• KIPS Transactions on Software and Data Engineering
• /
• v.2 no.10
• /
• pp.731-738
• /
• 2013

We analyze public opinion via a sentiment analysis of tweets collected by using recent topic keywords extracted from newspaper articles. Newspaper articles collected within a certain period of time are clustered by using K-means algorithm and topic keywords for each cluster are extracted by using term frequency. A sentiment analyzer learned by a machine learning method can classify tweets according to their polarity values. We have an assumption that tweets collected by using these topic keywords deal with the same topics as the newspaper articles mentioned if the tweets and the newspapers are generated around the same time. and we tried to verify the validity of this assumption.

• Journal of KIISE:Databases
• /
• v.37 no.2
• /
• pp.71-81
• /
• 2010

The problem of finding clusters is widely used in numerous applications, such as pattern recognition, image analysis, market analysis. The important factors that decide cluster quality are the similarity measure and the number of attributes. Similarity measures should be defined with respect to the data types. Existing similarity measures are well applicable to numerical attribute values. However, those measures do not work well when the data is described by categorical attributes, that is, when no inherent similarity measure between values. In high dimensional spaces, conventional clustering algorithms tend to break down because of sparsity of data points. To overcome this difficulty, a subspace clustering approach has been proposed. It is based on the observation that different clusters may exist in different subspaces. In this paper, we propose a new similarity measure for clustering of high dimensional categorical data. The measure is defined based on the fact that a good clustering is one where each cluster should have certain information that can distinguish it with other clusters. We also try to capture on the attribute dependencies. This study is meaningful because there has been no method to use both of them. Experimental results on real datasets show clusters obtained by our proposed similarity measure are good enough with respect to clustering accuracy.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2011.01a
• /
• pp.85-88
• /
• 2011

Fuzzy C-Means (FCM) 알고리듬은 가장 널리 사용되는 군집화 알고리듬 중 하나로 다양한 응용 분야에서 사용되고 있다. 하지만 FCM은 여러 가지 문제점을 가지고 있으며 초기 원형 설정이 그 중 하나이다. FCM은 국부 최적해에 수렴하므로 초기 원형 설정에 따라 클러스터링 결과가 달라진다. 이 논문에서는 이러한 FCM의 초기 원형 설정 문제를 개선하기 위하여 커널밀도 추정 (kernel density estimation) 기법을 활용하는 방법을 제안한다. 제안한 방법에서는 먼저 커널 밀도 추정을 수행한 후 밀도가 높은 지역에 클러스터의 초기 원형을 설정하고 원형이 설정된 영역의 밀도를 감소시키는 과정을 반복함으로써 효율적으로 초기 원형을 설정할 수 있다. 제안된 방법이 일반적으로 사용되는 무작위 초기화 방법에 비해 효율적이라는 사실은 실험결과를 통해 확인할 수 있다.

• Journal of the Institute of Convergence Signal Processing
• /
• v.10 no.1
• /
• pp.72-79
• /
• 2009

This paper describes the performance evaluation of NHD(nonhomogeneity detector) for STAP(space-time adaptive processing) airborne radar according to various normalization methods in the nonhomogeneous clutter environment. In practice, the clutter can be characterized as random variation signals, because it sometimes includes signals with very large magnitude like impulsive signal due to the system environment. The received interference signals are composed of homogeneous and nonhomogeneous data. In this situation, NHB is needed to maintain the STAP performance. The normalization using the NHD result is an effective method for removing the nonhomogeneous data. The optimum normalization can be performed by a representative value considered with a characteristic of the given data, so we propose the K-means clustering algorithm. The characteristic of random variation data due to nonhomogeneous clutters can be considered by the number of clusters, and then the representative value for selecting the homogeneous data is determined in the clustering result. In order to reflect a characteristic of the nonstationary interference data, we also investigate the algorithm for a calculation of the proper number of clusters. Through our simulations, we verified that the K-means clustering algorithm has very superior normalization and target detection performances compared with the previous introduced normalization methods.

• Journal of the Korean Institute of Electrical and Electronic Material Engineers
• /
• v.20 no.10
• /
• pp.901-906
• /
• 2007

In this study, we measured the partial discharge phenomenon of inside the closed switchgear, using ultra wide band antenna. The characteristics of $\Phi-q-n$ in the normal state are stable, and confirmed at less than 0.01, but in proceeding states, about 2 times larger. And in the abnormal state, it grew hundreds of times larger compared with normal state. According to K-means analysis, if slant of discharge characteristics is a straight line close to "0" and standard deviation is small, it is in a normal state. However if we can find a peak from K-means clusters and standard deviation to be large, it is in an abnormal state.

