Matches in SemOpenAlex for { <https://semopenalex.org/work/W3212904554> ?p ?o ?g. }
Showing items 1 to 85 of
85
with 100 items per page.
- W3212904554 endingPage "2060" @default.
- W3212904554 startingPage "2055" @default.
- W3212904554 abstract "In semiconductor foundries, wafer map defect analysis is crucial to prevent yield excursion. However, traditional manual inspection can hardly meet the high-throughput demand. Deep learning-based automatic defect detection shows promising efforts to achieve high accuracy and efficiency, yet the current approaches’ performance is limited by the imbalanced dataset and lack of interpretability. In this article, we propose a variational autoencoder-enhanced deep learning model (VAEDLM) for wafer defect imbalanced classification. It is light-weighted and effective in wafer defect pattern recognition on imbalanced dataset. It used variational autoencoders (VAEs) and decoders to generate similar wafer defect maps and a refined deep convolutional neural network (CNN) for feature learning. We demonstrate the method using an authentic wafer map dataset, WM-811K. The performance is not only significantly improved after data augmentation, but it also beats the state-of-the art methods, reaching 99.19% accuracy, 99.10% recall, 99.23% precision, 99.96% AUC, and 99.16% for F1-score. It clearly demonstrates the method’s efficacy to deal with the imbalanced defect pattern. Our study using saliency map and t-distributed stochastic neighbor embedding (t-SNE) further leads to enhanced interpretability." @default.
- W3212904554 created "2021-11-22" @default.
- W3212904554 creator A5010455569 @default.
- W3212904554 creator A5042739384 @default.
- W3212904554 creator A5057378727 @default.
- W3212904554 creator A5062907745 @default.
- W3212904554 date "2021-12-01" @default.
- W3212904554 modified "2023-10-01" @default.
- W3212904554 title "A Variational Autoencoder Enhanced Deep Learning Model for Wafer Defect Imbalanced Classification" @default.
- W3212904554 cites W1979091955 @default.
- W3212904554 cites W1979757125 @default.
- W3212904554 cites W2020286945 @default.
- W3212904554 cites W2030362328 @default.
- W3212904554 cites W2034243637 @default.
- W3212904554 cites W2095848267 @default.
- W3212904554 cites W2104441235 @default.
- W3212904554 cites W2104550562 @default.
- W3212904554 cites W2128272608 @default.
- W3212904554 cites W2594332903 @default.
- W3212904554 cites W2790607928 @default.
- W3212904554 cites W2792944472 @default.
- W3212904554 cites W2805484002 @default.
- W3212904554 cites W2922187519 @default.
- W3212904554 cites W2943898222 @default.
- W3212904554 cites W2964154860 @default.
- W3212904554 cites W3024903722 @default.
- W3212904554 doi "https://doi.org/10.1109/tcpmt.2021.3126083" @default.
- W3212904554 hasPublicationYear "2021" @default.
- W3212904554 type Work @default.
- W3212904554 sameAs 3212904554 @default.
- W3212904554 citedByCount "12" @default.
- W3212904554 countsByYear W32129045542022 @default.
- W3212904554 countsByYear W32129045542023 @default.
- W3212904554 crossrefType "journal-article" @default.
- W3212904554 hasAuthorship W3212904554A5010455569 @default.
- W3212904554 hasAuthorship W3212904554A5042739384 @default.
- W3212904554 hasAuthorship W3212904554A5057378727 @default.
- W3212904554 hasAuthorship W3212904554A5062907745 @default.
- W3212904554 hasConcept C101738243 @default.
- W3212904554 hasConcept C108583219 @default.
- W3212904554 hasConcept C119857082 @default.
- W3212904554 hasConcept C153180895 @default.
- W3212904554 hasConcept C154945302 @default.
- W3212904554 hasConcept C160671074 @default.
- W3212904554 hasConcept C171250308 @default.
- W3212904554 hasConcept C192562407 @default.
- W3212904554 hasConcept C2781067378 @default.
- W3212904554 hasConcept C41008148 @default.
- W3212904554 hasConcept C41608201 @default.
- W3212904554 hasConcept C81363708 @default.
- W3212904554 hasConceptScore W3212904554C101738243 @default.
- W3212904554 hasConceptScore W3212904554C108583219 @default.
- W3212904554 hasConceptScore W3212904554C119857082 @default.
- W3212904554 hasConceptScore W3212904554C153180895 @default.
- W3212904554 hasConceptScore W3212904554C154945302 @default.
- W3212904554 hasConceptScore W3212904554C160671074 @default.
- W3212904554 hasConceptScore W3212904554C171250308 @default.
- W3212904554 hasConceptScore W3212904554C192562407 @default.
- W3212904554 hasConceptScore W3212904554C2781067378 @default.
- W3212904554 hasConceptScore W3212904554C41008148 @default.
- W3212904554 hasConceptScore W3212904554C41608201 @default.
- W3212904554 hasConceptScore W3212904554C81363708 @default.
- W3212904554 hasFunder F4320321001 @default.
- W3212904554 hasFunder F4320322163 @default.
- W3212904554 hasIssue "12" @default.
- W3212904554 hasLocation W32129045541 @default.
- W3212904554 hasOpenAccess W3212904554 @default.
- W3212904554 hasPrimaryLocation W32129045541 @default.
- W3212904554 hasRelatedWork W2605281151 @default.
- W3212904554 hasRelatedWork W3006943036 @default.
- W3212904554 hasRelatedWork W3191046242 @default.
- W3212904554 hasRelatedWork W3208423683 @default.
- W3212904554 hasRelatedWork W4206493799 @default.
- W3212904554 hasRelatedWork W4213225422 @default.
- W3212904554 hasRelatedWork W4294031299 @default.
- W3212904554 hasRelatedWork W4299487748 @default.
- W3212904554 hasRelatedWork W4306194456 @default.
- W3212904554 hasRelatedWork W4310880831 @default.
- W3212904554 hasVolume "11" @default.
- W3212904554 isParatext "false" @default.
- W3212904554 isRetracted "false" @default.
- W3212904554 magId "3212904554" @default.
- W3212904554 workType "article" @default.