FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4206574562> ?p ?o ?g. }

• W4206574562 endingPage "1145" @default.
• W4206574562 startingPage "1128" @default.
• W4206574562 abstract "Abstract This study proposes an unsupervised, online structural health monitoring framework robust to the sensor configuration, that is, the number and placement of sensors. The proposed methodology leverages generative adversarial networks (GANs). The GAN's discriminator network is the novelty detector, while its generator provides additional data to tune the detection threshold. GAN models are trained with the fast Fourier transform of structural accelerations as input, avoiding the need for any structure‐specific feature extraction. Dense, convolutional (convolutional neural network), and long short‐term memory (LSTM) units are evaluated as discriminators under different GAN training loss patterns, that is, the differences between discriminator and generator training losses. Results show that the LSTM‐based discriminators and the suggested threshold tuning technique to be robust even in loss patterns with overfitted discriminators, a probable outcome of limited training sets. The framework is evaluated on two benchmark datasets. With only 100 s of training data, it achieved 95% novelty detection accuracy, distinguishing between different damage classes and identifying their resurgence under varying sensor configurations. Finally, the majority‐vote‐ensemble of discriminator‐generator pairs at different training epochs is introduced to reduce false alarms, improve novelty detection accuracy and stability." @default.
• W4206574562 created "2022-01-26" @default.
• W4206574562 creator A5018946694 @default.
• W4206574562 creator A5043962698 @default.
• W4206574562 creator A5075891941 @default.
• W4206574562 creator A5076937338 @default.
• W4206574562 creator A5088033157 @default.
• W4206574562 date "2022-01-21" @default.
• W4206574562 modified "2023-10-16" @default.
• W4206574562 title "Toward a general unsupervised novelty detection framework in structural health monitoring" @default.
• W4206574562 cites W125792881 @default.
• W4206574562 cites W2035912441 @default.
• W4206574562 cites W2039938372 @default.
• W4206574562 cites W2052449364 @default.
• W4206574562 cites W2126431552 @default.
• W4206574562 cites W2131929809 @default.
• W4206574562 cites W2517705048 @default.
• W4206574562 cites W2523802016 @default.
• W4206574562 cites W2556345765 @default.
• W4206574562 cites W2586537367 @default.
• W4206574562 cites W2617614397 @default.
• W4206574562 cites W2621512993 @default.
• W4206574562 cites W2756789966 @default.
• W4206574562 cites W2776541877 @default.
• W4206574562 cites W2790452209 @default.
• W4206574562 cites W2791965385 @default.
• W4206574562 cites W2810305857 @default.
• W4206574562 cites W2892901700 @default.
• W4206574562 cites W2896568470 @default.
• W4206574562 cites W2898456550 @default.
• W4206574562 cites W2921927106 @default.
• W4206574562 cites W2956100145 @default.
• W4206574562 cites W2965544196 @default.
• W4206574562 cites W2990423348 @default.
• W4206574562 cites W2995673861 @default.
• W4206574562 cites W3006037028 @default.
• W4206574562 cites W3015728455 @default.
• W4206574562 cites W3026226589 @default.
• W4206574562 cites W3027547176 @default.
• W4206574562 cites W3028757148 @default.
• W4206574562 cites W3033621544 @default.
• W4206574562 cites W3035423866 @default.
• W4206574562 cites W3045404572 @default.
• W4206574562 cites W3046387678 @default.
• W4206574562 cites W3048988402 @default.
• W4206574562 cites W3092593798 @default.
• W4206574562 cites W3094166660 @default.
• W4206574562 cites W3108425245 @default.
• W4206574562 cites W3115020213 @default.
• W4206574562 cites W3128119818 @default.
• W4206574562 cites W3137602051 @default.
• W4206574562 cites W3159065758 @default.
• W4206574562 cites W3161361986 @default.
• W4206574562 cites W3176607300 @default.
• W4206574562 cites W3180937864 @default.
• W4206574562 doi "https://doi.org/10.1111/mice.12812" @default.
• W4206574562 hasPublicationYear "2022" @default.
• W4206574562 type Work @default.
• W4206574562 citedByCount "22" @default.
• W4206574562 countsByYear W42065745622022 @default.
• W4206574562 countsByYear W42065745622023 @default.
• W4206574562 crossrefType "journal-article" @default.
• W4206574562 hasAuthorship W4206574562A5018946694 @default.
• W4206574562 hasAuthorship W4206574562A5043962698 @default.
• W4206574562 hasAuthorship W4206574562A5075891941 @default.
• W4206574562 hasAuthorship W4206574562A5076937338 @default.
• W4206574562 hasAuthorship W4206574562A5088033157 @default.
• W4206574562 hasConcept C112972136 @default.
• W4206574562 hasConcept C119857082 @default.
• W4206574562 hasConcept C121332964 @default.
• W4206574562 hasConcept C13280743 @default.
• W4206574562 hasConcept C138885662 @default.
• W4206574562 hasConcept C153180895 @default.
• W4206574562 hasConcept C154945302 @default.
• W4206574562 hasConcept C163258240 @default.
• W4206574562 hasConcept C185798385 @default.
• W4206574562 hasConcept C205649164 @default.
• W4206574562 hasConcept C27206212 @default.
• W4206574562 hasConcept C2776401178 @default.
• W4206574562 hasConcept C2778738651 @default.
• W4206574562 hasConcept C2778924833 @default.
• W4206574562 hasConcept C2779803651 @default.
• W4206574562 hasConcept C2780992000 @default.
• W4206574562 hasConcept C41008148 @default.
• W4206574562 hasConcept C41895202 @default.
• W4206574562 hasConcept C52622490 @default.
• W4206574562 hasConcept C62520636 @default.
• W4206574562 hasConcept C76155785 @default.
• W4206574562 hasConcept C81363708 @default.
• W4206574562 hasConcept C94915269 @default.
• W4206574562 hasConceptScore W4206574562C112972136 @default.
• W4206574562 hasConceptScore W4206574562C119857082 @default.
• W4206574562 hasConceptScore W4206574562C121332964 @default.
• W4206574562 hasConceptScore W4206574562C13280743 @default.
• W4206574562 hasConceptScore W4206574562C138885662 @default.
• W4206574562 hasConceptScore W4206574562C153180895 @default.
• W4206574562 hasConceptScore W4206574562C154945302 @default.
• W4206574562 hasConceptScore W4206574562C163258240 @default.

• next