• 한국경영과학회지
• /
• 제28권4호
• /
• pp.39-60
• /
• 2003

In this study, we evaluate financial performance of 21 domestic life insurers using SAW (simple additive weighting), ELECTREII, cluster analysis respectively, and suggest a hybrid approach of combining cluster analysis and ELECTREII to reclassify the life insurers into more meaningful groups according to their respective financial features. We also perform the sensitivity analysis employing ANOVA and Tukey's test to examine the robustness of ELECTREII, which would be influenced by decision maker's subjective preference parameters. Consequently, it is shown that ELECTREII turns out to be a flexible method providing decision makers with useful ranking Information especially under fuzzy decision making situation with incomparable alternatives, and hence it can serve as a complementary method to overcome the weakness of classical cluster analysis.

• 산업융합연구
• /
• 제14권1호
• /
• pp.39-45
• /
• 2016

This paper deals with the consideration of mathematical models with regards to growth of cluster and firms by reviewing the Metcalf and Breuner's articles. prior studies have been argued the phenomenon of local industrial clusters and districts. Several concepts have been adopted to support the success of and changes to these clusters and firm growth. Through the review of two papers, evolution of both cluster and firm growth may be achieved in terms of utilizations of the different local aspects and mechanisms. This paper supports the theoretical back bone with regards to the regional cluster policy implementing in Korea for the purpose of regional developments. In particular, a mathematical model that, on a more abstract level, captures the fundamental dynamic structure of all the observed mechanisms. On the basis of this model, the emergence and evolution of local clusters can be described. Also this model has given that the knowledge sharing between firms has an important role to firms and cluster' growth.

• 정보관리학회지
• /
• 제29권2호
• /
• pp.45-70
• /
• 2012

개체들 사이의 관계를 저차원 공간에 매핑하는 다차원척도법을 수행하기 위한 다양한 방법과 알고리즘이 개발되어왔다. 그러나 PROXSCAL이나 ALSCAL과 같은 기존의 기법들은 50개 이상의 개체를 포함하는 데이터 집합을 대상으로 개체 간의 관계와 군집 구조를 시각화하는데 있어서 효과적이지 못한 것으로 나타났다. 이 연구에서 제안하는 군집 지향 척도법 CLUSCAL(CLUster-oriented SCALing)은 기존 방법과 달리 입력되는 데이터의 군집 구조를 고려하도록 고안되었다. 50명의 저자동시인용 데이터와 85개 단어의 동시출현 데이터에 대해서 적용해본 결과 제안한 CLUSCAL 기법은 군집 구조를 잘 식별할 수 있는 MDS 지도를 생성하는 유용한 기법임이 확인되었다.

• 대한산업공학회지
• /
• 제37권3호
• /
• pp.180-190
• /
• 2011

Efficient energy consumption is a critical factor for deployment and operation of wireless sensor networks (WSNs). To achieve energy efficiency there have been several hierarchical routing protocols that organize sensors into clusters where one sensor is a cluster-head to forward messages received from its cluster-member sensors to the base station of the WSN. In this paper, we propose a self-organized clustering method for cluster-head selection and cluster based routing for a WSN. To select cluster-heads and organize clustermembers for each cluster, every sensor uses only local information and simple decision mechanisms which are aimed at configuring a self-organized system. By these self-organized interactions among sensors and selforganized selection of cluster-heads, the suggested method can form clusters for a WSN and decide routing paths energy efficiently. We compare our clustering method with a clustering method that is a well known routing protocol for the WSNs. In our computational experiments, we show that the energy consumptions and the lifetimes of our method are better than those of the compared method. The experiments also shows that the suggested method demonstrate properly some self-organized properties such as robustness and adaptability against uncertainty for WSN's.

• Agribusiness and Information Management
• /
• 제7권1호
• /
• pp.21-36
• /
• 2015

This study aims to analyze the differences of ginseng product consumers and segment Korean fresh ginseng and red ginseng root markets based on attributes for the purchase. As a result of analyzing survey data, the red ginseng root consumers had different aspects from fresh ginseng consumers. According to the result of cluster analysis, the fresh ginseng consumers were subdivided into three segments (safety-oriented consumption cluster, label centered consumption cluster, and high involvement consumption cluster), while the red ginseng root consumers were subdivided into four segments (convenience-oriented consumption cluster, high involvement consumption cluster, raw material's safety-oriented cluster, and raw material's information importance cluster). ANOVA and Crosstab were conducted to investigate characteristics of each cluster.

• 지식경영연구
• /
• 제15권4호
• /
• pp.147-170
• /
• 2014

This study investigates the main characteristics of Chinese automobile industry based on the technology learning, architecture theory and cluster. As a case study sample, we chose three most representative automobile firms from three main cities in China, FAW from northern part of China, SAIC from middle part of China, and BYD from southern part of China. According to the research findings, FAW has equipped self-production ability in virtue of political support but felled behind in future transportation due to lack of convergence with local cluster. In case of SAIS, similar phenomenon happened in spite of highest purchasing power of shanghai. BYD has achieved great quantum jump through the aggressive investment strategy in electric vehicle even though there are still many technological learning and experience to be cumulated. Overall, this research extends the current literature on key roles (technological learning, architecture, and cluster features) in the automobile industry growth by suggesting their crucial aspects in knowledge management and strategic planning to a newly emerging market, China, and sheds light on the relationship between regional characteristics and automobile growth.

