An Attention-Augmented Convolutional Neural Network With Focal Loss for Mixed-Type Wafer Defect Classification
Silicon wafer defect classification is crucial for improving fabrication and chip production. Although 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, wh...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2023-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10268403/ |
| _version_ | 1797661522325929984 |
|---|---|
| author | Uzma Batool Mohd Ibrahim Shapiai Salama A. Mostafa Mohd Zamri Ibrahim |
| author_facet | Uzma Batool Mohd Ibrahim Shapiai Salama A. Mostafa Mohd Zamri Ibrahim |
| author_sort | Uzma Batool |
| collection | DOAJ |
| description | Silicon wafer defect classification is crucial for improving fabrication and chip production. Although 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. |
| first_indexed | 2024-03-11T18:45:46Z |
| format | Article |
| id | doaj.art-8c02eab9b67e4750ac72370e435df47d |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-03-11T18:45:46Z |
| publishDate | 2023-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-8c02eab9b67e4750ac72370e435df47d2023-10-11T23:00:17ZengIEEEIEEE Access2169-35362023-01-011110889110890510.1109/ACCESS.2023.332102510268403An Attention-Augmented Convolutional Neural Network With Focal Loss for Mixed-Type Wafer Defect ClassificationUzma Batool0https://orcid.org/0000-0003-0589-5643Mohd Ibrahim Shapiai1https://orcid.org/0000-0003-0594-8231Salama A. Mostafa2https://orcid.org/0000-0001-5348-502XMohd Zamri Ibrahim3https://orcid.org/0000-0003-0795-4096Centre for Artificial Intelligence and Robotics iKohza, Malaysia–Japan International Institute of Technology, Universiti Teknologi Malaysia, Kuala Lumpur, MalaysiaCentre for Artificial Intelligence and Robotics iKohza, Malaysia–Japan International Institute of Technology, Universiti Teknologi Malaysia, Kuala Lumpur, MalaysiaFaculty of Computer Science and Information Technology, Universiti Tun Hussein Onn Malaysia, Parit Raja, Johor, MalaysiaFaculty of Electrical and Electronics Engineering Technology, Universiti Malaysia Pahang, Pekan, Pahang, MalaysiaSilicon wafer defect classification is crucial for improving fabrication and chip production. Although 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.https://ieeexplore.ieee.org/document/10268403/Anomaly detectiondeep learningmixed-type defectsmulti-defect classificationpattern recognitionchannel attention |
| spellingShingle | Uzma Batool Mohd Ibrahim Shapiai Salama A. Mostafa Mohd Zamri Ibrahim An Attention-Augmented Convolutional Neural Network With Focal Loss for Mixed-Type Wafer Defect Classification IEEE Access Anomaly detection deep learning mixed-type defects multi-defect classification pattern recognition channel attention |
| title | An Attention-Augmented Convolutional Neural Network With Focal Loss for Mixed-Type Wafer Defect Classification |
| title_full | An Attention-Augmented Convolutional Neural Network With Focal Loss for Mixed-Type Wafer Defect Classification |
| title_fullStr | An Attention-Augmented Convolutional Neural Network With Focal Loss for Mixed-Type Wafer Defect Classification |
| title_full_unstemmed | An Attention-Augmented Convolutional Neural Network With Focal Loss for Mixed-Type Wafer Defect Classification |
| title_short | An Attention-Augmented Convolutional Neural Network With Focal Loss for Mixed-Type Wafer Defect Classification |
| title_sort | attention augmented convolutional neural network with focal loss for mixed type wafer defect classification |
| topic | Anomaly detection deep learning mixed-type defects multi-defect classification pattern recognition channel attention |
| url | https://ieeexplore.ieee.org/document/10268403/ |
| work_keys_str_mv | AT uzmabatool anattentionaugmentedconvolutionalneuralnetworkwithfocallossformixedtypewaferdefectclassification AT mohdibrahimshapiai anattentionaugmentedconvolutionalneuralnetworkwithfocallossformixedtypewaferdefectclassification AT salamaamostafa anattentionaugmentedconvolutionalneuralnetworkwithfocallossformixedtypewaferdefectclassification AT mohdzamriibrahim anattentionaugmentedconvolutionalneuralnetworkwithfocallossformixedtypewaferdefectclassification AT uzmabatool attentionaugmentedconvolutionalneuralnetworkwithfocallossformixedtypewaferdefectclassification AT mohdibrahimshapiai attentionaugmentedconvolutionalneuralnetworkwithfocallossformixedtypewaferdefectclassification AT salamaamostafa attentionaugmentedconvolutionalneuralnetworkwithfocallossformixedtypewaferdefectclassification AT mohdzamriibrahim attentionaugmentedconvolutionalneuralnetworkwithfocallossformixedtypewaferdefectclassification |