Article
Computer Science, Interdisciplinary Applications
Dong-Hee Lee, Eun-Su Kim, Seung-Hyun Choi, Young-Mok Bae, Jong-Bum Park, Young-Chan Oh, Kwang-Jae Kim
Summary: This study proposes a new method for defect pattern classification, which combines information on shape, size, location, and bin dimensions. The Bin2Vec method is used to determine the RGB code for each bin, and three levels of bin dimensions are defined through analysis and clustering of a large number of WBMs. Compared to existing taxonomies, this method can identify major defect patterns, new defect patterns, and non-critical defect patterns.
COMPUTERS IN INDUSTRY
(2023)
Article
Computer Science, Artificial Intelligence
Chia-Yu Hsu, Ju-Chien Chien
Summary: This study proposes an ensemble convolutional neural network (ECNN) framework for WBM pattern classification, which effectively identifies common WBM defect patterns and performs superior in terms of precision, recall, F1, and other conventional machine learning classifiers.
JOURNAL OF INTELLIGENT MANUFACTURING
(2022)
Article
Chemistry, Analytical
Eunmi Shin, Chang D. Yoo
Summary: The purpose of this study was to classify defect patterns on wafers with limited resources and time. The study introduced an efficient convolutional neural network model that achieved high performance while reducing resource usage and processing time. By classifying nine frequently found defect patterns, the experiment demonstrated that the model outperformed traditional models in terms of parameter usage, training speed, and inference speed, with an accuracy of 98% and an F1 score of 89.5%.
Article
Engineering, Manufacturing
Yi Wang, Dong Ni
Summary: Wafer maps are critical data for quality control and yield improvement. Most existing automated classification methods for wafer bin maps are limited to scenarios with binary maps and single failure patterns. In this study, a deep learning analysis framework is proposed to handle complex wafer bin maps with multiple bin numbers and spatial failure patterns. The framework is validated using real-world and synthesized datasets, showing superior classification performance compared to other approaches.
IEEE TRANSACTIONS ON SEMICONDUCTOR MANUFACTURING
(2023)
Article
Metallurgy & Metallurgical Engineering
Yu Nai-gong, Xu Qiao, Wang Hong-lu, Lin Jia
Summary: This paper proposes a WBM defect pattern inspection strategy based on the DenseNet deep learning model, with improvements made to the structure and training loss function. Additionally, a constrained mean filtering algorithm is introduced to filter noise grains. Using an entropy-based Monte Carlo dropout algorithm for model prediction, the uncertainty of the model decision can be quantified. Experimental results demonstrate that the improved DenseNet has better recognition ability compared to traditional algorithms in typical WBM defect patterns. Analyzing model uncertainty can effectively reduce the miss or false detection rate and help identify new patterns.
JOURNAL OF CENTRAL SOUTH UNIVERSITY
(2021)
Article
Automation & Control Systems
Youngjae Bae, Seokho Kang
Summary: In this paper, an improved training method for wafer map pattern classification is proposed, which trains a convolutional neural network using supervised contrastive learning. The experimental results show that the proposed method can enhance classification accuracy compared with existing methods, particularly when the training dataset is small.
ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE
(2023)
Article
Automation & Control Systems
Jianbo Yu, Zongli Shen, Shijin Wang
Summary: The study introduces a wafer map defect recognition (WMDR) model based on deep transfer learning and deep forest, which proves to effectively enhance wafer defect recognition performance and outperform other well-known CNNs and classifiers.
ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE
(2021)
Article
Automation & Control Systems
Muhammd Tahir, Hilal Tayara, Maqsood Hayat, Kil To Chong
Summary: 4 mC is an essential epigenetic modification that plays crucial roles in cellular processes. An efficient computational system called iDNA-4mC-DL was developed, showing outstanding performance on multiple datasets and potentially serving as a more supportive tool for basic research and academia.
CHEMOMETRICS AND INTELLIGENT LABORATORY SYSTEMS
(2021)
Article
Computer Science, Interdisciplinary Applications
Suhee Yoon, Seokho Kang
Summary: This paper proposes a semi-automatic wafer map pattern classification method that selectively utilizes a CNN based on its predictive uncertainty, achieving high accuracy while involving a process engineer.
COMPUTERS & INDUSTRIAL ENGINEERING
(2022)
Article
Genetics & Heredity
Di Liu, Zhengkui Lin, Cangzhi Jia
Summary: Machine learning methods have been proven to be effective in predicting neuropeptides. NeuroCNN_GNB, a novel ensemble tool based on four convolution neural network models, outperformed other methods in terms of accuracy. The framework also provides important interpretations using the SHAP algorithm, highlighting the relevant features for neuropeptide prediction.
FRONTIERS IN GENETICS
(2023)
Article
Engineering, Electrical & Electronic
Yuxiang Wei, Huan Wang
Summary: This article proposes a mixed-type wafer defect pattern recognition framework based on multifaceted dynamic convolution (MFD), which effectively detects decisive features and integrates helpful information from defect patterns. Experimental results demonstrate the superiority of the proposed framework compared to traditional methods.
IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT
(2022)
Article
Engineering, Electrical & Electronic
Qiao Xu, Naigong Yu, Firdaous Essaf
Summary: This paper proposes a deep learning method using the attention mechanism and cosine normalization to learn robust knowledge from imbalanced datasets in wafer map inspection. Experimental results show that the proposed method has better performance when trained on imbalanced datasets.
Article
Engineering, Multidisciplinary
You-Jin Park, Rong Pan, Douglas C. Montgomery
Summary: In this study, a new hybrid resampling algorithm is proposed to improve the performance of classifiers by considering semiconductor wafer defect data and wafer warpage information.
QUALITY AND RELIABILITY ENGINEERING INTERNATIONAL
(2023)
Article
Computer Science, Interdisciplinary Applications
Subhrajit Nag, Dhruv Makwana, Sai Chandra R. Teja, Sparsh Mittal, C. Krishna Mohan
Summary: With the increasing integration density and design intricacy of semiconductor wafers, the number and complexity of defects in them are also on the rise. This paper presents a novel network called WSCN that performs simultaneous classification and segmentation of both single and mixed-type wafer defects. WSCN uses a shared encoder for training, resulting in a smaller model size and computational cost compared to previous works, and achieves convergence in fewer training epochs.
COMPUTERS IN INDUSTRY
(2022)
Review
Mathematics
Muhammad Shehrayar Khan, Atif Rizwan, Muhammad Shahzad Faisal, Tahir Ahmad, Muhammad Saleem Khan, Ghada Atteia
Summary: With the increase in users of social media websites such as IMDb and the availability of publicly accessible data, opinion mining has become more accessible. This study explores the categorization of movie reviews, which can be challenging due to the complexity of human language. The use of the Word2Vec model and various features, such as psychological, readability, and linguistic features, were investigated. The results showed that the SVM algorithm with self-trained Word2Vec achieved an F-Measure of 86%, while using a combination of psychological, linguistic, readability features, and Word2Vec features resulted in an F-Measure of 87.93%.