FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3166365836> ?p ?o ?g. }

• W3166365836 endingPage "109754" @default.
• W3166365836 startingPage "109754" @default.
• W3166365836 abstract "Unsupervised domain adaptation has achieved certain success in recent cross-domain fault diagnosis research. As a widely used transfer strategy, the distribution alignment often occurs with the problems of too few valid alignment samples, too low confidence of predicted labels, and the inadequate alignment of marginal or conditional distributions. Therefore, this paper proposes a statistical distribution recalibration method of soft labels (SDRS). First, SDRS defines the valid samples and confusion interval in the statistical distribution of per-class predicted probabilities. Then, from the perspective of binary classification, a recalibration space in the confusion interval is further optimized by a center distance metric, to improve predicted confidence and valid distribution alignment. Built on SDRS, a novel cross-domain fault diagnosis approach named SDRS-DAN is constructed, where dynamic distribution adaptation is used to match and adjust the marginal and conditional distribution discrepancies adaptively. Extensive experiments prove the effectiveness of SDRS-DAN in cross-location and cross-machine scenarios. • The proposed SDRS improves the domain adaptation of unsupervised fault diagnosis. • The SDRS provides more valid samples for distribution alignment of fault data. • The recalibration space of SDRS can be optimized by center distance metric. • SDRS-DAN method obtains higher accuracy on cross-machine fault diagnosis tasks. • The dynamic adaptation in SDRS-DAN can adjust the distribution alignment better." @default.
• W3166365836 created "2021-06-22" @default.
• W3166365836 creator A5011472059 @default.
• W3166365836 creator A5014785715 @default.
• W3166365836 creator A5020225736 @default.
• W3166365836 creator A5025851882 @default.
• W3166365836 creator A5069887186 @default.
• W3166365836 date "2021-09-01" @default.
• W3166365836 modified "2023-10-16" @default.
• W3166365836 title "A statistical distribution recalibration method of soft labels to improve domain adaptation for cross-location and cross-machine fault diagnosis" @default.
• W3166365836 cites W2032838163 @default.
• W3166365836 cites W2039914769 @default.
• W3166365836 cites W2060300932 @default.
• W3166365836 cites W2115403315 @default.
• W3166365836 cites W243674440 @default.
• W3166365836 cites W2515979703 @default.
• W3166365836 cites W2529693955 @default.
• W3166365836 cites W2567470842 @default.
• W3166365836 cites W2583525646 @default.
• W3166365836 cites W2801166683 @default.
• W3166365836 cites W2803165512 @default.
• W3166365836 cites W2898375427 @default.
• W3166365836 cites W2903917280 @default.
• W3166365836 cites W2904218127 @default.
• W3166365836 cites W2914298094 @default.
• W3166365836 cites W2918285655 @default.
• W3166365836 cites W2964937757 @default.
• W3166365836 cites W2965977924 @default.
• W3166365836 cites W2969372261 @default.
• W3166365836 cites W2984201918 @default.
• W3166365836 cites W2990705538 @default.
• W3166365836 cites W2991087548 @default.
• W3166365836 cites W2999414995 @default.
• W3166365836 cites W3004464175 @default.
• W3166365836 cites W3013328650 @default.
• W3166365836 cites W3024143642 @default.
• W3166365836 cites W3024666507 @default.
• W3166365836 cites W3027995188 @default.
• W3166365836 cites W3029391820 @default.
• W3166365836 cites W3081710967 @default.
• W3166365836 cites W3090135004 @default.
• W3166365836 cites W3096831136 @default.
• W3166365836 cites W3112738995 @default.
• W3166365836 cites W3126446664 @default.
• W3166365836 cites W3127277566 @default.
• W3166365836 cites W3130126636 @default.
• W3166365836 cites W3135644512 @default.
• W3166365836 doi "https://doi.org/10.1016/j.measurement.2021.109754" @default.
• W3166365836 hasPublicationYear "2021" @default.
• W3166365836 type Work @default.
• W3166365836 sameAs 3166365836 @default.
• W3166365836 citedByCount "6" @default.
• W3166365836 countsByYear W31663658362022 @default.
• W3166365836 countsByYear W31663658362023 @default.
• W3166365836 crossrefType "journal-article" @default.
• W3166365836 hasAuthorship W3166365836A5011472059 @default.
• W3166365836 hasAuthorship W3166365836A5014785715 @default.
• W3166365836 hasAuthorship W3166365836A5020225736 @default.
• W3166365836 hasAuthorship W3166365836A5025851882 @default.
• W3166365836 hasAuthorship W3166365836A5069887186 @default.
• W3166365836 hasConcept C110121322 @default.
• W3166365836 hasConcept C124101348 @default.
• W3166365836 hasConcept C127313418 @default.
• W3166365836 hasConcept C127413603 @default.
• W3166365836 hasConcept C134306372 @default.
• W3166365836 hasConcept C139807058 @default.
• W3166365836 hasConcept C153180895 @default.
• W3166365836 hasConcept C154945302 @default.
• W3166365836 hasConcept C15744967 @default.
• W3166365836 hasConcept C165205528 @default.
• W3166365836 hasConcept C169760540 @default.
• W3166365836 hasConcept C175551986 @default.
• W3166365836 hasConcept C200601418 @default.
• W3166365836 hasConcept C2776434776 @default.
• W3166365836 hasConcept C33923547 @default.
• W3166365836 hasConcept C36503486 @default.
• W3166365836 hasConcept C41008148 @default.
• W3166365836 hasConcept C95623464 @default.
• W3166365836 hasConceptScore W3166365836C110121322 @default.
• W3166365836 hasConceptScore W3166365836C124101348 @default.
• W3166365836 hasConceptScore W3166365836C127313418 @default.
• W3166365836 hasConceptScore W3166365836C127413603 @default.
• W3166365836 hasConceptScore W3166365836C134306372 @default.
• W3166365836 hasConceptScore W3166365836C139807058 @default.
• W3166365836 hasConceptScore W3166365836C153180895 @default.
• W3166365836 hasConceptScore W3166365836C154945302 @default.
• W3166365836 hasConceptScore W3166365836C15744967 @default.
• W3166365836 hasConceptScore W3166365836C165205528 @default.
• W3166365836 hasConceptScore W3166365836C169760540 @default.
• W3166365836 hasConceptScore W3166365836C175551986 @default.
• W3166365836 hasConceptScore W3166365836C200601418 @default.
• W3166365836 hasConceptScore W3166365836C2776434776 @default.
• W3166365836 hasConceptScore W3166365836C33923547 @default.
• W3166365836 hasConceptScore W3166365836C36503486 @default.
• W3166365836 hasConceptScore W3166365836C41008148 @default.
• W3166365836 hasConceptScore W3166365836C95623464 @default.
• W3166365836 hasLocation W31663658361 @default.
• W3166365836 hasOpenAccess W3166365836 @default.

• next