• Journal of Information Processing Systems
• /
• v.20 no.2
• /
• pp.185-199
• /
• 2024

In this paper, an improved automated spectral clustering (IASC) algorithm is proposed to address the limitations of the traditional spectral clustering (TSC) algorithm, particularly its inability to automatically determine the number of clusters. Firstly, a cluster number evaluation factor based on the optimal clustering principle is proposed. By iterating through different k values, the value corresponding to the largest evaluation factor was selected as the first-rank number of clusters. Secondly, the IASC algorithm adopts a density-sensitive distance to measure the similarity between the sample points. This rendered a high similarity to the data distributed in the same high-density area. Thirdly, to improve clustering accuracy, the IASC algorithm uses the cosine angle classification method instead of K-means to classify the eigenvectors. Six algorithms-K-means, fuzzy C-means, TSC, EIGENGAP, DBSCAN, and density peak-were compared with the proposed algorithm on six datasets. The results show that the IASC algorithm not only automatically determines the number of clusters but also obtains better clustering accuracy on both synthetic and UCI datasets.

• Journal of Environmental Health Sciences
• /
• v.46 no.6
• /
• pp.726-734
• /
• 2020

Objectives: The aim of this study was to analyze and classify the characteristics of potential damage from hazardous chemical accidents in 229 administrative units in South Korea by reflecting the social and environmental characteristics of areas where chemical accidents can occur. Methods: A number of indicators were selected through preceding studies. Factor analysis was performed on selected indicators to derive factors, and cluster analysis was performed based on the factor scores. Results: As a result of the cluster analysis, 229 administrative units were divided into three clusters, and it was confirmed that each cluster had its own characteristics. Conclusions: The first cluster, "areas at risk of accident occurrence and spread of damage" was a type with a high potential for accident damage and a high density of hazardous facilities. The second cluster, "Urban infrastructure damage hazard areas" appeared to be a cluster with high urban development characteristics. Finally, the third cluster 'Urban and environmental damage hazard areas' appeared to be a cluster with an excellent natural environment. This study went further from the qualitative discussion related to existing chemical accidents to identify and respond to accident damage by reflecting the social and environmental characteristics of the region. Distinct from the previous studies related to the causes of accidents and the response system, it is meaningful to conduct empirical research focusing on the affected areas by analyzing the possibility of accident damage in reflection of the social and environmental characteristics of the community.

• The Research Journal of the Costume Culture
• /
• v.11 no.2
• /
• pp.193-207
• /
• 2003

The purpose of this study was to investigate the demographics and general clothing buying behavior according to clothing shopping orientation of female workers. A questionnaire was developed to measure clothing shopping orientation, fashion information sources, stores selection criteria, clothing purchasing frequency of a year, purchasing expenditure of clothing, the demographics. The questionnaire was administered to 775 female teacher in Chonnam. The data was analyzed using percentage, frequency, mean, factor analysis, Cluster Analysis, x 1_test and ANOVA, Duncan test. The results of the study were as follows: 1. The female teachers were classified into four groups by the cluster analysis; indifferent shopping group, rational shopping group, conspicuous shopping group, recreational shopping group. 2. In the case of purchasing motives, significant differences were found according to shopping orientation subdivision in four factors. 3. The evaluation criteria of product were significantly different depending on shopping orientation subdivision in practical attribute, socio-psychological attribute, and aesthetic attribute. 4. The significant differences were found according to shopping orientation subdivision in general clothing purchasing behavior(purchasing price range of clothing, clothing purchasing frequency of a year, method of payment, number of stores visited, experience of buying in the import brand)

• Journal of Families and Better Life
• /
• v.26 no.3
• /
• pp.1-14
• /
• 2008

The purpose of the study was to examine the internet purchase behavior of items and self-assessment according to self-concept of elementary school students. The data were collected from 716 elementary school students by a self-administered questionnaire. Frequencies and means, Cronbach's Alpha, factor analysis, t-test, Pearson's correlation analysis, cross-tabulation analysis, cluster Analysis were conducted by SPSSWIN 12.0. The results from this study were as follows; First, from self-concept measurements, 4 factors(affective, social, schooling, Family self-concept) were extracted through factor analysis. Second, the subjects were classified into 3 clusters as self-concept types(high self-concept, middle self-concept, low self-concept) through cluster analysis. Third, the significant variables affecting internet purchase behaviors of items included grade, allowance, rank in class, the number of hours on the internet. As the self-concept gets higher, the frequence of the impulsive purchase and imitation purchases gets lower. In the contrary, as the self-concept gets higher, the self-assessment on the impulse purchases and imitation purchases also gets higher. In combination, these results suggest that irrational purchase behaviors were protected by positive self-concept, therefore it is important that children have positive a self-concept.

