FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3204244861> ?p ?o ?g. }

• W3204244861 endingPage "107619" @default.
• W3204244861 startingPage "107619" @default.
• W3204244861 abstract "This paper proposes a new framework, named BDD, which bridges Duval’s method with a deep neural network (DNN) approach for power transformer fault diagnosis using dissolved gas analysis (DGA). The proposed BDD consists of the following three key points. First, to overcome an important issue that most DGA data found in real-world industrial settings is unlabeled, Duval’s method is newly used to provide knowledge, which is called pseudo-labeling information, to a DNN for unlabeled DGA data. Second, motivated by the fact that the pseudo-labeled data does not always declare correct answers, a DNN architecture with an auxiliary regularization task is newly proposed, which is somewhat robust to the noisy labeled data. Last, a parameter transfer learning approach is applied to evolve the pre-trained DNN model, which is trained from a large amount of pseudo-labeled source DGA data, for diagnosing the sparse labeled target DGA data. Four case studies are executed through the use of KEPCO's massive unlabeled DGA data and IEC TC 10′s sparse labeled DGA data: (i) a comparison with the existing methods, (ii) examination of the effectiveness of parameter freezing via feature space investigation, (iii) studying the robustness of the regularization task under noisy labeled DGA, and (iv) probing the hyperparameter effects. Moreover, to strengthen the proposed model’s effectiveness, the last fifth case study performs a comparison with the existing methods for KEPCO's sparse labeled data instead of IEC TC 10 data. We confirm that the proposed BDD method outperforms existing methods, thanks to the Duval method’s weak supervision, the regularization task, and parameter transfer." @default.
• W3204244861 created "2021-10-11" @default.
• W3204244861 creator A5055579210 @default.
• W3204244861 creator A5059282584 @default.
• W3204244861 creator A5069917187 @default.
• W3204244861 creator A5084771659 @default.
• W3204244861 creator A5091850759 @default.
• W3204244861 date "2022-03-01" @default.
• W3204244861 modified "2023-09-30" @default.
• W3204244861 title "Learning from even a weak teacher: Bridging rule-based Duval method and a deep neural network for power transformer fault diagnosis" @default.
• W3204244861 cites W1965266627 @default.
• W3204244861 cites W1975708537 @default.
• W3204244861 cites W1994013367 @default.
• W3204244861 cites W1995094777 @default.
• W3204244861 cites W2076139712 @default.
• W3204244861 cites W2080850431 @default.
• W3204244861 cites W2084277209 @default.
• W3204244861 cites W2104885131 @default.
• W3204244861 cites W2134815257 @default.
• W3204244861 cites W2148714802 @default.
• W3204244861 cites W2161381512 @default.
• W3204244861 cites W2290798416 @default.
• W3204244861 cites W2300781102 @default.
• W3204244861 cites W2340811421 @default.
• W3204244861 cites W2415033110 @default.
• W3204244861 cites W2470441196 @default.
• W3204244861 cites W2515319207 @default.
• W3204244861 cites W2724730420 @default.
• W3204244861 cites W2746002367 @default.
• W3204244861 cites W2770049107 @default.
• W3204244861 cites W2887782657 @default.
• W3204244861 cites W2898375427 @default.
• W3204244861 cites W2924922918 @default.
• W3204244861 cites W2957568672 @default.
• W3204244861 cites W2962764460 @default.
• W3204244861 cites W2985255601 @default.
• W3204244861 cites W2993397516 @default.
• W3204244861 cites W2999710741 @default.
• W3204244861 cites W3024720112 @default.
• W3204244861 cites W3028316317 @default.
• W3204244861 cites W3074479686 @default.
• W3204244861 cites W3091448810 @default.
• W3204244861 cites W3094501577 @default.
• W3204244861 cites W3154017982 @default.
• W3204244861 cites W792551570 @default.
• W3204244861 cites W3126948899 @default.
• W3204244861 doi "https://doi.org/10.1016/j.ijepes.2021.107619" @default.
• W3204244861 hasPublicationYear "2022" @default.
• W3204244861 type Work @default.
• W3204244861 sameAs 3204244861 @default.
• W3204244861 citedByCount "11" @default.
• W3204244861 countsByYear W32042448612022 @default.
• W3204244861 countsByYear W32042448612023 @default.
• W3204244861 crossrefType "journal-article" @default.
• W3204244861 hasAuthorship W3204244861A5055579210 @default.
• W3204244861 hasAuthorship W3204244861A5059282584 @default.
• W3204244861 hasAuthorship W3204244861A5069917187 @default.
• W3204244861 hasAuthorship W3204244861A5084771659 @default.
• W3204244861 hasAuthorship W3204244861A5091850759 @default.
• W3204244861 hasConcept C104317684 @default.
• W3204244861 hasConcept C108583219 @default.
• W3204244861 hasConcept C119599485 @default.
• W3204244861 hasConcept C119857082 @default.
• W3204244861 hasConcept C124101348 @default.
• W3204244861 hasConcept C127413603 @default.
• W3204244861 hasConcept C153180895 @default.
• W3204244861 hasConcept C154945302 @default.
• W3204244861 hasConcept C165801399 @default.
• W3204244861 hasConcept C174348530 @default.
• W3204244861 hasConcept C181335627 @default.
• W3204244861 hasConcept C185592680 @default.
• W3204244861 hasConcept C2776135515 @default.
• W3204244861 hasConcept C2776145971 @default.
• W3204244861 hasConcept C31258907 @default.
• W3204244861 hasConcept C41008148 @default.
• W3204244861 hasConcept C50644808 @default.
• W3204244861 hasConcept C55493867 @default.
• W3204244861 hasConcept C63479239 @default.
• W3204244861 hasConcept C66322947 @default.
• W3204244861 hasConcept C81818771 @default.
• W3204244861 hasConcept C8642999 @default.
• W3204244861 hasConceptScore W3204244861C104317684 @default.
• W3204244861 hasConceptScore W3204244861C108583219 @default.
• W3204244861 hasConceptScore W3204244861C119599485 @default.
• W3204244861 hasConceptScore W3204244861C119857082 @default.
• W3204244861 hasConceptScore W3204244861C124101348 @default.
• W3204244861 hasConceptScore W3204244861C127413603 @default.
• W3204244861 hasConceptScore W3204244861C153180895 @default.
• W3204244861 hasConceptScore W3204244861C154945302 @default.
• W3204244861 hasConceptScore W3204244861C165801399 @default.
• W3204244861 hasConceptScore W3204244861C174348530 @default.
• W3204244861 hasConceptScore W3204244861C181335627 @default.
• W3204244861 hasConceptScore W3204244861C185592680 @default.
• W3204244861 hasConceptScore W3204244861C2776135515 @default.
• W3204244861 hasConceptScore W3204244861C2776145971 @default.
• W3204244861 hasConceptScore W3204244861C31258907 @default.
• W3204244861 hasConceptScore W3204244861C41008148 @default.
• W3204244861 hasConceptScore W3204244861C50644808 @default.

• next