• 식물분류학회지
• /
• 제49권1호
• /
• pp.13-27
• /
• 2019

Numerical taxonomy is employed to determine the phenetic proximity of the Egyptian taxa belonging to the genus Ononis L. A classical clustering analysis and a principal component analysis (PCA) were used to separate 57 macro- and micromorphological characters in order to circumscribe 11 taxa of Ononis. A clustering analysis using the unweighted pair-group method with the arithmetic means (UPGMA) method gives the highest co-phenetic correlation. Results from clustering and PCA revealed the segregation of five groups. Our results are in line, to some certain degree, with the traditional sub-sectional concept, as can be seen in the grouping of the representative members of the subsections Diffusae and Mittisimae together and the representative members of the subsections Viscosae and Natrix. The phenetic uniqueness of Ononis variegata and O. reclinata subsp. mollis was formally established. However, our findings contradict the classic sectional concept; this opinion was suggested earlier in previous phylogenetic circumscriptions of the genus. The most useful characters that provide taxonomic clarity were discussed.

• 한국국방경영분석학회지
• /
• 제6권2호
• /
• pp.89-127
• /
• 1980

The multivariate analysis techniques of cluster analysis are examined in this article. The theory and applications of the techniques and computer software concerning these techniques are discussed and sample jobs are included. A hierarchical cluster analysis algorithm, available in the IMSL software package, is applied to a set of data extracted from a group of subjects for the purpose of partitioning a collection of 26 attributes of a weapon system into six clusters of superattributes. A nonhierarchical clustering procedure were applied to a collection of data of tanks considering of twenty-four observations of ten attributes of tanks. The cluster analysis shows that the tanks cluster somewhat naturally by nationality. The principal componant analysis and the discriminant analysis show that tank weight is the single most important discriminator among nationality although they are not shown in this article because of the space restriction. This is a part of thesis for master's degree in operations research.

• 한국지능시스템학회:학술대회논문집
• /
• 한국퍼지및지능시스템학회 1998년도 The Third Asian Fuzzy Systems Symposium
• /
• pp.453-458
• /
• 1998

In this paper, a new approach to modeling of nonlinear systems using fuzzy theory is presented. So as to handle a variety of nonlinearity and reflect the degree of confidence in the informations about system, we combine multiple model method with hierarchical prioritized structure. The mountain clustering technique is used in partition of system, and TSK rule structure is adopted to form the fuzzy rules. Back propagation algorithm is used for learning parameters in the rules. Computer simulations are performed to verify the effectiveness of the proposed method. It is useful for the treatment fo the nonlinear system of which the quantitative math-approach is difficult.

• 한국정보통신설비학회:학술대회논문집
• /
• 한국정보통신설비학회 2008년도 정보통신설비 학술대회
• /
• pp.17-20
• /
• 2008

A clustering scheme for ad hoc networks is aimed at managing a number of mobile devices by utilizing hierarchical structure of the networks. In order to construct and maintain an effective hierarchical structure in ad hoc networks where mobile devices may move at high mobility, the following requirements must be satisfied. The role of each mobile device for the hierarchical structure is adaptive to dynamic change of the topology of the ad hoc networks. The role of each mobile device should thus change autonomously based on the local information. The overhead for management of the hierarchical structure is small. The number of mobile devices in each cluster should thus be almost equivalent. This paper proposes an adaptive multihop clustering scheme for highly mobile ad hoc networks. The results obtained by extensive simulation experiments show that the proposed scheme does not depend on mobility and node degree of mobile devices in the ad hoc network, which satisfy the above requirements.

• 한국전기전자재료학회논문지
• /
• 제20권11호
• /
• pp.959-964
• /
• 2007

To investigate the influence of partial discharge(PD) distribution characteristics due to various defects on the power cable joints interface, we used the K-means clustering method. As the result of PD number(n) distribution analyzing on $\Phi-n$ graph, the phase angle($\Phi$) of cluster centroid shifted to $0^{\circ}\;and\;180^{\circ}$ increasing with applying voltage. It was confirmed that the PD quantify(q) and euclidean distance of centroid were increased with applying voltage from the centroid distribution analyzing of $\Phi-q$ plane. The dispersion degree was increased with calculated standard deviation of the $\Phi-q$ cluster centroid. The PD number and mean value on $\Phi-q$ graph were some different by electric field concentration with defect types.

• 천문학회지
• /
• 제29권spc1호
• /
• pp.19-21
• /
• 1996

We apply topological measures of clustering such as percolation and genus curves (PC & GC) and shape statistics to a set of scale free N-body simulations of large scale structure. Both genus and percolation curves evolve with time reflecting growth of non-Gaussianity in the N-body density field. The amplitude of the genus curve decreases with epoch due to non-linear mode coupling, the decrease being more noticeable for spectra with small scale power. Plotted against the filling factor GC shows very little evolution - a surprising result, since the percolation curve shows significant evolution for the same data. Our results indicate that both PC and GC could be used to discriminate between rival models of structure formation and the analysis of CMB maps. Using shape sensitive statistics we find that there is a strong tendency for objects in our simulations to be filament-like, the degree of filamentarity increasing with epoch.

