• The International Journal of Costume Culture
• /
• v.4 no.2
• /
• pp.77-85
• /
• 2001

The purpose of this study was to classify the somatotype around a upper body of 30's men. The subjects were 202 working men aged from 30 to 39 and the data of 33 items including computed items were analysed by factor analysis and cluster analysis. Re results were as follows: As a factor of somatotype in evaluating males in 30's, the horizontal area represented the chest circumference at scye and the breadth items, the vortical region indicated hit length posterior, front length, back length, the breadth difference and the length difference. The somatotype by cluster analysis was classified with 3 type. Type I as the Roher's index 1.21 indicating the smallest in the circumference and weight item was classified as the thin and long featuring bending somatotype. Type 2 with the Rohrer's index 1.35 showing the mid-group between type 1 and 3 had the highest distribution rate as the balanced featuring the standard somatotype. Type 3 as the rohrer's index 1.40 was the largest physical condition group in the obesity featuring the turning over somatotype.

• Communications for Statistical Applications and Methods
• /
• v.22 no.1
• /
• pp.55-67
• /
• 2015

An important problem in cluster analysis is the selection of variables that define cluster structure that also eliminate noisy variables that mask cluster structure; in addition, outlier detection is a fundamental task for cluster analysis. Here we provide an automated K-means clustering process combined with variable selection and outlier identification. The Automated K-means clustering procedure consists of three processes: (i) automatically calculating the cluster number and initial cluster center whenever a new variable is added, (ii) identifying outliers for each cluster depending on used variables, (iii) selecting variables defining cluster structure in a forward manner. To select variables, we applied VS-KM (variable-selection heuristic for K-means clustering) procedure (Brusco and Cradit, 2001). To identify outliers, we used a hybrid approach combining a clustering based approach and distance based approach. Simulation results indicate that the proposed automated K-means clustering procedure is effective to select variables and identify outliers. The implemented R program can be obtained at http://www.knou.ac.kr/~sskim/SVOKmeans.r.

• Journal of the Korean Society of Fisheries and Ocean Technology
• /
• v.50 no.4
• /
• pp.530-541
• /
• 2014

The dredge gear is dragged along the bottom of the sea to catch targeted edible bottom dwelling species. Species composition and ecological index of the catches of dredge were estimated around Gangneung coastal fishing ground by dredge with different mesh size and tooth space from July to December 2013. Eight different types of dredge including four different tooth space (24.7 mm, 29.9 mm, 34.9 mm, 40.1 mm) and four different mesh size(15.5 mm, 32.7 mm, 51.1 mm, 60.0 mm) were used in the experiment. During the experiment, total catches were collected 31 species as sipunculida 1 species, mollusca 13 species, annelida 3 species, arthropoda 8 species, echinodermata 4 species and others 2 species. The dominant genus were mollusca and echinodermata while the dominant species were Megangulus venulosus, Pseudocardium sachalinensis, Schaphechinus brevis. The richness index was ranged 1.29-1.72, evenness index was 0.6-0.65 and diversity index was 1.65-1.83 according to the tooth space and mesh size of dredge. Richness index, diversity index were high at tooth space 34.9 mm dredge and ecological index showed decreasing tendency with the increasing of mesh size of dredge. Cluster and MDS analysis, based on a Bray-Curtis and similarity matrix of fourth root transformed data of number of species and wet weight, showed division into four different groups as four different tooth space (Group A), four different mesh size Group B (51.1 mm, 60.0 mm), Group C (32.7 mm) and Group D (15.5 mm).

• Journal of the Korean Association of Geographic Information Studies
• /
• v.10 no.4
• /
• pp.75-86
• /
• 2007

The subjects were fifteen dong at downtown of Busan. LQ index and cluster analysis were used to research space functions of downtown in both years, that is to say, 2000 and 2005. At the analysis of LQ index in 2000, the secondary industries were specialized at traditional markets as well as large-scaled commercial districts, while the tertiary industries were done at financial business districts. LQ index in 2005 did not make change mostly comparing with the one in 2000: But, main businesses at downtown that belonged to the tertiary industries rapidly dwindled at old downtown to make appearance at Seomyeon of new downtown. Main businesses at old downtown in the past moved to new downtown to dwindle main functions at old downtown. The cluster analysis was done by using LQ index to classify into three clusters. The first cluster was old downtown that functions of downtown dwindle, and the second cluster was residence area, and the third cluster was the area where space function at downtown was very much active. The findings were as follow: Firstly, various kinds of urban regeneration plans should be made to control dwindling of old downtown and to establish comprehensive and systematic plans on new downtown. Secondly, downtown space functions could be placed depending upon specialization of each industry so that industries being suitable to the area should be introduced to construct development base.

• Journal of the Korean Society for Library and Information Science
• /
• v.57 no.3
• /
• pp.351-379
• /
• 2023

The goal of this study is to investigate the domestic and international research trends on metaverse related researches. To achieve this goal, a set of 913 journal articles were collected from KCI (Korea Citation Index), 232 articles from WoS (Web of Science), and 277 articles from WoS-CPCI (Conference Proceeding Citation Index). A descriptive analysis shows the number of researches has been increased radically, and the mostly researched subject areas are interdisciplinary, computer science, and education in KCI, business and economics in WoS, and computer science in WoS-CPCI. The co-occurrence network analysis using author keywords revealed that technology related terms such as virtual reality and augmented reality showed high centrality measures in all of the databases, and the cluster analysis resulted in education and metaverse platform related keywords cluster from KCI, bibliometric analysis related keywords cluster from WoS, and all the metaverse technology related keywords cluster from WoS-CPCI.

