• 한국인터넷방송통신학회논문지
• /
• 제15권6호
• /
• pp.187-193
• /
• 2015

ICT 힐링플랫폼은 만성질환 예방을 목적으로 하며 개인의 생체신호 및 생황습관 등의 정보에 기반을 둔 질환 조기 경보를 목표로 한다. 이를 위한 2-step 개방형 시스템(TOS)에는 힐링플랫폼과 개인건강데이터 저장소간의 중계가 설계되었으며 데이터 처리과정을 실시간으로 전송(모니터링)하기 위한 대량 커넥션 기반의 publish/subscribe(pub/sub) 서비스가 고려되었다. 그러나 TOS pub/sub의 초기 설계에서는 커넥션 메시지를 deflate 알고리즘으로 인코딩하기 위해, 커넥션의 유휴(idle) 여부 및 메시지의 종류에 상관없이 동일한 버퍼를 할당한다. 본 논문의 동적 버퍼 할당은 다음과 수행된다. 우선 각 커넥션의 메시지 전송 유형을 큐잉하고, 각 큐는 tf-idf를 통해 특징(feature)추출 연산 후 벡터로 변환하여 k-means 클러스터에 입력하여 군집을 생성한다. 특정 군집으로 분류된 커넥션은 해당 군집의 자원 테이블에 따라 자원을 재할당 한다. 이때 각 군집의 센트로이드(centroid)는 해당 군집을 대표하는 큐잉 패턴을 사전에 선택하여 자원참조 테이블(버퍼 크기별 인코딩 효율)로 도출한다. 제안된 설계는 TOS의 인코딩 버퍼 자원을 네트워크 커넥션에 효율적으로 배분하기 위해, 군집 및 특징 연산을 위한 연산 자원과 네트워크 대역폭 간의 trade-off를 수행함으로써 TOS의 tps(단위 시간당 실시간 데이터 처리 모니터링 연결수)를 높이는데 활용할 수 있다.

• International Journal of Computer Science & Network Security
• /
• 제22권7호
• /
• pp.75-84
• /
• 2022

The efficiency of the regional fiscal policy implementation is based on the achievement of target criteria in the formation and distribution of own financial resources of local budgets, reducing their deficit and reducing dependence on transfers. It is also relevant to compare the development of financial autonomy of regions in the course of decentralisation of fiscal relations. The study consists in the cluster analysis of the effectiveness of fiscal policy implementation in the context of 24 regions and the capital city of Kyiv (except for temporarily occupied territories) under conditions of fiscal decentralisation. Clustering of the regions of Ukraine by 18 indicators of fiscal policy implementation efficiency was carried out using Ward's minimum variance method and k-means clustering algorithm. As a result, the regions of Ukraine are grouped into 5 homogeneous clusters. For each cluster measures were developed to increase own revenues and minimize dependence on official transfers to increase the level of financial autonomy of the regions. It has been proved that clustering algorithms are an effective tool in assessing the effectiveness of fiscal policy implementation at the regional level and stimulating further expansion of financial decentralisation of regions.

• 한국컴퓨터정보학회논문지
• /
• 제20권12호
• /
• pp.15-20
• /
• 2015

In this paper, we propose a modified fuzzy clustering algorithm which can overcome the center deviation due to the Euclidean distance commonly used in fuzzy clustering. Among fuzzy clustering methods, Fuzzy C-Means (FCM) is the most well-known clustering algorithm and has been widely applied to various problems successfully. In FCM, however, cluster centers tend leaning to high density clusters because the Euclidean distance measure forces high density cluster to make more contribution to clustering result. Proposed is an enhanced algorithm which modifies the objective function of FCM by adding a center-scattering term to make centers not to be close due to the cluster density. The proposed method converges more to real centers with small number of iterations compared to FCM. All the strengths can be verified with experimental results.

