Convolutional Neural Network (CNN) Based Automated Defect Classification (ADC) with Imbalanced Data

In the semiconductor manufacturing industry, Automatic Defect Classification (ADC) plays an important role in maintaining high wafer inspection quality and reducing yield loss. ADC performance has benefitted from using machine learning (ML) algorithms; however, performance is negatively affected by the data imbalance and limited amounts of training data. Synthetic Minority Oversampling Technique (SMOTE) is an oversampling technique to adjust the skewed class distribution of a dataset so that the bias of the majority class is reduced. This paper shows that applying SMOTE achieved higher accuracy and purity on two imbalanced datasets, consisting of scanning electron microscopy (SEM) images collected with ASML-HMI eP™ and eScan® series inspection tools. The ML models are also less sensitive to the selection of hyperparameters when SMOTE is applied. We also show that better classification results can be obtained with less training samples with SMOTE; we conducted an experiment where a ML model trained on only 25% of samples with SMOTE achieved a higher ADC accuracy and purity performance compared to the same ML model trained on all samples but without SMOTE. In another experiment using a highly imbalanced SEM dataset with very few counts of the defect-of- interest (DOI), the combination of SMOTE and random undersampling of the majority class improves the accuracy by up to 5x while maintaining the same level of purity.

Learning from imbalanced data sets, where the number of examples of one (majority) class is much higher than the others, presents an important challenge to the machine learning community. Traditional machine learning algorithms may be biased towards the majority class, thus producing poor predictive accuracy over the minority class. In this paper, we describe a new approach that combines boosting, an ensemble-based learning algorithm, with data generation to improve the predictive power of classifiers against imbalanced data sets consisting of two classes. In the DataBoost-IM method, hard examples from both the majority and minority classes are identified during execution of the boosting algorithm. Subsequently, the hard examples are used to separately generate synthetic examples for the majority and minority classes. The synthetic data are then added to the original training set, and the class distribution and the total weights of the different classes in the new training set are rebalanced. The DataBoost-IM method was evaluated, in terms of the F-measures, G-mean and overall accuracy , against seventeen highly and moderately imbalanced data sets using decision trees as base classifiers. Our results are promising and show that the DataBoost-IM method compares well in comparison with a base classifier, a standard benchmarking boosting algorithm and three advanced boosting-based algorithms for imbalanced data set. Results indicate that our approach does not sacrifice one class in favor of the other, but produces high predictions against both minority and majority classes.

Imbalanced data classification is a challenging task in real applications. In this work. A method is proposed for image classification using imbalanced distribution of classes. The proposed method extracts an appropriate feature vector which can be fed into a simple classifier such as support vector machine (SVM) for classification. At first, the clustering-based feature extraction (CBFE) is applied to initially reduce the feature space. Then, the relationships among each considered sample with the minority classes and majority classes are explored through constructing two individual graphs. The Laplacian matrices of these graphs are combined to provide a dedicated projection matrix for each sample under test while preserve the manifold structure of minority and majority classes. The initial feature reduction just needs the first order data statistics and the second graph-based projection is unsupervised. Moreover, SVM is not sensitive to the training set size. So, the proposed method is not only efficient for imbalanced data classification but also it is efficient for data classification in small sample size situations. Different subsets of SVHN and CIFAR-10 datasets with various imbalance ratios are used for experiments. The results show superior performance of the proposed method compared to SVM and convolutional neural network (CNN). No data augmentation or oversampling is done for balancing the data distribution in the proposed method. But, due to weak performance of CNN with imbalanced datasets, the image augmentation is applied for CNN as the competitor. However, the proposed method without data augmentation provides better results than CNN with data augmentation.