• The Journal of Fisheries Business Administration
• /
• v.52 no.1
• /
• pp.83-99
• /
• 2021

Fisheries policies are diversifying, including welfare programs for fishermen, revitalization of earfish and villages, and support for the sixth industrialization of fishing villages. In response to these policy changes, the purpose of this study is to categorize the fishing village fraternity, which is a local community, a fishery production organization, and a basic unit of a fishing village, and compares the characteristics of each type A number of indicators were selected by collecting data on the Categorization and evaluation of fishing villages fraternity and the statistical geographic information service. A number of indicators were extracted as representative factor variables using the principal component analysis, and then cluster analysis was performed to categorize the fishing village fraternity. This study was the first to attempt a comprehensive approach to revitalize the fishing village economy by using not only demographic and social characteristics, industrial and economic characteristics, but also regional characteristics. The characteristics of each type of fishing village fraternity find its significance in that it provides basic information that can be used in policy decisions. In order to strengthen the sustainability of the fishing community in the future and contribute to the sustainable development at the national level, the development of sustainable fishing village fraternity development indicators and follow-up studies on fishing village regeneration strategies will be needed.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2014.01a
• /
• pp.9-13
• /
• 2014

The performance of large scale software applications has been automatically increasing for last few decades under the influence of Moore's law - the number of transistors on a microprocessor roughly doubled every eighteen months. However, on-chip transistors limitations and heating issues led to the emergence of multicore processors. The energy efficient ARM based System-on-Chip (SoC) processors are being considered for future high performance computing systems. In this paper, we present a case study of two widely used parallel programming models i.e. MPI and MapReduce on distributed memory cluster of ARM SoC development boards. The case study application, Black-Scholes option pricing equation, was parallelized and evaluated in terms of power consumption and throughput. The results show that the Hadoop implementation has low instantaneous power consumption that of MPI, but MPI outperforms Hadoop implementation by a factor of 1.46 in terms of total power consumption to execution time ratio.

• Science of Emotion and Sensibility
• /
• v.16 no.4
• /
• pp.493-502
• /
• 2013

The purpose of this study was to find out the adjective scales, which will be used in the qualitative sensory evaluation of taste, by collecting and analyzing adjectives of expressing taste of Korean language. For the purpose, we rated the mutual similarities among selected 92 adjectives which include the sense of taste, texture, smell and temperature from foods, and then carried out factor analysis and clustering analysis by using correlation based on the similarities. According to the factor analysis there are more than 10 important factors involved in the linguistic representation of taste including food temperature, texture and smell as well as taste. Also, from the cluster analysis, we found that the adjectives can be clustered with groups of the adjectives representing general taste, negative taste, texture and temperature of food. In addition we analyzed the correlation between the adjectives to represent the generic preference of taste and the adjectives to express individual factors of the preferences that are resulted from cluster analysis. The analysis results could show that we need to restrict the type of foods to find out the meaningful limited number of sensory adjective scales for taste in the future.

• Journal of Intelligence and Information Systems
• /
• v.27 no.1
• /
• pp.1-21
• /
• 2021