• ETRI Journal
• /
• 제40권6호
• /
• pp.788-793
• /
• 2018

3D reconstruction of urban architecture, land, and roads is an important part of building a "digital city." Unmanned aerial vehicles (UAVs) are gradually replacing other platforms, such as satellites and aircraft, in geographical image collection; the reason for this is not only lower cost and higher efficiency, but also higher data accuracy and a larger amount of obtained information. Recent 3D reconstruction algorithms have a high degree of automation, but their computation time is long and the reconstruction models may have many voids. This paper decomposes the object into multiple regional parallel reconstructions using the clustering principle, to reduce the computation time and improve the model quality. It is proposed to detect the planar area under low resolution, and then reduce the number of point clouds in the complex area.

• 한국콘텐츠학회:학술대회논문집
• /
• 한국콘텐츠학회 2004년도 추계 종합학술대회 논문집
• /
• pp.389-394
• /
• 2004

본 논문에서는 디자인 패턴을 분류하기 위해 패턴구조의 특성을 가지고 분류하였다. 그리고 클러스터링에 의한 분류는 패싯 분류에 의한 방법보다 높은 정확도를 보여주었다. 따라서 자동화된 분류방법인 클러스터링 알고리즘을 사용하여 디자인 패턴을 분류하는 것이 효과적이라 할 수 있다. 디자인 패턴의 분류는 검색 시 유사한 패턴들이 같은 카테고리에 저장이 되므로 유사패턴을 비교하여 사용할 수 있으며, 패턴 클러스터링에 의해 분류되고, 패턴의 링크정보를 이용하여 저장하므로 저장소를 효율적으로 관리할 수 있다.

• Journal of Electrical Engineering and Technology
• /
• 제13권2호
• /
• pp.998-1007
• /
• 2018

The advent of Wireless Sensor Networks (WSN) has led to their use in numerous applications. Sensors are autonomous in nature and are constrained by limited resources. Designing an autonomous topology with criteria for economic and energy conservation is considered a major goal in WSN. The proposed honey-hive clustering consumes minimum energy and resources with minimal transmission delay compared to the existing approaches. The honey-hive approach consists of two phases. The first phase is an Intra-Cluster Min-Max Discrepancy (ICMMD) analysis, which is based on the local honey-hive data gathering technique and the second phase is Inter-Cluster Frequency Matching (ICFM), which is based on the global optimal data aggregation. The proposed data aggregation mechanism increases the optimal connectivity range of the sensor node to a considerable degree for inter-cluster and intra-cluster coverage with an improved optimal energy conservation.

• 지능정보연구
• /
• 제17권1호
• /
• pp.111-125
• /
• 2011

클러스터링(Clustering)은 유사한 문서나 데이터를 묶어 군집화해주는 프로세스이다. 클러스터링은 문서들을 대표하는 개념별로 그룹화함으로써 사용자가 자신이 원하는 주제의 문서를 찾기 위해 모든 문서를 검사할 필요가 없도록 도와준다. 이를 위해 유사한 문서를 찾아 그룹화하고, 이 그룹의 대표되는 개념을 도출하여 표현해주는 기법이 요구된다. 이 상황에서 문제점으로 대두되는 것이 복합 개념(Complex Concept)의 탐지이다. 복합 개념은 서로 다른 개념의 여러 클러스터에 속하는 중복 개념이다. 기존의 클러스터링 방법으로는 문서를 클러스터링할 때 동일한 레벨에 있는 서로 다른 개념의 클러스터에 속하는 중복된 복합 개념의 클러스터를 찾아서 표현할 수가 없었고, 또한 복합 개념과 각 단순 개념(Simple Concept) 사이의 의미적 계층 관계를 제대로 검증하기가 어려웠다. 본 논문에서는 기존 클러스터링 방법의 문제점을 해결하여 복합 개념을 쉽게 찾아 표현하는 방법을 제안한다. 기존의 계층적 클러스터링 알고리즘을 변형하여 동일 레벨에서 중복을 허용하는 계층적 클러스터링(Hierarchical Overlapping Clustering, HOC) 알고리즘을 개발하였다. HOC 알고리즘은 문서를 클러스터링하여 그 결과를 트리가 아닌 개념 중복이 가능한 Lattice 계층 구조로 표현함으로써 이를 통해 여러 개념이 중복된 복합 개념을 탐지할 수 있었다. HOC 알고리즘을 이용해 생성된 각 클러스터의 개념이 제대로 된 의미적인 계층 관계로 표현되었는지는 특징 선택(Feature Selection) 방법을 적용하여 검증하였다.