A model-based clustering approach to the recognition of the spatial defect patterns produced during semiconductor fabrication

Defects on semiconductor wafers tend to cluster and the spatial defect patterns of these defect clusters contain valuable information about potential problems in the manufacturing processes. This study proposes a model-based clustering algorithm for automatic spatial defect recognition on semiconductor wafers. A mixture model is proposed to model the distributions of defects on wafer surfaces. The proposed algorithm can find the number of defect clusters and identify the pattern of each cluster automatically. It is capable of detecting defect clusters with linear patterns, curvilinear patterns and ellipsoidal patterns. Promising results have been obtained from simulation studies.     

Detection and classification of defect patterns on semiconductor wafers

The detection of process problems and parameter drift at an early stage is crucial to successful semiconductor manufacture. The defect patterns on the wafer can act as an important source of information for quality engineers allowing them to isolate production problems. Traditionally, defect recognition is performed by quality engineers using a scanning electron microscope. This manual approach is not only expensive and time consuming but also it leads to high misidentification levels. In this paper, an automatic approach consisting of a spatial filter, a classification module and an estimation module is proposed to validate both real and simulated data. Experimental results show that three types of typical defect patterns: (i) a linear scratch; (ii) a circular ring; and (iii) an elliptical zone can be successfully extracted and classified. A Gaussian EM algorithm is used to estimate the elliptic and linear patterns, and a spherical-shell algorithm is used to estimate ring patterns. Furthermore, both convex and nonconvex defect patterns can be simultaneously recognized via a hybrid clustering method. The proposed method has the potential to be applied to other industries.     

A generalised uncertain decision tree for defect classification of multiple wafer maps

Classification of defect chip patterns is one of the most important tasks in semiconductor manufacturing process. During the final stage of the process just before release, engineers must manually classify and summarise information of defect chips from a number of wafers that can aid in diagnosing the root causes of failures. Traditionally, several learning algorithms have been developed to classify defect patterns on wafer maps. However, most of them focused on a single wafer bin map based on certain features. The objective of this study is to propose a novel approach to classify defect patterns on multiple wafer maps based on uncertain features. To classify distinct defect patterns described by uncertain features on multiple wafer maps, we propose a generalised uncertain decision tree model considering correlations between uncertain features. In addition, we propose an approach to extract uncertain features of multiple wafer maps from the critical fail bit test (FBT) map, defect shape, and location based on a spatial autocorrelation method. Experiments were conducted using real-life DRAM wafers provided by the semiconductor industry. Results show that the proposed approach is much better than any existing methods reported in the literature.     

Defect pattern recognition on wafers using convolutional neural networks

In semiconductor manufacturing, wafer testing is performed to ensure the performance of each product after wafer fabrication. The wafer map is used to visualize the color-coded wafer test results based on the locations. The defects on the wafer map may be randomly distributed or form clustered patterns. The various clustered defect patterns are usually caused by assignable faults. The identification of the patterns is thus important to provide valuable hints for the root causes diagnosis. Solving the problems helps improve the manufacturing processes and reduce costs. In this study, we present a novel convolutional neural network (CNN)–based method to automatically recognize the defect pattern on wafer maps. Our method uses polar mapping before the training of CNN to transform the circular wafer map into a matrix, which can be processed within CNN architecture. This procedure also reduces the input size and solves variations in wafer sizes and die sizes. To eliminate the effects of rotation, we apply data augmentation in the training of CNN. Experiments using the real-world dataset prove the effectiveness and superiority of our method.     

Wafer yield prediction using derived spatial variables

Unreliable chips tend to form spatial clusters on semiconductor wafers. The spatial patterns of these defects are largely reflected in functional testing results. However, the spatial cluster information of unreliable chips has not been fully used to predict the performance in field use in the literature. This paper proposes a novel wafer yield prediction model that incorporates the spatial clustering information in functional testing. Fused LASSO is first adopted to derive variables based on the spatial distribution of defect clusters. Then, a logistic regression model is used to predict the final yield (ratio of chips that remain functional until expected lifetime) with derived spatial covariates and functional testing values. The proposed model is evaluated both on real production wafers and in an extensive simulation study. The results show that by explicitly considering the characteristics of defect clusters, our proposed model provides improved performance compared to existing methods. Moreover, the cross‐validation experiments prove that our approach is capable of using historical data to predict yield on newly produced wafers.     