• Korean Journal of Social Welfare Studies
• /
• no.36
• /
• pp.81-101
• /
• 2008

The purpose of this study is to analyze characteristics of welfare level for the persons with disabilities in Korean local governments. The study adopted multidimensional scaling and cluster analysis. Based on prior studies and comparative importance research, three indicators were extracted from the welfare circumstance index for the disabled. They are the ratio of the registered disabled population, the ratio of the disabled household in poor households, the ratio of dependence on public finance. Also, nine dimensions and twenty seven indicators were extracted from the welfare level index. The dimensions are as follows : Education, income & economic activities support, welfare services infra-structure, health & welfare service support, movement convenience & safety, rights protection, culture, leisure & information accessibility, welfare administration & budget for the disabled. The findings from the welfare circumstance index show that local governments are divided into three groups and all indicators are statistically significant. On the other hand, the findings from the welfare level index, show that local governments are divided into four groups and five indicators are statistically significant. Based on these findings, the study proposes improvement in the disabled welfare level, and balanced development of local governments.

• Journal of Distribution Science
• /
• v.19 no.12
• /
• pp.33-43
• /
• 2021

Purpose: This paper aims to determine features of the relationship between human development, tourism and national brand. Research design, data and methodology: ranking indicators, cluster analysis, K means method, correlation analysis. Results: The analysis covers data for 95 countries for 2019. The number of countries is justified by the availability of comparable data for calculations. A direct relationship between the indicators for the entire sample has been revealed in the result of the correlation analysis. However, this relationship has not been confirmed for the groups of countries that were formed through the cluster analysis. Spearman Rank Order and Kendall Tau Correlations have been calculated for the five obtained clusters. In two of the five clusters, the relationship between the indicators has not been found. A strong negative link between all the indicators has been detected in the cluster with average index values. A strong positive link between TTCI and BSI has been revealed in the group of countries with the best index values. A strong positive link between TTCI and HDI has been found in the group of countries with the worst index values. Conclusions: The analysis demonstrates that there is a relationship between BSI, TTCI and HDI, and while this link is observed for the sample as a whole, it is not homogeneous for groups of countries.

• Journal of Korean Society for Atmospheric Environment
• /
• v.30 no.5
• /
• pp.504-509
• /
• 2014

Twenty-five stations of the urban monitoring network in Seoul were assessed with a focus on surveillance function of the exceedances of 8-hour ozone and 24-hour $PM_{10}$ standards. The two standards were selected because their attainment rates were particularly low. Two hierarchical cluster analyses were performed to group stations with similar atmospheric environments-one using daily highest 8-hour [$O_3+NO_2$], 8-hour $O_3$ concentrations plus corresponding 8-hour $NO_2$ concentrations considering the interconversion of $O_3$ and $NO_2$, and the other using 24-hour $PM_{10}$ concentrations. An index to measure higher concentration and exceedances of the standards was introduced. Within a cluster, sufficiently high score was assigned to the trends station or the station with higher index. Scores for $O_3+NO_2$ and $PM_{10}$ of a given station were added and ranked in the descending order to determine the relative importance.

• Proceedings of the National Institute of Ecology of the Republic of Korea
• /
• v.2 no.3
• /
• pp.144-152
• /
• 2021

Sanankerto is one of pilot projects for tourism villages in Indonesia due to its natural tourism potential with a 24-ha bamboo forest located in Boon Pring Andeman area. However, the distribution of existing bamboo has never been identified or mapped. Thus, the mana gement is facing difficulty in planning and developing tourism potential as well as spatial management in the area. Therefore, the objectives of this study were to identify and analyze the structure of bamboo vegetation in the Boon Pring Tourism village an d to perform vegetation mapping. The type of research was descriptive exploratory with a cluster sampling technique (i.e., a two-stage cluster) covering an area of ± 10 ha. Bamboo vegetation analysis was performed by calculating diversity index (H'), evenness index (E), and Species Richness index (R). Data were collected through observation and interviews with local people and the manager to determine zonation division. Mapping of bamboo vegetation based on zoning was processed into thematic maps using ArcG is 10.3. Micro climatic factors were measured with three replications for each sub -cluster. Data were analyzed descriptively and quantitatively. Nine species of bamboo identified. Diversity, evenness, and species richness indices differed at each location. Activities of local communities, tourists, and manager determined the presence, number, and distribution of bamboo species. These bamboo distribution maps in three zoning (utilization, buffer, and core) can be used by manager for planning and developing natural tourism potential.

• Journal of Ecology and Environment
• /
• v.29 no.4
• /
• pp.365-379
• /
• 2006

Collection of moths in four Gotjawal terrains of Jeju Island was conducted using black light trap, beginning July through September 2005. The insects investigated were classified into 146 species, 15 families and 7 superfamilies, and Noctuoidea appeared to have accounted for 41.1%, or 60 species, which was the largest number among them, followed by Geometroidea. Ercheia niveostrigata was found to have been the dominant species over the entire area. The diversity index showed the highest at Aewol Gotjawal and the lowest at Hangyeong-Andeog Gotjawal. Aewol Gotjawal formed a cluster with Gujwa- Sungsan Gotjawal at the lowest chord distance (0.75). At the higher chord distance of 0.82, Jocheon- Hamdeog Gotjawal fused the cluster of Aewol Gotjawal and Gujwa-Sungsan Gotjawal. Hangyeong-Andeog Gotjawal fused with the rest three terrains, forming a single cluster at the highest chord distance of 0.89.