Semiconductor Wafer Defect Classification Using Support Vector Machine with Weighted Dynamic Time Warping Kernel Function

Jeong, Young-Seon

doi:10.7232/iems.2017.16.3.420

Cited by 9 publications

(5 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In [16], a wafer test flow was optimized with a graphical model and in [17], defect characteristics by wafer mapping were D e l e t e d investigated, but did not consider the marginal defects. A method in [18] predicts test results using Support Vector Machine (SVM) with a weighted dynamic time warping kernel function, but did not consider classification [19].…”

Section: Introductionmentioning

confidence: 99%

“…As we can see, most of previous works are based on conventional fault models [11,12,13,14,15,16,17,18], lack of research on marginal defects and process variation defects with machine learning classification methods. To bridge this gap and formally show that, in a quest to reduce ELF and increase reliability, the work presented in this paper combines the concepts of regression and KNN algorithm with data preprocessing method.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Retraction:Reliability assurance in early-life-failure test through improved nearest neighbor regression

Song

Liang

Huang

et al. 2020

IEICE Electron. Express

View full text Add to dashboard Cite

During manufacturing test, researchers usually overlook the importance of process variation defects and marginal defects, which can seriously affect test results of Early-Life-Failure (ELF). Theoretically, machine learning classification methods can be used to identify these two defects. In fact, when features overfitting or data distribution overlap seriously, classifiers perform poorly, it will not achieve the desired results. This paper first-ever proposes a kind of data preprocessing method combines improved K-Nearest Neighbors (KNN) regression classifier, so that the classification results will be enhanced in terms of classification performance. Experiment results demonstrate that the predictive accuracy is 45% higher than the traditional logistic regression method. This proposed method will drive critical new requirements for fault modeling, test generation and test application, and implementing them effectively will require a new level of collaboration between process and product developers.

show abstract

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Retraction:Reliability assurance in early-life-failure test through improved nearest neighbor regression

Song

Liang

Huang

et al. 2020

IEICE Electron. Express

View full text Add to dashboard Cite

show abstract

“…Liu et al (2019) achieved an accuracy of 99.95% by its SVM model for the real-time defect detection task. Also, Baly & Hajj (2012) and Jeong (2017) have achieved good results with the SVM method implementation in semiconductor manufacturing. Lastly, we would like to mention the study from Hoang & Nguyen (2020), where the authors proposed a sequence of SVM and state-of-the-art history-based adaptive differential evolution with linear population size reduction for concrete quality management, which achieved an accuracy of 93%.…”

Section: • Support Vector Machinementioning

confidence: 91%

A PRISMA-driven systematic review of data mining methods used for defects detection and classification in the manufacturing industry

Bártová

Bína

Váchová

2022

Prod.

View full text Add to dashboard Cite

Paper aims: This research aims to analyze the primary studies published in recent years focusing on defect detection or classification in manufacturing and extract information about frequently used data mining (DM) methods, their accuracy, strengths, and limitations.Originality: Industrial production is now undergoing a dynamic transformation in the context of Industry 4.0, where implementation of data mining is a frequently discussed topic, and such an overall summary is missing.Research method: In this study, the PRISMA-driven systematic literature review is combined with the approach defined by Kitchenham (2004). Main findings:The most frequently used data mining methods for defect detection are Bayesian network (BN) and Support vector machine (SVM). Besides previously mentioned methods, the Decision trees (DT) and Clustering are often used for defect classification. Neural Networks (NN) use is common for both defect detection and classification. DT, together with the Genetic algorithm (GA) and SVM, achieved the highest average accuracy. Recently, authors often combine different DM methods, and also methods for data dimensionality reduction are often used. Implications for theory and practice:This study contributes to the quality management literature by extending a summary of recently used DM methods for defect detection and classification. This summary can help researchers choose a suitable method and build models for achieving its research purpose.

show abstract

“…The introduction of fast and accurate object detection models, namely, the single shot detector (SSD) was adopted as the defect detection model [21]. Other researchers have exploited the use of Dynamic Time Warping [4], SVM [22] in order to improve classification accuracy. In addition to these advanced machine learning techniques, a powerful compute mode e.g.…”

Section: Related Workmentioning

confidence: 99%

Wafer Defect Localization and Classification Using Deep Learning Techniques

2022

View full text Add to dashboard Cite

Accurate detection and classification of wafer defects constitute an important component in semiconductor manufacturing. It provides interpretable information to find the possible root causes of defects and to take actions for quality management and yield improvement. Traditional approach to classify wafer defects, performed manually by experienced engineers using computer-aided tools, is time-consuming and can be low in accuracy. Hence, automated detection of wafer defects using deep learning approaches has attracted considerable attention to improve the performance of detection process. However, a majority of these works have focused on defect classification and have ignored defect localization which is equally important in determining how specific process steps can lead to defects in certain locations. To address this, we evaluate the state-of-the-art You Only Look Once (YOLO) architecture to accurately locate and classify wafer map defects. Experimental results obtained on 19200 wafer maps show that YOLOv3 and YOLOv4, the variants of YOLO architecture, can achieve >94% of classification accuracy in real-time. For comparison, other architectures, namely ResNet50 and DenseNet121 are also evaluated for wafer defect classification and they give accuracies 89% and 92% respectively, however, without localization abilities. We find that the object detection methods are very useful in locating and classifying defects on semiconductor wafers.

show abstract

Semiconductor Wafer Defect Classification Using Support Vector Machine with Weighted Dynamic Time Warping Kernel Function

Cited by 9 publications

References 0 publications

Retraction:Reliability assurance in early-life-failure test through improved nearest neighbor regression

Retraction:Reliability assurance in early-life-failure test through improved nearest neighbor regression

A PRISMA-driven systematic review of data mining methods used for defects detection and classification in the manufacturing industry

Wafer Defect Localization and Classification Using Deep Learning Techniques

Contact Info

Product

Resources

About