A novel hybrid resampling for semiconductor wafer defect bin classification

Generally, defective dies on semiconductor wafer maps tend to form spatial clusters in distinguishable patterns which contain crucial information on specific problems of equipment or process, thus it is highly important to identify and classify diverse defect patterns accurately. However, in practice, there exists a serious class imbalance problem, that is, the number of the defective dies on semiconductor wafer maps is usually much smaller than that of the non-defective dies. In various machine learning applications, a typical classification algorithm is, however, developed under the assumption that the number of instances for each class is nearly balanced. If the conventional classification algorithm is applied to a class imbalanced dataset, it may lead to incorrect classification results and degrade the reliability of the classification algorithm. In this research, we consider the semiconductor wafer defect bin data combined with wafer warpage information and propose a new hybrid resampling algorithm to improve performance of classifiers. From the experimental analysis, we show that the proposed algorithm provides better classification performance compared to other data preprocessing methods regardless of classification models.     

Analysis of Semi-Supervised Text Clustering Algorithm on Marine Data

Semi-supervised clustering improves learning performance as long as it uses a small number of labeled samples to assist un-tagged samples for learning. This paper implements and compares unsupervised and semi-supervised clustering analysis of BOAArgo ocean text data. Unsupervised K-Means and Affinity Propagation (AP) are two classical clustering algorithms. The Election-AP algorithm is proposed to handle the final cluster number in AP clustering as it has proved to be difficult to control in a suitable range. Semi-supervised samples thermocline data in the BOA-Argo dataset according to the thermocline standard definition, and use this data for semi-supervised cluster analysis. Several semi-supervised clustering algorithms were chosen for comparison of learning performance: Constrained-K-Means, Seeded-K-Means, SAP (Semi-supervised Affinity Propagation), LSAP (Loose Seed AP) and CSAP (Compact Seed AP). In order to adapt the single label, this paper improves the above algorithms to SCKM (improved Constrained-K-Means), SSKM (improved Seeded-K-Means), and SSAP (improved Semi-supervised Affinity Propagationg) to perform semi-supervised clustering analysis on the data. A DSAP (Double Seed AP) semi-supervised clustering algorithm based on compact seeds is proposed as the experimental data shows that DSAP has a better clustering effect. The unsupervised and semi-supervised clustering results are used to analyze the potential patterns of marine data.     

Yield prediction via spatial modeling of clustered defect counts across a wafer map

In this paper we propose spatial modeling approaches for clustered defects observed using an Integrated Circuit (IC) wafer map. We use the spatial location of each IC chip on the wafer as a covariate for the corresponding defect count listed in the wafer map. Our models are based on a Poisson regression, a negative binomial regression, and Zero-Inflated Poisson (ZIP) regression. Analysis results indicate that yield prediction can be greatly improved by capturing the spatial distribution of defects across the wafer map. In particular, the ZIP model with spatial covariates shows considerable promise as a yield model since it additionally models zero-defective chips. The modeling procedures are tested using a practical example.     

Multi-step ART1 algorithm for recognition of defect patterns on semiconductor wafers

The integrated circuits (ICs) on wafers are highly vulnerable to defects generated during the semiconductor manufacturing process. The spatial patterns of locally clustered defects are likely to contain information related to the defect generating mechanism. For the purpose of yield management, we propose a multi-step adaptive resonance theory (ART1) algorithm in order to accurately recognise the defect patterns scattered over a wafer. The proposed algorithm consists of a new similarity measure, based on the p-norm ratio and run-length encoding technique and pre-processing procedure: the variable resolution array and zooming strategy. The performance of the algorithm is evaluated based on the statistical models for four types of simulated defect patterns, each of which typically occurs during fabrication of ICs: random patterns by a spatial homogeneous Poisson process, ellipsoid patterns by a multivariate normal, curvilinear patterns by a principal curve, and ring patterns by a spherical shell. Computational testing results show that the proposed algorithm provides high accuracy and robustness in detecting IC defects, regardless of the types of defect patterns residing on the wafer.     