Cyber-security experts often require the help of an automated process that filters and classifies network attacks. To apply specific preventive measures for securing networks, the classification of the attack type is the key. Many Machine Learning (ML) models have been proposed as a base for Network Intrusion Detection (NID) systems. However, their performance varies based on multiple factors. For instance, an ML model fitted on a highly imbalanced dataset can be biased toward over-represented attack types. On the other hand, paying attention only to the ML model’s performance in the minority classes can negatively affect its performance in the majority classes. This paper proposes an NID system that addresses the issue of imbalanced datasets and uses Convolutional Neural Networks (CNN) to classify the different attack types. We compare the performance of our proposed system to other systems that use: Random Over-Sampling (ROS), Synthetic Minority Oversampling TEchnique (SMOTE), Adaptive Synthetic Sampling (ADASYN), and Generative Adversarial Networks (GAN). Using the NSL-KDD and the BoT-IoT datasets for benchmarking, we show that our proposed system performs well in the minority classes: recall scores of 70.50% and 72.08% on the User to Root (U2R) and Remote to Local (R2L) attack classes of the NSL-KDD dataset, respectively, while maintaining an overall False Alarm Rate (FAR) of 6.50% and a recall of 90.46% on the binary classification task. Our proposed system scores a weighted average F1-Score of 99.45% on the multi-class classification task using the BoT-IoT dataset.

PurposeThe aim of this study was to analyse and review deep learning convolutional neural networks for detecting and diagnosing early-stage dental caries on periapical radiographs.Materials and MethodsIn order to conduct this review, the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines were followed. Studies published from 2015 to 2021 under the keywords (deep convolutional neural network) AND (caries), (deep learning caries) AND (convolutional neural network) AND (caries) were systematically reviewed.ResultsWhen dental caries is improperly diagnosed, the lesion may eventually invade the enamel, dentin, and pulp tissue, leading to loss of tooth function. Rapid and precise detection and diagnosis are vital for implementing appropriate prevention and treatment of dental caries. Radiography and intraoral images are considered to play a vital role in detecting dental caries; nevertheless, studies have shown that 20% of suspicious areas are mistakenly diagnosed as dental caries using this technique; hence, diagnosis via radiography alone without an objective assessment is inaccurate. Identifying caries with a deep convolutional neural network-based detector enables the operator to distinguish changes in the location and morphological features of dental caries lesions. Deep learning algorithms have broader and more profound layers and are continually being developed, remarkably enhancing their precision in detecting and segmenting objects.ConclusionClinical applications of deep learning convolutional neural networks in the dental field have shown significant accuracy in detecting and diagnosing dental caries, and these models hold promise in supporting dental practitioners to improve patient outcomes.

Hyperspectral remote sensing image classification based on residual generative Adversarial Neural Networks

The imbalanced data refer to datasets where the number of samples in one class (majority class) is much higher than the other (minority class) causing biased classifiers in favor of the majority class. Currently, it is difficult to develop an effective model using machine learning algorithms without considering data preprocessing to balance the imbalanced data sets. In this paper, we propose a Relevant Information-based under-sampling (RIS) approach to improve the classification performance for the minority class by selecting the most relevant samples from the majority class as training data. Our RIS approach is based on a self-organizing principle of relevant information, which allows extracting the underlying structure of the majority class preserving different levels of detail of the original data with a smaller number of samples. Additionally, the RIS captures the data structure beyond second order statistics by estimating information theoretic measures which quantify the statistical structure of the majority class accurately, decreasing the consequences of the imbalanced classes distribution problem. We test our methodology on synthetic and real-world imbalanced datasets. Finally, we use a cross-validation scheme to quantify the classifier performance by evaluating the geometric mean. Results show that our proposal outperforms the state of the art methods for imbalanced class distributions regarding classification geometric mean, especially in highly imbalanced datasets.

Skin cancer diagnosis faces challenges in efficiency and accuracy. This research addresses the need for improved non-invasive diagnostic tools by leveraging deep learning for multi-class skin cancer classification from dermoscopic images. A key focus is overcoming the limitations of imbalanced datasets, common in medical imaging, which can hinder model performance. We propose an optimal strategy utilizing a Convolutional Neural Network (CNN) transfer learning methodology. The process involves CNN-based segmentation to isolate relevant regions, followed by feature extraction and classification. We comparatively evaluated three pre-trained transfer learning techniques: DenseNet201, ResNet50, and VGG16, using the HAM10000 dataset (10,015 images across seven skin cancer classes). To mitigate severe class imbalance, Random Oversampling was employed, chosen for its simplicity and effectiveness in balancing the dataset and enhancing model generalization. Model performance was rigorously evaluated using accuracy, precision, recall, and F1-score. DenseNet201 consistently achieved superior performance, with an accuracy of 97% post-oversampling. It also exhibited the highest precision, recall, and F1-score across all models, confirming its effectiveness in classifying both majority and minority classes. Compared to previous studies on HAM10000, our DenseNet201 model's test accuracy of 96.52% is competitive or superior to reported accuracy of 90-92%. This highlights the synergistic effect of DenseNet201's efficient feature reuse and robust data balancing. This research provides a robust framework for advanced methodologies in skin cancer classification, particularly for imbalanced medical image datasets.