• Proceedings of the Korean Information Science Society Conference
• /
• 2002.10d
• /
• pp.277-279
• /
• 2002

웹 로그 기반의 웹 사용 마이닝은 명시적 평가 의존, 확장성 결여, 그리고 다차원 및 희박한 데이터에 성능이 떨어지는 협력적 여과의 문제를 다소 해결할 수 있다. 그러나 k-Means 군집화 방법으로 생성된 군집속 유사 사용자 이동 패턴으로는 클러스터속 사용자 전체의 선호도를 표현할 수 없으므로 사용자 이동 패턴인 트랜잭션들로부터 사용 프로파일을 유도해야 한다. 본 논문에서는 유사 군집 사용자들의 관심과 기호를 표현할 수 있도록 클러스터 내부 데이타로부터 평균 가중치 및 빈발 지지도 임계값을 사용하여 개선된 사용 프로파일을 생성하고 실험 데이터를 통한 예측력과 추천에 대한 성능을 평가한다.

• The Korean Journal of Applied Statistics
• /
• v.26 no.6
• /
• pp.999-1007
• /
• 2013

This research shows several types of moving pictures from the data: 1) the word cloud of Korean texts, 2) the heat map of n ${\times}$ p matrices, 3) the moving image of p ${\times}$ p scatterplot matrix, 4) the local projective display of k clusters (Huh and Lee, 2012). Moving pictures may reveal the hidden information and beauty of the datasets and ignite the curiosity of information consumers. Video files are attached.

• Journal of Practical Engineering Education
• /
• v.14 no.3
• /
• pp.565-572
• /
• 2022

Card sorting is a useful data collection method for understanding users' perceptions of relationships between items. In general, card sorting is an intuitive and cost-effective technique that is very useful for user research and evaluation. In this study, the core competencies of each field were used as competency cards used in the next stage of card sorting for course development, and the clustering results were derived by applying the K-means algorithm to cluster the results. As a result of card sorting, competency clustering for core competencies for each occupation in each field was verified based on Participant-Centric Analysis (PCA). For the number of core competency cards for each occupation, the number of participants who agreed appropriately for clustering and the degree of card similarity were derived compared to the number of sorting participants.

• Journal of KIISE:Software and Applications
• /
• v.35 no.9
• /
• pp.572-587
• /
• 2008

The Self-organizing Feature Map(SOFM) that is one of unsupervised neural networks is a very powerful tool for data clustering and visualization in high-dimensional data sets. Although the SOFM has been applied in many engineering problems, it needs to cluster similar weights into one class on the trained SOFM as a post-processing, which is manually performed in many cases. The traditional clustering algorithms, such as t-means, on the trained SOFM however do not yield satisfactory results, especially when clusters have arbitrary shapes. This paper proposes automatic clustering on trained SOFM, which can deal with arbitrary cluster shapes and be globally optimized by graph cuts. When using the graph cuts, the graph must have two additional vertices, called terminals, and weights between the terminals and vertices of the graph are generally set based on data manually obtained by users. The Proposed method automatically sets the weights based on mode-seeking on a distance matrix. Experimental results demonstrated the effectiveness of the proposed method in texture segmentation. In the experimental results, the proposed method improved precision rates compared with previous traditional clustering algorithm, as the method can deal with arbitrary cluster shapes based on the graph-theoretic clustering.

• Journal of the Korean BIBLIA Society for library and Information Science
• /
• v.31 no.3
• /
• pp.79-99
• /
• 2020

The purpose of this study is to investigate the model of cluster analysis techniques for grouping public libraries and analyze their characteristics. Statistical data of public libraries of the National Library Statistics System were used, and three models of cluster analysis were applied. As a result of the study, cluster analysis was conducted based on the size of public libraries, and it was largely divided into two clusters. The size of the cluster was largely skewed to one side. For grouping based on size, the ward method of hierarchical cluster analysis and the k-means cluster analysis model were suitable. Three suggestions were presented as implications of the grouping method of public libraries. First, it is necessary to collect library service-related data in addition to statistical data. Second, an analysis model suitable for the data set to be analyzed must be applied. Third, it is necessary to study the possibility of using cluster analysis techniques in various fields other than library grouping.