
- W4288045089 hasConcept C2776434776 @default.
- W4288045089 hasConcept C41008148 @default.
- W4288045089 hasConcept C95623464 @default.
- W4288045089 hasConceptScore W4288045089C119857082 @default.
- W4288045089 hasConceptScore W4288045089C150899416 @default.
- W4288045089 hasConceptScore W4288045089C153180895 @default.
- W4288045089 hasConceptScore W4288045089C154945302 @default.
- W4288045089 hasConceptScore W4288045089C2776434776 @default.
- W4288045089 hasConceptScore W4288045089C41008148 @default.
- W4288045089 hasConceptScore W4288045089C95623464 @default.
- W4288045089 hasFunder F4320321001 @default.
- W4288045089 hasFunder F4320328119 @default.
- W4288045089 hasFunder F4320335787 @default.
- W4288045089 hasLocation W42880450891 @default.
- W4288045089 hasOpenAccess W4288045089 @default.
- W4288045089 hasPrimaryLocation W42880450891 @default.
- W4288045089 hasRelatedWork W2563096758 @default.
- W4288045089 hasRelatedWork W2623427976 @default.
- W4288045089 hasRelatedWork W2921036759 @default.
- W4288045089 hasRelatedWork W2961085424 @default.
- W4288045089 hasRelatedWork W3017503936 @default.
- W4288045089 hasRelatedWork W4281382123 @default.
- W4288045089 hasRelatedWork W4308262314 @default.
- W4288045089 hasRelatedWork W4382286161 @default.
- W4288045089 hasRelatedWork W4382897170 @default.
- W4288045089 hasRelatedWork W3158004940 @default.
- W4288045089 hasVolume "227" @default.
- W4288045089 isParatext "false" @default.
- W4288045089 isRetracted "false" @default.
- W4288045089 workType "article" @default.