Integrated circuit chip fabrication may induce defects on silicon wafers due to inadequate manufacturing environment, equipment malfunctioning and operational flaws. An identification and analysis of these defects facilitates the process engineering by backtracking and addressing their causes of generation. There exist various computer vision techniques to automate the silicon wafer defect inspection. Recently, deep learning has been employed for the task, with its diverse modeling approaches and network configurations, aiming at providing the best performing classifiers for wafer defect inspection. However, the data for wafer inspection is known to be highly imbalanced. For instance, WM-811K, having abundance of non-defective images and small sets of samples in defect classes. Deep networks trained on such uneven data tend to bias towards major classes leading to false classifiers. This research proposes a convolutional neural network while addressing class imbalance through data undersampling. The proposed method performance has been evaluated by a set of metrics and results are compared with an existing machine learning approach. The results comparison demonstrated 90.44% test accuracy of the method as compared to 78.48% of the existing work. This shows that the imbalance mitigation with the proposed strategy offers a better solution for the wafer defects classification.

For the purpose of applying information technology to the creation of ink style painting, the algorithm of ink painting rendering based on the deep learning framework and convolutional neural network model is designed and improved. Firstly, the ink style rendering program is written in Python. Secondly, VGG under Caffe architecture and Illustration 2Vec models are transplanted to TensorFlow architecture, and the image is rendered in ink style based on deep learning framework and convolutional neural network model. Finally, based on Node.js, the server-side program for image ink style rendering is built. Among them, Express is adopted as the Web-side framework, and the front-end page effect is completed. The results show that the ink rendering logic program is applicable, and the expected purpose is achieved.

paper, we focus on exploring the relationship between weave patterns and their mechanical properties in woven fiber composites through Machine Learning. Specifically, we explore the interactions between woven architectures and in-plane stiffness properties through Deep Convolutional Neural Network (DCNN) and Generative Adversarial Network (GAN). Our research is important for exploring how woven composite’s pattern is related to its mechanical properties and accelerating woven composite design as well as optimization. We focus on two tasks: (1) Stiffness prediction: Predicting in-plane stiffness properties for given weave patterns. Our DCNN extracts high-level features through several convolutional and fully connected layers to determine the final predictions. (2) Weave pattern prediction: Predicting weave patterns for target stiffness properties, which can be treated as the reverse task of the first one. Due to many-to-one mapping between weave patterns and the composite properties, we utilize a Decoder Neural Network as our baseline model and compare its performance with GAN and Genetic Algorithm. We represent the weave patterns as 2D checkerboard models and use finite element analysis (FEA) to determine in-plane stiffness properties, which serve as input data for our ML framework. We show that: (1) for stiffness prediction, DCNN can predict stiffness values for a given weave pattern with relatively high accuracy (above 93%); (2) for weave pattern prediction, the GAN model gives the best prediction accuracy (above 92%) while Decoder Neural Network has the best time efficiency. HAOTIAN FENG

Learning from imbalanced data has conventionally been conducted on stationary data sets. Recently, there have been several methods proposed for mining imbalanced data streams, in which training data is read in consecutive data chunks. Each data chunk is considered as a conventional imbalanced data set, making it easy to apply sampling methods to balance data chunks. However, one drawback of chunk-based learning methods is that the update of classification models is delayed until a full data chunk is received. Therefore, this paper proposes a new method for online learning from imbalanced data streams, which uses naive Bayes as the base learner. To deal with the problem of class imbalance, a new training instance from the minority class is always involved in learning, but one from the majority class is only used with a small probability. In effect, this method corresponds to an under-sampling technique on imbalanced data streams. We show the effectiveness of the proposed online learning method on ten UCI data sets of various domains. Problems in the performance of naive Bayes on imbalanced data sets are also discussed.

