Matches in SemOpenAlex for { <https://semopenalex.org/work/W4387247620> ?p ?o ?g. }
- W4387247620 endingPage "108905" @default.
- W4387247620 startingPage "108891" @default.
- W4387247620 abstract "Silicon wafer defect classification is crucial in improving fabrication and chip production. While deep learning methods have been successful in single-defect wafer classification, the increasing complexity of the fabrication process has introduced the challenge of multiple defects on wafers, which requires more robust feature learning and classification techniques. Attention mechanisms have been used to enhance feature learning for multiple wafer defects. However, they have limited use in a few mixed-type defect categories, and their performance declines as the number of mixed patterns increases. This work proposes an attention-augmented convolutional neural networks (A2CNN) model for enhanced discriminative feature learning of complex defects. The A2CNN model emphasizes the features in the channel and spatial dimensions. Additionally, the model adopts the focal loss function to reduce misclassification and a global average pooling layer to enhance the network’s generalization by reducing overfitting. The A2CNN model is evaluated on the MixedWM38 wafer defect dataset using 10-fold cross-validation. It achieves impressive results, with accuracy, precision, recall, and F1-score reported as 98.66%, 99.0%, 98.55%, and 98.82% respectively. Compared to existing works, the A2CNN model performs better by effectively learning valuable information for complex mixed-type wafer defects." @default.
- W4387247620 created "2023-10-03" @default.
- W4387247620 creator A5016511172 @default.
- W4387247620 creator A5037731226 @default.
- W4387247620 creator A5081758518 @default.
- W4387247620 creator A5082166185 @default.
- W4387247620 date "2023-01-01" @default.
- W4387247620 modified "2023-10-18" @default.
- W4387247620 title "An Attention-Augmented Convolutional Neural Network with Focal Loss for Mixed-Type Wafer Defect Classification" @default.
- W4387247620 cites W1536680647 @default.
- W4387247620 cites W2032099903 @default.
- W4387247620 cites W2051946048 @default.
- W4387247620 cites W2092243497 @default.
- W4387247620 cites W2120196566 @default.
- W4387247620 cites W2179352600 @default.
- W4387247620 cites W2770860928 @default.
- W4387247620 cites W2792319557 @default.
- W4387247620 cites W2798589477 @default.
- W4387247620 cites W2805484002 @default.
- W4387247620 cites W2884585870 @default.
- W4387247620 cites W2890887208 @default.
- W4387247620 cites W2963150697 @default.
- W4387247620 cites W2963351448 @default.
- W4387247620 cites W3000953789 @default.
- W4387247620 cites W3006183307 @default.
- W4387247620 cites W3006864628 @default.
- W4387247620 cites W3012024740 @default.
- W4387247620 cites W3024903722 @default.
- W4387247620 cites W3040197709 @default.
- W4387247620 cites W3082906739 @default.
- W4387247620 cites W3084263271 @default.
- W4387247620 cites W3089513243 @default.
- W4387247620 cites W3113907917 @default.
- W4387247620 cites W3113911158 @default.
- W4387247620 cites W3119943851 @default.
- W4387247620 cites W3124804470 @default.
- W4387247620 cites W3146366485 @default.
- W4387247620 cites W3164104137 @default.
- W4387247620 cites W3193736071 @default.
- W4387247620 cites W3208624098 @default.
- W4387247620 cites W4210493968 @default.
- W4387247620 cites W4210627858 @default.
- W4387247620 cites W4212980558 @default.
- W4387247620 cites W4213350031 @default.
- W4387247620 cites W4214914131 @default.
- W4387247620 cites W4224931281 @default.
- W4387247620 cites W4283387112 @default.
- W4387247620 cites W4286687376 @default.
- W4387247620 cites W4292722430 @default.
- W4387247620 cites W4297502257 @default.
- W4387247620 cites W4297505414 @default.
- W4387247620 cites W4313270795 @default.
- W4387247620 cites W4313591049 @default.
- W4387247620 cites W4321033348 @default.
- W4387247620 cites W4323540155 @default.
- W4387247620 doi "https://doi.org/10.1109/access.2023.3321025" @default.
- W4387247620 hasPublicationYear "2023" @default.
- W4387247620 type Work @default.
- W4387247620 citedByCount "0" @default.
- W4387247620 crossrefType "journal-article" @default.
- W4387247620 hasAuthorship W4387247620A5016511172 @default.
- W4387247620 hasAuthorship W4387247620A5037731226 @default.
- W4387247620 hasAuthorship W4387247620A5081758518 @default.
- W4387247620 hasAuthorship W4387247620A5082166185 @default.
- W4387247620 hasBestOaLocation W43872476201 @default.
- W4387247620 hasConcept C108583219 @default.
- W4387247620 hasConcept C119857082 @default.
- W4387247620 hasConcept C138885662 @default.
- W4387247620 hasConcept C153180895 @default.
- W4387247620 hasConcept C154945302 @default.
- W4387247620 hasConcept C160671074 @default.
- W4387247620 hasConcept C192562407 @default.
- W4387247620 hasConcept C22019652 @default.
- W4387247620 hasConcept C2776401178 @default.
- W4387247620 hasConcept C41008148 @default.
- W4387247620 hasConcept C41895202 @default.
- W4387247620 hasConcept C49040817 @default.
- W4387247620 hasConcept C50644808 @default.
- W4387247620 hasConcept C70437156 @default.
- W4387247620 hasConcept C81363708 @default.
- W4387247620 hasConcept C97931131 @default.
- W4387247620 hasConceptScore W4387247620C108583219 @default.
- W4387247620 hasConceptScore W4387247620C119857082 @default.
- W4387247620 hasConceptScore W4387247620C138885662 @default.
- W4387247620 hasConceptScore W4387247620C153180895 @default.
- W4387247620 hasConceptScore W4387247620C154945302 @default.
- W4387247620 hasConceptScore W4387247620C160671074 @default.
- W4387247620 hasConceptScore W4387247620C192562407 @default.
- W4387247620 hasConceptScore W4387247620C22019652 @default.
- W4387247620 hasConceptScore W4387247620C2776401178 @default.
- W4387247620 hasConceptScore W4387247620C41008148 @default.
- W4387247620 hasConceptScore W4387247620C41895202 @default.
- W4387247620 hasConceptScore W4387247620C49040817 @default.
- W4387247620 hasConceptScore W4387247620C50644808 @default.
- W4387247620 hasConceptScore W4387247620C70437156 @default.
- W4387247620 hasConceptScore W4387247620C81363708 @default.
- W4387247620 hasConceptScore W4387247620C97931131 @default.
- W4387247620 hasFunder F4320310112 @default.