Evaluation of the machine learning classifier in wafer defects classification

Jizat, Jessnor Arif Mat; Majeed, Anwar P. P. Abdul; Nasir, Ahmad Fakhri Ab.; Taha, Zahari; Yuen, Edmund

doi:10.1016/j.icte.2021.04.007

Cited by 35 publications

(15 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In addition, the objective of authors [20] is to establish the best Machine Learning classifier for the application of wafer defect detection. The experiments proved that the logistic regression classifier is the best classifier for detection with an accuracy of 86.9%.…”

Section: Machine Learning Based Approachesmentioning

confidence: 99%

Leveraging Pima Dataset to Diabetes Prediction: Case Study of Deep Neural Network

Hounguè¹,

Bigirimana²

2022

JCC

View full text Add to dashboard Cite

Diabetes is a chronic disease. In 2019, it was the ninth leading cause of death with an estimated 1.5 million deaths. Poorly controlled, diabetes can lead to serious health problems. That explains why early diagnosis of diabetes is very important. Several approaches that use Artificial Intelligence, specifically Deep Learning, have been widely used with promising results. The contribution of this paper is in two-folds: 1) Deep Neural Network (DNN) approach is used on Pima Indian dataset to predict diabetes using 10 k-fold cross validation and 89% accuracy is obtained; 2) comparative analysis of previous work is provided on diabetes prediction using DNN with the tested model. The results showed that 10 k-fold cross-validation could decrease the efficiency of diabetes prediction models using DNN.

show abstract

Section: Machine Learning Based Approachesmentioning

confidence: 99%

Leveraging Pima Dataset to Diabetes Prediction: Case Study of Deep Neural Network

Hounguè¹,

Bigirimana²

2022

JCC

View full text Add to dashboard Cite

show abstract

“…An RF algorithm was used to build prediction models exploiting wafer map features as input variables in order to better predict the die-level failures in the final test [28]. Several ML-based detection approaches, such as Gaussian density estimation, Gaussian mixture model, k-means Clustering, LR, stochastic gradient descent, etc., have been used to detect faulty wafers in semiconductor manufacturing [29,30]. Moreover, ensemble learning-based ML approaches have also shown great performance in the recognition of wafer map failure pattern types.…”

Section: Literature Reviewmentioning

confidence: 99%

A Deep Convolutional Neural Network-Based Multi-Class Image Classification for Automatic Wafer Map Failure Recognition in Semiconductor Manufacturing

et al. 2021

View full text Add to dashboard Cite

Wafer maps provide engineers with important information about the root causes of failures during the semiconductor manufacturing process. Through the efficient recognition of the wafer map failure pattern type, the semiconductor manufacturing process and its product performance can be improved, as well as reducing the product cost. Therefore, this paper proposes an accurate model for the automatic recognition of wafer map failure types using a deep learning-based convolutional neural network (DCNN). For this experiment, we use WM811K, which is an open-source real-time wafer map dataset containing wafer map images of nine failure classes. Our research contents can be briefly summarized as follows. First, we use random sampling to extract 500 images from each class of the original image dataset. Then we propose a deep convolutional neural network model to generate a multi-class classification model. Lastly, we evaluate the performance of the proposed prediction model and compare it with three other popular machine learning-based models—logistic regression, random forest, and gradient boosted decision trees—and several well-known deep learning models—VGGNet, ResNet, and EfficientNet. Consequently, the comprehensive analysis showed that the performance of the proposed DCNN model outperformed those of other popular machine learning and deep learning-based prediction models.

show abstract

“…Generally, TL is used in huge processing tasks to reduce the amount of computational power. TL can be more accurate, faster with lesser data training and successfully implemented in several studies for instance in [12][13][14].…”

Section: Related Workmentioning

confidence: 99%

Traffic Sign Classification Using Transfer Learning: An Investigation of Feature-Combining Model

et al. 2021

Self Cite

View full text Add to dashboard Cite

The traffic sign classification system is a technology to help drivers to recognise the traffic sign hence reducing the accident. Many types of learning models have been applied to this technology recently. However, the deployment of learning models is unknown and shown to be non-trivial towards image classification and object detection. The implementation of Transfer Learning (TL) has been demonstrated to be a powerful tool in the extraction of essential features as well as can save lots of training time. Besides, the feature-combining model exhibited great performance in the TL method in many applications. Nonetheless, the utilisation of such methods towards traffic sign classification applications are not yet being evaluated. The present study aims to exploit and investigate the effectiveness of transfer learning feature-combining models, particularly to classify traffic signs. The images were gathered from GTSRB dataset which consists of 10 different types of traffic signs i.e. warning, stop, repair, not enter, traffic light, turn right, speed limit (80km/s), speed limit (50km/s), speed limit (60km/s), and turn left sign board. A total of 7000 images were then split to 70:30 for train and test ratio using a stratified method. The VGG16 and VGG19 TL-features models were used to combine with two classifiers, Random Forest (RF) and Neural Network. In summary, six different pipelines were trained and tested. From the results obtained, the best pipeline was VGG16+VGG19 with RF classifier, which was able to yield an average classification accuracy of 0.9838. The findings showed that the feature-combining model successfully classifies the traffic signs much better than the single TL-feature model. The investigation would be useful for traffic signs classification applications i.e. for ADAS systems

show abstract

Evaluation of the machine learning classifier in wafer defects classification

Cited by 35 publications

References 11 publications

Leveraging Pima Dataset to Diabetes Prediction: Case Study of Deep Neural Network

Leveraging Pima Dataset to Diabetes Prediction: Case Study of Deep Neural Network

A Deep Convolutional Neural Network-Based Multi-Class Image Classification for Automatic Wafer Map Failure Recognition in Semiconductor Manufacturing

Traffic Sign Classification Using Transfer Learning: An Investigation of Feature-Combining Model

Contact Info

Product

Resources

About