A Direct Data-Cluster Analysis Method Based on Neutrosophic Set Implication

Raw data are classified using clustering techniques in a reasonable manner to create disjoint clusters. A lot of clustering algorithms based on specific parameters have been proposed to access a high volume of datasets. This paper focuses on cluster analysis based on neutrosophic set implication, i.e., a k-means algorithm with a threshold-based clustering technique. This algorithm addresses the shortcomings of the k-means clustering algorithm by overcoming the limitations of the threshold-based clustering algorithm. To evaluate the validity of the proposed method, several validity measures and validity indices are applied to the Iris dataset (from the University of California, Irvine, Machine Learning Repository) along with k-means and threshold-based clustering algorithms. The proposed method results in more segregated datasets with compacted clusters, thus achieving higher validity indices. The method also eliminates the limitations of threshold-based clustering algorithm and validates measures and respective indices along with k-means and thresholdbased clustering algorithms.     

Automatic Data Clustering Based Mean Best Artificial Bee Colony Algorithm

Fuzzy C-means (FCM) is a clustering method that falls under unsupervised machine learning. The main issues plaguing this clustering algorithm are the number of the unknown clusters within a particular dataset and initialization sensitivity of cluster centres. Artificial Bee Colony (ABC) is a type of swarm algorithm that strives to improve the members’ solution quality as an iterative process with the utilization of particular kinds of randomness. However, ABC has some weaknesses, such as balancing exploration and exploitation. To improve the exploration process within the ABC algorithm, the mean artificial bee colony (MeanABC) by its modified search equation that depends on solutions of mean previous and global best is used. Furthermore, to solve the main issues of FCM, Automatic clustering algorithm was proposed based on the mean artificial bee colony called (AC-MeanABC). It uses the MeanABC capability of balancing between exploration and exploitation and its capacity to explore the positive and negative directions in search space to find the best value of clusters number and centroids value. A few benchmark datasets and a set of natural images were used to evaluate the effectiveness of AC-MeanABC. The experimental findings are encouraging and indicate considerable improvements compared to other state-of-the-art approaches in the same domain.     

An Adaptive Anomaly Detection Algorithm Based on CFSFDP

CFSFDP (Clustering by fast search and find of density peak) is a simple and crisp density clustering algorithm. It does not only have the advantages of density clustering algorithm, but also can find the peak of cluster automatically. However, the lack of adaptability makes it difficult to apply in intrusion detection. The new input cannot be updated in time to the existing profiles, and rebuilding profiles would waste a lot of time and computation. Therefore, an adaptive anomaly detection algorithm based on CFSFDP is proposed in this paper. By analyzing the influence of new input on center, edge and discrete points, the adaptive problem mainly focuses on processing with the generation of new cluster by new input. The improved algorithm can integrate new input into the existing clustering without changing the original profiles. Meanwhile, the improved algorithm takes the advantage of multi-core parallel computing to deal with redundant computing. A large number of experiments on intrusion detection on Android platform and KDDCUP 1999 show that the improved algorithm can update the profiles adaptively without affecting the original detection performance. Compared with the other classical algorithms, the improved algorithm based on CFSFDP has the good basic performance and more room of improvement.     

An Asynchronous Clustering and Mobile Data Gathering Schema Based on Timer Mechanism in Wireless Sensor Networks

Recently, Wireless sensor networks (WSNs) have become very popular research topics which are applied to many applications. They provide pervasive computing services and techniques in various potential applications for the Internet of Things (IoT). An Asynchronous Clustering and Mobile Data Gathering based on Timer Mechanism (ACMDGTM) algorithm is proposed which would mitigate the problem of “hot spots” among sensors to enhance the lifetime of networks. The clustering process takes sensors’ location and residual energy into consideration to elect suitable cluster heads. Furthermore, one mobile sink node is employed to access cluster heads in accordance with the data overflow time and moving time from cluster heads to itself. Related experimental results display that the presented method can avoid long distance communicate between sensor nodes. Furthermore, this algorithm reduces energy consumption effectively and improves package delivery rate.     