Breast cancer is the leading cause of death in women worldwide; prevention of possible death from breast cancer can be decreased by early identification ultrasound image analysis by classifying ultrasound images into three classes (Normal, Benign, and Malignant), where the dataset used has imbalanced data. Imbalanced data cause the classification system only to recognize the majority class, so it is necessary to handle imbalanced data. In this study, imbalanced data can be handled by implementing the Deep Convolution Generative Adversarial Network (DCGAN) method as the addition of synthetic images to the training data. The DCGAN method generates synthetic images with feature learning on a Convolutional Neural Network (CNN), making DCGAN more stable than the basic generative adversarial network method. Synthetic and original images were further classified using the CNN GoogleNet method, which performs well in image classification and with reasonable computation cost. Synthetic ultrasound images were generated using a tuning hyperparameter in the DCGAN method to adjust the input size on GoogleNet for imbalanced data handling. From the experiment result, the implementation of DCGAN-GoogleNet has a higher accuracy in handling imbalanced data than conventional augmentation and other previous research, with an accuracy value reaching 91.61%, which is 1% to 4% higher than the accuracy value in the previous method.

The rapid expansion of digital infrastructures has led to an unprecedented increase in cyber threats, necessitating advanced techniques for real-time anomaly detection in network traffic. Traditional rule-based and statistical methods often fail to detect sophisticated attacks due to their reliance on predefined signatures and limited adaptability to evolving threats. Deep learning has emerged as a promising alternative, leveraging data-driven approaches to enhance detection accuracy. Convolutional Neural Networks (CNNs) have demonstrated efficiency in extracting spatial-temporal patterns from network traffic, while Transformer-based architectures excel in capturing long-range dependencies and sequential anomalies. However, existing solutions face challenges related to scalability, computational overhead, imbalanced datasets, and adversarial robustness. This chapter provides a comprehensive analysis of CNN and Transformer-based deep learning architectures for real-time anomaly detection, highlighting their strengths, limitations, and practical deployment challenges. A hybrid approach integrating CNNs and Transformers is explored to enhance detection performance by combining local feature extraction with global sequence modeling. the role of synthetic data augmentation, adaptive learning techniques, and adversarial defense mechanisms in improving model generalization and resilience is examined. Future research directions focus on explainable AI, lightweight models for real-time applications, and self-supervised learning for mitigating data scarcity. The insights presented in this chapter contribute to the advancement of AI-driven cybersecurity solutions, enabling proactive threat detection and risk mitigation in dynamic network environments.

Early detection of cutaneous melanoma (CM) is crucial for patient survival, yet avoiding overdiagnosis remains essential. Differentiating CM from benign melanoma simulators (MelSim) is challenging due to overlapping features. Deep learning convolutional neural networks (DL-CNNs) have demonstrated dermatologist-level accuracy in identifying CM. We hypothesized that support from DL-CNN could increase dermatologists' accuracy in differentiating CM from MelSim. This cross-sectional reader study analyzed the diagnostic performance of a DL-CNN and 27 dermatologists for 200 skin lesions (100 CM, 100 MelSim). The DL-CNN assigned malignancy scores ranging from 0 to 1 (> 0.5 indicating malignancy). Dermatologists assessed lesions across three levels: (I) dermoscopy only, (II) full case information (dermoscopy, close-up images, metadata), and (III) full case information plus DL-CNN scores. Primary outcomes were sensitivity, specificity, and ROC-AUC of dermatologists with or without DL-CNN-support (level-II versus -III). The DL-CNN and dermatologists in level-II showed a comparable sensitivity (95 % CI) of 90.0 % (82.6-94.5 %) and 90.1 % (86.9-93.2 %, p = 0.153), respectively. However, the DL-CNN's specificity (67.0 % (57.3-75.4 %) versus 73.2 % (69.1-77.3 %)) and ROC-AUC (0.889 (0.845-0.932) versus 0.951 (0.920-0.982)) were significantly lower than for dermatologists (all p < 0.01). When dermatologists integrated DL-CNN predictions (level-III) their sensitivity increased to 91.4 % (88.3-94.5 %, p < 0.001) without markedly changing specificity (74.2 % (70.6-77.7 %, p = 0.435)) or ROC-AUC (0.954 (0.927-0.982, p = 0.581)). Collaboration with a DL-CNN slightly improved dermatologists' diagnostic accuracy in a mixed CM and MelSim dataset, by increasing sensitivity without a loss of specificity. The DL-CNN's level of sensitivity in this difficult-to-diagnose dataset underlines the potential as an assistant diagnostic tool.