• 한국식품조리과학회지
• /
• 제23권3호통권99호
• /
• pp.327-336
• /
• 2007

Life-style factors often include social relationships as well as consumption, entertainment and dress patterns. They also typically reflect an individual's attitudes, values and worldview. Life-style types have become and an important factor for segmenting customer markets ever since significant relationships between life-style and customers' behavior was proven. This study examined the relationships between the life-styles of young customers' and the important attributes of foodservice encounters. Factors analysis with VARIMAX and K-means cluster analysis were conducted to group the subjects by life-style. According to the factors analysis, four underlying dimensions were identified and labeled: (1) 'actively fashioned', (2) 'luxury picky', (3) 'healthy toward', and (4) 'utilitarian leisure'. Based on the factor scores derived from the factors analysis, the K-means cluster analysis classified three groups as statistically significant using ANOVA(p<0.05). The overall mean score for the 3rd cluster 'trendy-active picky' was higher than the other two clusters, and represented very picky attitudes about foodservice attributes. The 3rd cluster also seemed to apply higher standards to all of the foodservice attributes. By order of importance, the most important attributes of the 2nd cluster 'pursue-utilitarian leisure' were food serving time, automation systems, server's hygienes, employee kindness, time in line, and menu variety. In spite of low concerns for the life-style attributes, the first cluster 'passively indifferent' recognized menu variety, food sanitation, food serving time, server's hygiene, menu price, air circulation, and room temperature as important. These results suggest that young diners in Korea could be classified by their diverse life-styles that are represented as trendy, utilitarian, and indifferent and will hopefully contribute to the foodservice industry's ability to segment customer characteristics by different life-styles in Korea.

• Human Ecology Research
• /
• 제61권2호
• /
• pp.233-245
• /
• 2023

The aim of this study was to identify community-level childcare infrastructure for infants and toddlers and to use the data to categorize community types using K-Means cluster analysis with spatial constraints. Seven indicators of childcare resource supply were used for the purpose of categorization and the results revealed six types of community cluster. Communities in the Type 1 cluster provided sufficient parks, libraries, and kindergartens, but lacked pediatric facilities and private education institutions. This cluster comprised small cities and rural areas in Gangwon-do, Gyeongsangbuk-do, Chungcheongbuk-do, and Jeollabuk-do. The Type 2 cluster had numerous pediatric facilities and childcare centers, but lacked other childcare infrastructure. This comprised small and medium-sized cities in Gyeonggi-do, some areas in Chungcheongnam-do, Chungcheongbuk-do, and Gangwon-do bordering Gyeonggi-do. The Type 3 cluster comprised Busan, Daegu, and Gyeongsangnam-do, but had insufficient childcare infrastructure as a whole. Type 4 had the largest number of childcare centers, libraries, and private education institutions and comprised Jeollabuk-do, areas near Gwangju, and Jeju-do. Type 5, consisting of Seoul, Incheon and the southern part of Gyeonggi-do had many pediatric facilities and certified childcare centers, but lacked other childcare infrastructure. Type 6, being the rural areas and islands in Jeollanam-do, had sufficient kindergartens, but other infrastructure was insufficient. These results are expected to provide local government with policy implications in terms of relieving the childcare burden on residents with infants and toddlers.

• 한국컴퓨터정보학회논문지
• /
• 제28권7호
• /
• pp.189-198
• /
• 2023

최근 지구온난화로 인한 폭염, 태풍, 폭설 등 기후변화를 급증하고 있다. 미국 뉴욕에서 개최된 제 25차 '기후변화 당사국총회(COP25)'에 따른 세계 각국은 '탄소중립' 달성하기 위한 협상을 진행했다. 도시는 경제발전뿐만 아니라 탄소중립 과정에서도 중요한 역할을 수행한다. 본 연구는 이산화탄소와 관계되는 경제요인 및 환경요인을 고려하여 엘보우 규칙 (Elbow method) 과 K-means 군집 알고리즘을 활용하여 한국 63개 도시의 탄소배출 현황을 분석하였다. 연구결과에 따른 한국 도시는 기술집약 도시, 경공업 도시, 미래 혁신도시, 중공업 도시, 서비스 집약도시 및 농촌, 가정생산집약도시로 구분될 수 있고 향후 시도별 탄소중립 목표를 실천하기 위해 구체적인 제안을 제시하였다.

