• Molecules and Cells
• /
• 제25권2호
• /
• pp.279-288
• /
• 2008

The analysis of microarray data is essential for large amounts of gene expression data. In this review we focus on clustering techniques. The biological rationale for this approach is the fact that many co-expressed genes are co-regulated, and identifying co-expressed genes could aid in functional annotation of novel genes, de novo identification of transcription factor binding sites and elucidation of complex biological pathways. Co-expressed genes are usually identified in microarray experiments by clustering techniques. There are many such methods, and the results obtained even for the same datasets may vary considerably depending on the algorithms and metrics for dissimilarity measures used, as well as on user-selectable parameters such as desired number of clusters and initial values. Therefore, biologists who want to interpret microarray data should be aware of the weakness and strengths of the clustering methods used. In this review, we survey the basic principles of clustering of DNA microarray data from crisp clustering algorithms such as hierarchical clustering, K-means and self-organizing maps, to complex clustering algorithms like fuzzy clustering.

• Communications for Statistical Applications and Methods
• /
• 제26권1호
• /
• pp.57-67
• /
• 2019

Income distribution is a major concern in economic theory. In regional economics, it is often of interest to compare income distributions in different regions. Traditional methods often compare the income inequality of different regions by assuming parametric forms of the income distributions, or using summary statistics like the Gini coefficient. In this paper, we propose a nonparametric procedure to test for heterogeneity in income distributions among different regions, and a K-means clustering procedure for clustering income distributions based on energy distance. In simulation studies, it is shown that the energy distance based method has competitive results with other common methods in hypothesis testing, and the energy distance based clustering method performs well in the clustering problem. The proposed approaches are applied in analyzing data from China Health and Nutrition Survey 2011. The results indicate that there are significant differences among income distributions of the 12 provinces in the dataset. After applying a 4-means clustering algorithm, we obtained the clustering results of the income distributions in the 12 provinces.

• Asian Pacific Journal of Cancer Prevention
• /
• 제17권2호
• /
• pp.823-827
• /
• 2016

Determination of the colorectal cancer stage is possible only after surgery based on pathology results. However, sometimes this may prove impossible. The aim of the present study was to determine colorectal cancer stage using three clustering methods based on preoperative clinical findings. All patients referred to the Colorectal Research Center of Shiraz University of Medical Sciences for colorectal cancer surgery during 2006 to 2014 were enrolled in the study. Accordingly, 117 cases participated. Three clustering algorithms were utilized including k-means, hierarchical and fuzzy c-means clustering methods. External validity measures such as sensitivity, specificity and accuracy were used for evaluation of the methods. The results revealed maximum accuracy and sensitivity values for the hierarchical and a maximum specificity value for the fuzzy c-means clustering methods. Furthermore, according to the internal validity measures for the present data set, the optimal number of clusters was two (silhouette coefficient) and the fuzzy c-means algorithm was more appropriate than the k-means clustering approach by increasing the number of clusters.

• Journal of the Korean Statistical Society
• /
• 제31권4호
• /
• pp.519-532
• /
• 2002

K-means clustering is a well-known partitioning method of multivariate observations. Recently, the method is implemented broadly in data mining softwares due to its computational efficiency in handling large data sets. However, it does not yield a suitable visual display of multivariate observations that is important especially in exploratory stage of data analysis. The aim of this study is to develop a K-means clustering method that enables visual display of multivariate observations in a low-dimensional space, for which the projection pursuit method is adopted. We propose a computationally inexpensive and reliable algorithm and provide two numerical examples.

• Journal of the Korean Data and Information Science Society
• /
• 제28권5호
• /
• pp.1133-1144
• /
• 2017

기상자료를 이용한 군집분석은 기상 특성에 근거한 기상 지역의 세분화를 가능하게 하고 군집을 이루는 지형별 기상 특성의 파악을 용이하게 한다. 이때 기상관측자료를 이용한 군집분석은 관측지점의 밀도가 다르기 때문에 우리나라의 기상특성이 고르게 반영되지 못할 수 있다. 반면 수치모델 격자자료는 $5km{\times}5km$ 간격으로 조밀하고 고른 자료의 생산이 가능하므로 우리나라의 기상 특성을 고르게 반영할 수 있다. 본 연구에서는 기온과 강수량의 수치모델 격자자료를 이용하여 군집분석을 수행하고, 그 결과를 바탕으로 기상관측지점에 대한 군집을 결정하였다. 기상 특성이 월별로 상이할 수 있기 때문에 군집분석은 월별로 수행하였으며, K-Means 군집분석 방법의 단점을 보완하고자 계층적 군집분석 방법인 Ward 방법과 결합하여 적용하였다. 그 결과 우리나라 기상관측지점들에 대해 시 공간적으로 세분화된 군집화가 이루어졌다.