Genetic-Frog-Leaping Algorithm for Text Document Clustering

In recent years, the volume of information in digital form has increased tremendously owing to the increased popularity of the World Wide Web. As a result, the use of techniques for extracting useful information from large collections of data, and particularly documents, has become more necessary and challenging. Text clustering is such a technique; it consists in dividing a set of text documents into clusters (groups), so that documents within the same cluster are closely related, whereas documents in different clusters are as different as possible. Clustering depends on measuring the content (i.e., words) of a document in terms of relevance. Nevertheless, as documents usually contain a large number of words, some of them may be irrelevant to the topic under consideration or redundant. This can confuse and complicate the clustering process and make it less accurate. Accordingly, feature selection methods have been employed to reduce data dimensionality by selecting the most relevant features. In this study, we developed a text document clustering optimization model using a novel genetic frog-leaping algorithm that efficiently clusters text documents based on selected features. The proposed approach is based on two metaheuristic algorithms: a genetic algorithm (GA) and a shuffled frog-leaping algorithm (SFLA). The GA performs feature selection, and the SFLA performs clustering. To evaluate its effectiveness, the proposed approach was tested on a well-known text document dataset: the “20Newsgroup” dataset from the University of California Irvine Machine Learning Repository. Overall, after multiple experiments were compared and analyzed, it was demonstrated that using the proposed algorithm on the 20Newsgroup dataset greatly facilitated text document clustering, compared with classical K-means clustering. Nevertheless, this improvement requires longer computational time.     

OLED显示屏表面缺陷自动检测方法

目的 为了解决OLED显示屏表面周期性纹理背景和缺陷边界模糊、对比度低的特征导致其表面缺陷检测困难的问题,开展OLED显示屏表面缺陷自动检测方法研究.方法 对OLED显示屏图像进行奇异值分解,选择前2个较大的奇异值重构图像纹理背景,对原图像和重构图像进行差分运算,获得残差图像.将残差图像像素随机赋予初始隶属度值,采用模糊C均值聚类法获得像素最终隶属度值.根据隶属度大小,将残差图像像素聚成2类,并从残差图像中准确地分割缺陷.结果 选取较大的2个奇异值可以有效地重构OLED显示屏的周期性纹理背景;模糊C均值聚类法分割缺陷获得的区域灰度一致性(U)平均值为0.9846.结论 基于奇异值分解的背景重构方法可以有效地检测OLED显示屏表面缺陷;与分水岭法和Otsu方法相比,模糊C均值聚类可以准确地分割模糊边界的缺陷区域.     

Unstructured Oncological Image Cluster Identification Using Improved Unsupervised Clustering Techniques

This paper presents, a new approach of Medical Image Pixels Clustering (MIPC), aims to trace the dissimilar patterns over the Magnetic Resonance (MR) image through the process of automatically identify the appropriate number of distinct clusters based on different improved unsupervised clustering schemes for enrichment, pattern predication and deeper investigation. The proposed MIPC consists of two stages: clustering and validation. In the clustering stage, the MIPC automatically identifies the distinct number of dissimilar clusters over the gray scale MR image based on three different improved unsupervised clustering schemes likely improved Limited Agglomerative Clustering (iLIAC), Dynamic Automatic Agglomerative Clustering (DAAC) and Optimum N-Means (ONM). In the second stage, the performance of MIPC approach is estimated by measuring Intra intimacy and Intra contrast of each individual cluster in the result of MR image based on proposed validation method namely Shreekum Intra Cluster Measure (SICM). Experimental results show that the MIPC approach is better suited for automatic identification of highly relative dissimilar clusters over the MR cancer images with higher Intra closeness and lower Intra contrast based on improved unsupervised clustering schemes.     