• 한국병원경영학회지
• /
• 제28권2호
• /
• pp.9-20
• /
• 2023

Purpose: This study classified the actual functions of geriatric hospitals and examined the differences in their characteristics, in order to provide a basis for discussions on defining the functions of geriatric hospitals and how to pay for care. Methodology: This study used various administrative data such as health insurance data and long-term care insurance data. Cluster analysis was used to categorize geriatric hospitals. To examine the validity of the cluster analysis results, we conducted a discriminant analysis to calculate the accuracy of the classification. To examine cluster characteristics, we examined structure, process, and outcome indicators for each cluster. Findings: The cluster analysis identified five clusters. They were geriatric hospitals with relatively short stays for cancer patients(cluster 1; cancer patient-centered), geriatric hospitals with relatively large numbers of patients using rehabilitation services(cluster 2; rehabilitation patient-centered), geriatric hospitals with a high proportion of relatively severe elderly patients(cluster 3; severe elderly patient-centered), geriatric hospitals with a high proportion of mildly ill elderly patients with various conditions(cluster 4; mildly ill elderly patient-centered), and geriatric hospitals with a significantly higher proportion of dementia patients(cluster 5; dementia patient-centered). The largest number of geriatric hospitals were categorized in clusters 4 and 5, and the structure and process indicators for these clusters were generally lower than for the other clusters. Practical Implications: We have confirmed the existence of geriatric hospitals where the medical function, which is the original purpose of a geriatric hospital, has been weakened. It has been observed that the quality level of these geriatric hospitals is likely to be lower compared to hospitals that prioritize enhanced medical functions. Therefore, it is suggested to consider the conversion of these geriatric hospitals into long-term care facilities, and careful consideration should be given to the review of care-giver payment coverage.

• 한국정보통신학회논문지
• /
• 제12권5호
• /
• pp.870-878
• /
• 2008

센서 네트워크를 구성하는 센서 노드는 대부분 보안성이 낮으며, 낮은 연산 능력과 적은 저장 용량으로 효율적인 보안 알고리즘을 적용할 수 없다. 따라서 불법적인 노드의 침입을 억 제할 수 없으며, 센서 노드의 전송 알고리즘만 알게되면 전송되는 정보를 쉽게 도청 할 수 있는 문제점을 갖게 된다. 본 논문에서는 센서 네트워크를 클러 터로 구분하고, 클러스터 내에서 센서 노드가 안전하게 정보를 전송할 수 있으며 불법적인 센서 노드의 침입을 억제할 수 있는 극좌표를 이용한 클러스터 기반의 센서 네트워크의 키 관리기법을 제안한다. 제안된 기법에서는 클러스터 내에서 모든 센서 노드는 CH(Cluster Header)가 제공하는 피벗값을 기반으로 인증키를 설정하도록 하고있다. 시뮬레이션 결과 기존의 페어 와이즈(pair-wise) 기법에 비하여 키 관리측면에서 안전한 키 관리와 불법적인 노드의 침입을 억 제할 수 있는 우수함을 증명하였다.

• 디지털산업정보학회논문지
• /
• 제5권1호
• /
• pp.23-32
• /
• 2009

Although the web is becoming a widely accepted medium, it provides relatively poor performance and low availability. A cluster consists of a collection of interconnected stand-alone computers working together and provides a high-availability solution in application area such as web services or information systems. Web server clusters require a high-availability service with a proactive and practical fault management. However, as the system complexity grows, it is not easy to meet the requirement. Therefore, web server clusters must have self-fault management capability for meeting high-availability requirement. In this paper, we propose high availability web server clusters using self-healing technique with a minimal human intervention. Our experimental results show that a proposed method can be used to improve the availability of web server clusters.

• 한국경영과학회:학술대회논문집
• /
• 한국경영과학회 1996년도 추계학술대회발표논문집; 고려대학교, 서울; 26 Oct. 1996
• /
• pp.31-34
• /
• 1996

The extensive researches have compared the performance of neural networks(NN) with those of various statistical techniques for the classification problem. The empirical results of these comparative studies have indicated that the neural networks often outperform the traditional statistical techniques. Moreover, there are some efforts that try to combine various classification methods, especially multivariate discriminant analysis with neural networks. While these efforts improve the performance, there exists a problem violating robust assumptions of multivariate discriminant analysis that are multivariate normality of the independent variables and equality of variance-covariance matrices in each of the groups. On the contrary, cluster analysis alleviates this assumption like neural networks. We propose a new approach to classification problems by combining the cluster analysis with neural networks. The resulting predictions of the composite model are more accurate than each individual technique.