• 정보관리학회지
• /
• 제21권3호
• /
• pp.251-267
• /
• 2004

이 연구에서는 전통적인 인쇄매체 환경에서 지식에 대해 지역적인 접근법을 제공하는 권말색인과 목차의 기능에 착안하여 용어 클러스터링 실험과 클러스터 대표어 선정 실험을 통해 개별문서의 지식구조 자동 생성 기법을 제안하였다. 자동 생성된 지식구조가 갖는 기능성을 평가하여 정보 검색 환경에서의 적용 가능성을 확인하였다. 용어 클러스터링 실험에서는 워드 기법의 성능이 중복 분류를 허용하는 퍼지 K-means 클러스터링 기법에 비해 높았으며, 클러스터 대표어 선정 기법으로는 단락빈도를 이용한 경우가 가장 좋은 성능을 나타냈다. 또한, 이용자 태스크를 기반으로 하여 최종적으로 생성된 지식구조의 기능성을 평가한 결과, 이 연구에서 자동 생성된 지식구조가 인쇄매체 환경에서의 권말색인과 목차가 갖는 기능을 어느 정도 수행한다는 것을 입증하였다.

• Communications for Statistical Applications and Methods
• /
• 제13권1호
• /
• pp.113-123
• /
• 2006

Normal mixture model(NMM) frequently used to cluster genes on microarray gene expression data. In this paper some of component means of NMM are modelled by a linear regression model so that its design matrix presents the pattern between sample classes in microarray matrix. This modelling for the component means by given design matrices certainly has an advantage that we can lead the clusters that are previously designed. However, it suffers from 'overfitting' problem because in practice genes often are highly dimensional. This problem also arises when the NMM restricted by the linear model for component-means is fitted. To cope with this problem, in this paper, the use of the factor analyzer NMM restricted by linear model is proposed to cluster genes. Also several design matrices which are useful for clustering genes are provided.

• 농촌계획
• /
• 제11권4호
• /
• pp.33-45
• /
• 2005

This study investigates the core elements of the formation and development of cluster using a multi-disciplinary approach and suggests a promoting strategy by development stage of cluster. As a sub-category of regional innovation system, the cluster has been considered as one of the most noticeable methodological argument to make the regional innovation system come true. In the meantime, this study examines the core elements of cluster shown in the theories and examples through six academic fields such as economics, geography, regional development, business administration, sociology and pedagogy and their educational back-ground. By means of establishing the incubation stage in the development of cluster, core elements are composed in the stages of birth, incubation and evolution in subsequent manner. A promoting strategy will be suggested through the implication of core elements in the reestablished stages.

• Smart Structures and Systems
• /
• 제26권1호
• /
• pp.23-33
• /
• 2020

Majority of the damage in engineering structures is nonlinear. Damage sensitive features (DSFs) extracted by traditional methods from linear time series models cannot effectively handle nonlinearity induced by structural damage. A new DSF is proposed based on vector space cosine similarity (VSCS), which combines K-means cluster analysis and Bayesian discrimination to detect nonlinear structural damage. A reference autoregressive moving average (ARMA) model is built based on measured acceleration data. This study first considers an existing DSF, residual standard deviation (RSD). The DSF is further advanced using the VSCS, and then the advanced VSCS is classified using K-means cluster analysis and Bayes discriminant analysis, respectively. The performance of the proposed approach is then verified using experimental data from a three-story shear building structure, and compared with the results of existing RSD. It is demonstrated that combining the linear ARMA model and the advanced VSCS, with cluster analysis and Bayes discriminant analysis, respectively, is an effective approach for detection of nonlinear damage. This approach improves the reliability and accuracy of the nonlinear damage detection using the linear model and significantly reduces the computational cost. The results indicate that the proposed approach is potential to be a promising damage detection technique.