Classification of Adversarial Attacks Using Ensemble Clustering Approach

As more business transactions and information services have been implemented via communication networks, both personal and organization assets encounter a higher risk of attacks. To safeguard these, a perimeter defence like NIDS (network-based intrusion detection system) can be effective for known intrusions. There has been a great deal of attention within the joint community of security and data science to improve machine-learning based NIDS such that it becomes more accurate for adversarial attacks, where obfuscation techniques are applied to disguise patterns of intrusive traffics. The current research focuses on non-payload connections at the TCP (transmission control protocol) stack level that is applicable to different network applications. In contrary to the wrapper method introduced with the benchmark dataset, three new filter models are proposed to transform the feature space without knowledge of class labels. These ECT (ensemble clustering based transformation) techniques, i.e., ECT-Subspace, ECT-Noise and ECT-Combined, are developed using the concept of ensemble clustering and three different ensemble generation strategies, i.e., random feature subspace, feature noise injection and their combinations. Based on the empirical study with published dataset and four classification algorithms, new models usually outperform that original wrapper and other filter alternatives found in the literature. This is similarly summarized from the first experiment with basic classification of legitimate and direct attacks, and the second that focuses on recognizing obfuscated intrusions. In addition, analysis of algorithmic parameters, i.e., ensemble size and level of noise, is provided as a guideline for a practical use.     

Information Theoretic Weighted Fuzzy Clustering Ensemble

In order to improve performance and robustness of clustering, it is proposed to generate and aggregate a number of primary clusters via clustering ensemble technique. Fuzzy clustering ensemble approaches attempt to improve the performance of fuzzy clustering tasks. However, in these approaches, cluster (or clustering) reliability has not paid much attention to. Ignoring cluster (or clustering) reliability makes these approaches weak in dealing with low-quality base clustering methods. In this paper, we have utilized cluster unreliability estimation and local weighting strategy to propose a new fuzzy clustering ensemble method which has introduced Reliability Based weighted co-association matrix Fuzzy C-Means (RBFCM), Reliability Based Graph Partitioning (RBGP) and Reliability Based Hyper Clustering (RBHC) as three new fuzzy clustering consensus functions. Our fuzzy clustering ensemble approach works based on fuzzy cluster unreliability estimation. Cluster unreliability is estimated according to an entropic criterion using the cluster labels in the entire ensemble. To do so, the new metric is defined to estimate the fuzzy cluster unreliability; then, the reliability value of any cluster is determined using a Reliability Driven Cluster Indicator (RDCI). The time complexities of RBHC and RBGP are linearly proportional with the number of data objects. Performance and robustness of the proposed method are experimentally evaluated for some benchmark datasets. The experimental results demonstrate efficiency and suitability of the proposed method.     

基于改进蝙蝠优化自确定的模糊C-均值聚类算法

针对模糊C-均值聚类算法敏感于初始聚类中心及聚类收敛慢、聚类数目手动设定等缺陷,提出了基于改进蝙蝠优化自确定的模糊C-均值聚类算法。该算法是基于密度峰值综合衡量聚类中心外围数据密集程度和聚类中心间距离,自动确定聚类中心和聚类数目,以此作为改进蝙蝠算法的初始中心;在原始蝙蝠算法中引入Levy飞行特征加强算法跳出局部最优能力;使用Powell局部搜索加快算法的收敛,利用改进的蝙蝠种群进行种群寻优,并将最优蝙蝠位置作为聚类C-均值新聚类中心,进行模糊聚类,以此循环交叉迭代多次最终获得聚类结果。将基于改进蝙蝠优化自确定的模糊C-均值聚类算法与其它两种聚类算法在标准数据集上进行仿真对比,实验结果表明:与其它两种算法相比,该算法收敛速度快、误差率低。     

A Novel Defect Inspection Method for Semiconductor Wafer Based on Magneto-Optic Imaging

The defects of semiconductor wafer may be generated from the manufacturing processes. A novel defect inspection method of semiconductor wafer is presented in this paper. The method is based on magneto-optic imaging, which involves inducing eddy current into the wafer under test, and detecting the magnetic flux associated with eddy current distribution in the wafer by exploiting the Faraday rotation effect. The magneto-optic image being generated may contain some noises that degrade the overall image quality, therefore, in this paper, in order to remove the unwanted noise present in the magneto-optic image, the image enhancement approach using multi-scale wavelet is presented, and the image segmentation approach based on the integration of watershed algorithm and clustering strategy is given. The experimental results show that many types of defects in wafer such as hole and scratch etc. can be detected by the method proposed in this paper.