FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3204781343> ?p ?o ?g. }

• W3204781343 endingPage "103546" @default.
• W3204781343 startingPage "103546" @default.
• W3204781343 abstract "• The effect of using label information in mini-batch generation is studied in this paper. • The composition and the order of mini-batch clearly affects the overall performance of the convolutional neural network diagnosis. • Equal mini-batch method outperforms conventional random mini-batch and other machine learning cases for the imbalanced data set problem. • Overall sensitive kernels based on the proposed kernel sensitivity analysis can estimate the performance of the trained network, accurately. • A case study validates the effect of label-based mini-batch and the sensitivity analysis method. This paper suggests label-based, mini-batch methods for convolutional neural network (CNN) based diagnosis of fluid-film bearing rotor systems. Rather than using random mini-batches in the training process, mini-batches are generated based on the label information. Label information is a critical factor for robust diagnosis. Five different types of label-based mini-batches are proposed and their performance is compared to the conventional random mini-batch method. In addition, sensitivity analysis of kernels in convolutional neural networks is suggested as a method to analyze the performance variation. A case study of a fluid-film bearing rotor system is used to show the effect of the proposed methods. The case study results indicate a wide range of performance variation among the proposed mini-batch methods. Of the examined methods, the equally labeled mini-batch approach presents the best performance. Moreover, the results of the kernel sensitivity analysis show that the use of properly sensitive kernels does positively affect the overall performance of the CNN." @default.
• W3204781343 created "2021-10-11" @default.
• W3204781343 creator A5040596221 @default.
• W3204781343 creator A5051700060 @default.
• W3204781343 creator A5064753952 @default.
• W3204781343 creator A5072782690 @default.
• W3204781343 creator A5084771659 @default.
• W3204781343 creator A5085835554 @default.
• W3204781343 date "2021-12-01" @default.
• W3204781343 modified "2023-10-18" @default.
• W3204781343 title "Label-based, Mini-batch Combinations Study for Convolutional Neural Network Based Fluid-film Bearing Rotor System Diagnosis" @default.
• W3204781343 cites W114517082 @default.
• W3204781343 cites W1983364832 @default.
• W3204781343 cites W2061570747 @default.
• W3204781343 cites W2129907507 @default.
• W3204781343 cites W2184192902 @default.
• W3204781343 cites W2341973567 @default.
• W3204781343 cites W2404692435 @default.
• W3204781343 cites W2485614840 @default.
• W3204781343 cites W2556345765 @default.
• W3204781343 cites W2562639359 @default.
• W3204781343 cites W2566702409 @default.
• W3204781343 cites W2593479727 @default.
• W3204781343 cites W2733093374 @default.
• W3204781343 cites W2754767460 @default.
• W3204781343 cites W2810292802 @default.
• W3204781343 cites W2906256948 @default.
• W3204781343 cites W2907007702 @default.
• W3204781343 cites W2908062660 @default.
• W3204781343 cites W2910881901 @default.
• W3204781343 cites W2914345141 @default.
• W3204781343 cites W2919115771 @default.
• W3204781343 cites W2953680418 @default.
• W3204781343 cites W2967625104 @default.
• W3204781343 cites W2971878484 @default.
• W3204781343 cites W2972137370 @default.
• W3204781343 cites W2975932043 @default.
• W3204781343 cites W2978144367 @default.
• W3204781343 cites W3004042885 @default.
• W3204781343 cites W3004165994 @default.
• W3204781343 cites W3009623390 @default.
• W3204781343 cites W3015364277 @default.
• W3204781343 cites W3015913963 @default.
• W3204781343 cites W3034878846 @default.
• W3204781343 cites W3040582905 @default.
• W3204781343 cites W3078132426 @default.
• W3204781343 cites W3082233933 @default.
• W3204781343 cites W3082329034 @default.
• W3204781343 cites W3088411073 @default.
• W3204781343 cites W3094109015 @default.
• W3204781343 cites W3102476541 @default.
• W3204781343 cites W3115630438 @default.
• W3204781343 cites W3123146821 @default.
• W3204781343 cites W3130900996 @default.
• W3204781343 cites W3144205684 @default.
• W3204781343 doi "https://doi.org/10.1016/j.compind.2021.103546" @default.
• W3204781343 hasPublicationYear "2021" @default.
• W3204781343 type Work @default.
• W3204781343 sameAs 3204781343 @default.
• W3204781343 citedByCount "3" @default.
• W3204781343 countsByYear W32047813432023 @default.
• W3204781343 crossrefType "journal-article" @default.
• W3204781343 hasAuthorship W3204781343A5040596221 @default.
• W3204781343 hasAuthorship W3204781343A5051700060 @default.
• W3204781343 hasAuthorship W3204781343A5064753952 @default.
• W3204781343 hasAuthorship W3204781343A5072782690 @default.
• W3204781343 hasAuthorship W3204781343A5084771659 @default.
• W3204781343 hasAuthorship W3204781343A5085835554 @default.
• W3204781343 hasConcept C127413603 @default.
• W3204781343 hasConcept C133731056 @default.
• W3204781343 hasConcept C153180895 @default.
• W3204781343 hasConcept C154945302 @default.
• W3204781343 hasConcept C17281054 @default.
• W3204781343 hasConcept C177124886 @default.
• W3204781343 hasConcept C199978012 @default.
• W3204781343 hasConcept C41008148 @default.
• W3204781343 hasConcept C50644808 @default.
• W3204781343 hasConcept C78519656 @default.
• W3204781343 hasConcept C81363708 @default.
• W3204781343 hasConceptScore W3204781343C127413603 @default.
• W3204781343 hasConceptScore W3204781343C133731056 @default.
• W3204781343 hasConceptScore W3204781343C153180895 @default.
• W3204781343 hasConceptScore W3204781343C154945302 @default.
• W3204781343 hasConceptScore W3204781343C17281054 @default.
• W3204781343 hasConceptScore W3204781343C177124886 @default.
• W3204781343 hasConceptScore W3204781343C199978012 @default.
• W3204781343 hasConceptScore W3204781343C41008148 @default.
• W3204781343 hasConceptScore W3204781343C50644808 @default.
• W3204781343 hasConceptScore W3204781343C78519656 @default.
• W3204781343 hasConceptScore W3204781343C81363708 @default.
• W3204781343 hasFunder F4320322098 @default.
• W3204781343 hasFunder F4320322120 @default.
• W3204781343 hasFunder F4320328359 @default.
• W3204781343 hasLocation W32047813431 @default.
• W3204781343 hasOpenAccess W3204781343 @default.
• W3204781343 hasPrimaryLocation W32047813431 @default.
• W3204781343 hasRelatedWork W1995108368 @default.
• W3204781343 hasRelatedWork W2061890722 @default.

• next