As the global business environment changes, uncertainties in technology development and market needs increase, and competition among companies intensifies, interests and demands for R&D activities of individual companies are increasing. In order to cope with these environmental changes, R&D companies are strengthening R&D investment as one of the means to enhance the qualitative competitiveness of R&D while paying more attention to facility investment. As a result, facilities or R&D investment elements are inevitably a burden for R&D companies to bear future uncertainties. It is true that the management strategy of increasing investment in R&D as a means of enhancing R&D capability is highly uncertain in terms of corporate performance. In this study, the structural factors that influence the R&D capabilities of companies are explored in terms of technology management capabilities, R&D capabilities, and corporate classification attributes by utilizing data mining techniques, and the characteristics these individual factors present according to the level of R&D capabilities are analyzed. This study also showed cluster analysis and experimental results based on evidence data for all domestic R&D companies, and is expected to provide important implications for corporate management strategies to enhance R&D capabilities of individual companies. For each of the three viewpoints, detailed evaluation indexes were composed of 7, 2, and 4, respectively, to quantitatively measure individual levels in the corresponding area. In the case of technology management capability and R&D capability, the sub-item evaluation indexes that are being used by current domestic technology evaluation agencies were referenced, and the final detailed evaluation index was newly constructed in consideration of whether data could be obtained quantitatively. In the case of corporate classification attributes, the most basic corporate classification profile information is considered. In particular, in order to grasp the homogeneity of the R&D competency level, a comprehensive score for each company was given using detailed evaluation indicators of technology management capability and R&D capability, and the competency level was classified into five grades and compared with the cluster analysis results. In order to give the meaning according to the comparative evaluation between the analyzed cluster and the competency level grade, the clusters with high and low trends in R&D competency level were searched for each cluster. Afterwards, characteristics according to detailed evaluation indicators were analyzed in the cluster. Through this method of conducting research, two groups with high R&D competency and one with low level of R&D competency were analyzed, and the remaining two clusters were similar with almost high incidence. As a result, in this study, individual characteristics according to detailed evaluation indexes were analyzed for two clusters with high competency level and one cluster with low competency level. The implications of the results of this study are that the faster the replacement cycle of professional managers who can effectively respond to changes in technology and market demand, the more likely they will contribute to enhancing R&D capabilities. In the case of a private company, it is necessary to increase the intensity of input of R&D capabilities by enhancing the sense of belonging of R&D personnel to the company through conversion to a corporate company, and to provide the accuracy of responsibility and authority through the organization of the team unit. Since the number of technical commercialization achievements and technology certifications are occurring both in the case of contributing to capacity improvement and in case of not, it was confirmed that there is a limit in reviewing it as an important factor for enhancing R&D capacity from the perspective of management. Lastly, the experience of utility model filing was identified as a factor that has an important influence on R&D capability, and it was confirmed the need to provide motivation to encourage utility model filings in order to enhance R&D capability. As such, the results of this study are expected to provide important implications for corporate management strategies to enhance individual companies' R&D capabilities.

• Journal of Environmental Science International
• /
• v.25 no.6
• /
• pp.767-787
• /
• 2016

In this study, we analyzed on-site monitoring data for 15 tributaries in Geumho watersheds for 3 years (2011-2013) in order to sort out priorities on water quality characteristics and improvement. As a result of estimating contribution to contamination of the tributary rivers, Dalseocheon showed the highest load densities, despite the smallest watershed area, with 22.7% $BOD_5$, 30.7% $COD_{Mn}$, 31.3% TOC and 47.6% TP. After conducting PCA (principal component analysis) and FA (factor analysis) to analyze water quality characteristics of the tributary rivers, the first factor was classified as $COD_{Mn}$, TOC, EC, TP and $BOD_5$, the second factor as pH, Chl-a and DO, the third factor as water temperature and TN, and the fourth factor as SS and surface flow. In addition, arithmetical sum of each factor's scores based on grading criteria revealed that Dalseocheon and Namcheon were classified into Group A for their highest scores - 96 and 93, respectively -, and selected as rivers that require water environmental management measures the most. Also, water environmental contamination inspection showed that Palgeocheon had the most number of aquatic factors to be controlled: $BOD_5$, $COD_{Mn}$, SS, TOC, T-P, Chl-a, etc.

• Journal of the Korean Institute of Landscape Architecture
• /
• v.16 no.2
• /
• pp.43-57
• /
• 1988

The purpose of this thesis is to suggest objective basic data for park management proposal through the quantitative analysis of users' behaviors and satisfaction for the actual conditions of management in the Chiri Mountain National Park. For this users' behaviors and socio-economic characteristics have been cross-analyzed. Specifically, it attempts to investigate users' anticipate and degree of satisfaction applied Expectancy Theory by Likert attitude scale. Users'behaviors patterns of each site have been analyzed by the factor analysis algorithm, and each factor scores of sites have been clustered by the cluster method. And also user' satisfaction for the actual conditions of management have been analyzed by using the multiple regression. The major user groups were students and youth groups accompanied by their friends ranging from 3 to 10. The values of user'post occupancy-evaluation for such as rockwall climbing and praying on the mountain of each site showed higher than those of anticipated, but evaluation values of other activities were lower. The user'behaviors of each site have been analyzed five factors by factor analysis algorithm. By using the control method for the number of factors, T.V. has been obtained as 50.58%. The factor score of factor covering the behavior patterns of student and youth yield high EV. and C.V.. On the analysis of cluster using factor score, factor IV in Hwaomsa temple site and Ssanggyesa temple site, factor II, v in Jungsanri Valley site, factor, I, III in Bangmudong valley site and factor I. IV in Baemsagol vallry site showed very high values, respectively. According to the multiple regression analysis, the major variables related to the satisfaction for the actual conditions of vegetation and landscape managements were reservation of groundcover, recovery of artificial injury, the surroundings of camping and temple site. In the park facilities and operation, the major variables related to the satisfaction were conditions of management such amenity facilities as privy, sign board, junk yard, camping site, and guidance of excursion, campaign and preservation of nature.