• Journal of the Korean Society for Industrial and Applied Mathematics
• /
• 제27권2호
• /
• pp.146-159
• /
• 2023

This paper proposes a hybrid algorithm combining K-means clustering and watershed algorithms for flower segmentation and counting. We use the K-means clustering algorithm to obtain the main colors in a complex background according to the cluster centers and then take a color space transformation to extract pixel values for the hue, saturation, and value of flower color. Next, we apply the threshold segmentation technique to segment flowers precisely and obtain the binary image of flowers. Based on this, we take the Euclidean distance transformation to obtain the distance map and apply it to find the local maxima of the connected components. Afterward, the proposed algorithm adaptively determines a minimum distance between each peak and apply it to label connected components using the watershed segmentation with eight-connectivity. On a dataset of 30 images, the test results reveal that the proposed method is more efficient and precise for the counting of overlapped flowers ignoring the degree of overlap, number of overlap, and relatively irregular shape.

• 한국지능시스템학회논문지
• /
• 제22권1호
• /
• pp.81-86
• /
• 2012

본 논문에서는 전형적인 Linear Discriminant Analysis을 확장시켜 전체 입력공간을 다수의 지역공간으로 분할하고 분할된 공간에 Local Linear Discriminant Analysis 기반으로 하여 패턴 분류 규칙을 설계하는 새로운 방법을 제안한다. 전체 입력공간을 여러 개의 지역공간으로 분할하기 위한 방법으로 unsupervised clustering의 대표적인 방법인 k-Means 클러스터링 기법과 최적화 알고리즘인 차분 진화 연산 알고리즘을 사용한다. 제안된 알고리즘의 성능 평가를 위해 기존의 패턴 분류기와 비교 결과를 제시한다.

• Asia pacific journal of information systems
• /
• 제16권1호
• /
• pp.127-144
• /
• 2006

The K-means algorithm is widely used at the initial stage of data analysis in data mining process, partly because of its low time complexity and the simplicity of practical implementation. Cluster validity indices are used along with the algorithm in order to determine the number of clusters as well as the clustering results of datasets. In this paper, we present a performance comparison of sixteen indices, which are selected from forty indices in literature, while considering their applicability to nonhierarchical clustering algorithms. Data sets used in the experiment are generated based on multivariate normal distribution. In particular, four error types including standardization, outlier generation, error perturbation, and noise dimension addition are considered in the comparison. Through the experiment the effects of varying number of points, attributes, and clusters on the performance are analyzed. The result of the simulation experiment shows that Calinski and Harabasz index performs the best through the all datasets and that Davis and Bouldin index becomes a strong competitor as the number of points increases in dataset.

• 산업경영시스템학회지
• /
• 제37권4호
• /
• pp.239-244
• /
• 2014

The conventional clustering approaches are mostly based on minimizing total dissimilarity of input and output. However, the clustering approach may not be helpful in some cases of clustering decision making units (DMUs) with production feature converting multiple inputs into multiple outputs because it does not care converting functions. Data envelopment analysis (DEA) has been widely applied for efficiency estimation of such DMUs since it has non-parametric characteristics. We propose a new clustering method to identify groups of DMUs that are similar in terms of their input-output profiles. A real world example is given to explain the use and effectiveness of the proposed method. And we calculate similarity value between its result and the result of a conventional clustering method applied to the example. After the efficiency value was added to input of K-means algorithm, we calculate new similarity value and compare it with the previous one.

• Translational and Clinical Pharmacology
• /
• 제25권3호
• /
• pp.147-152
• /
• 2017

This study focused on the role of cytochrome P450 2D6 (CYP2D6) genotypes to predict phenotypes in the metabolism of dextromethorphan. CYP2D6 genotypes and metabolic ratios (MRs) of dextromethorphan were determined in 201 Koreans. Unsupervised clustering algorithms, hierarchical and k-means clustering analysis, and color visualizations of CYP2D6 activity were performed on a subset of 130 subjects. A total of 23 different genotypes were identified, five of which were observed in one subject. Phenotype classifications were based on the means, medians, and standard deviations of the log MR values for each genotype. Color visualization was used to display the mean and median of each genotype as different color intensities. Cutoff values were determined using receiver operating characteristic curves from the k-means analysis, and the data were validated in the remaining subset of 71 subjects. Using the two highest silhouette values, the selected numbers of clusters were three (the best) and four. The findings from the two clustering algorithms were similar to those of other studies, classifying $^*5/^*5$ as a lowest activity group and genotypes containing duplicated alleles (i.e., $CYP2D6^*1/^*2N$) as a highest activity group. The validation of the k-means clustering results with data from the 71 subjects revealed relatively high concordance rates: 92.8% and 73.9% in three and four clusters, respectively. Additionally, color visualization allowed for rapid interpretation of results. Although the clustering approach to predict CYP2D6 phenotype from CYP2D6 genotype is not fully complete, it provides general information about the genotype to phenotype relationship, including rare genotypes with only one subject.