• 한국정밀공학회지
• /
• 제9권3호
• /
• pp.122-131
• /
• 1992

In this paper an approximate solution method for the large-scale Traveling Salesman Problem (TSP) is presented. The method starts with the subdivision of the problem domain into a number of cluster by considering their geometric characteristic. Each cluster has a limited number of nodes so as to get a local solution. They are linked go give the least pathe which covers the whole domain and become TSPs solution with start-and end-node. The approximate local solution in each cluster are obtained based on geometrical properties of the cluster, and combined to give an overall approximate solution for the larte-scale TSP.

• 대한지리학회지
• /
• 제47권2호
• /
• pp.226-244
• /
• 2012

본 연구는 구미 전자산업클러스터의 진화과정을 분석하고 지역산업변화에 정부의 역할을 이해하는데 그 목적이 있다. 1990년대 초반까지 구미 산업단지는 수도권에 본사를 둔 대기업 분공장의 집적지로 구미지역에서의 산업연계가 미약했다. 그러나 최근 20년 동안 구미는 지역 내 기업 간 연계와 중소기업의 혁신활동이 상당히 이루어져 전자산업중심의 클러스터로 발전하고 있다. 정부의 산업정책은 구미전자산업클러스터의 진화과정을 이해하는데 매우 중요하다. 초기의 국가산업정책은 전략산업의 선정과 개발을 통해 구미 국가산업단지의 성장과 전자산업 중심의 전문화에 영향을 미쳤으며, 최근의 혁신클러스터 정책은 기업, 대학, 연구소간의 연계를 강화하고 지역 내 혁신네트워크 형성을 지원하였다. 경상북도와 구미시는 지역 대학 및 기업과 직접 협력관계를 맺고 지역의 연구개발 역량 향상과 중소기업 지원을 위한 정책을 중심으로 지역 발전에 기여하였다. 중앙정부와 대기업의 역할에 더해 지방정부와 중소기업의 역할 증대가 구미산업클러스터 진화의 기반이 되고 있다.

• 한국환경복원기술학회지
• /
• 제25권1호
• /
• pp.41-55
• /
• 2022

Social interest in the fine particulate matter has increased significantly since the 2010s, and various efforts have been made to reduce it through environmental plans and policies. To support such environmental planning, in this study, spatial cluster characteristics of fine particulate matter (PM2.5) concentrations were analyzed in the metropolitan area to identify high-risk areas spatially, and the correlation with local environmental characteristics was also confirmed. The PM2.5 concentration for the recent 5 years (2016-2020) was targeted, and representative spatial statistical methods Getis-Ord Gi^* and Local Moran's I were applied. As a result of the analysis, the cluster form was different in Getis-Ord Gi^* and Local Moran's I, but they show high similarity in direction, therefore complementary results could be obtained. In the high concentration period, the hotspot concentration of the Getis-Ord Gi* method increased, but in Local Moran's I, the HH region, the high concentration cluster, showed a decreasing trend. Hotspots of the Getis-Ord Gi^* technique were prominent in the Pyeongtaek-Hwaseong and Yeoju-Icheon regions, and the HH cluster of Local Moran's I was located in the southwest, and the LL cluster was located in the northeast. As in the case of the metropolitan area, in the results of Seoul, there was a phenomenon of division between the northeast and southwest regions. The PM2.5 concentration showed a high correlation with the elevation, vegetation greenness and the industrial area ratio. During the high concentration period, the relation with vegetation greenness increased, and the elevation and industrial area ratio increased in the case of the annual average. This suggests that the function of vegetation can be maximized at a high concentration period, and the influence of topography and industrial areas is large on average. This characteristic was also confirmed in the basic statistics for each major cluster. The spatial clustering characteristics of PM2.5 can be considered in the national land and environmental plan at the metropolitan level. In particular, it will be effective to utilize the clustering characteristics based on the annual average concentration, which contributes to domestic emissions.

• 한국의류학회지
• /
• 제47권5호
• /
• pp.959-976
• /
• 2023

This study participated in educational programs for young designers and received trainings in sewing technology through government and local government-supported projects led by a from a skilled craftsman. These initiatives aim to revitalize the Dongdaemun fashion cluster, which is currently experiencing stagnation. Our goal is to develop denim brands that reflect the unique regional characteristics stemming from the skilled sewing techniques and denim processes of the Changsin·Sungin regions, the production hubs supporting Dongdaemun, to discover solutions for revitalizing the local industry. For the research method, we collected data by actively participating in support projects related to the Dongdaemun fashion cluster. Additionally, we gathered data by conducting a theoretical review of the sewing industry in the Changsin·Sungin regions and the Dongdaemun fashion cluster. The research results include developing a denim brand collection-eight denim products-based on Changsin-dong's unique denim sewing technology and various denim washing processes acquired through the support project and regional characteristics. Overall, this study is meaningful in presenting a sustainable plan to revitalize the domestic sewing and manufacturing industry, focusing on the Dongdaemun fashion cluster. We achieved this by developing a denim brand that leverages the sewing and washing process technology and the unique regional characteristics of Changsin-dong.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 1991년도 한국자동제어학술회의논문집(국내학술편); KOEX, Seoul; 22-24 Oct. 1991
• /
• pp.601-605
• /
• 1991

In this paper an approximate solution method for the large-scale Traveling Salesman Problem(TSP) is presented. The method start with the subdivision of the problem domain into a number of clusters by considering their geometries. The clusters have limited number of nodes so as to get local solutions. They are linked to give the least path which covers the whole domain and become TSPs with start- and end-node. The approximate local solutions in each cluster are obtained by using geometrical property of the cluster, and combined to give an overall-approximate solution for the large-scale TSP.

• 음성과학
• /
• 제10권4호
• /
• pp.159-166
• /
• 2003

To reduce the high dimensionality required for training of feature vectors in speaker identification, we propose an efficient GMM based on local PCA with Fuzzy clustering. The proposed method firstly partitions the data space into several disjoint clusters by fuzzy clustering, and then performs PCA using the fuzzy covariance matrix in each cluster. Finally, the GMM for speaker is obtained from the transformed feature vectors with reduced dimension in each cluster. Compared to the conventional GMM with diagonal covariance matrix, the proposed method needs less storage and shows faster result, under the same performance.

• 한국경제지리학회지
• /
• 제19권3호
• /
• pp.437-456
• /
• 2016

본 연구의 목적은 공연예술 산업의 입지적 특성을 파악하고, 그들의 지역 경제와의 연계성을 분석하는 것이다. 이를 위하여 공연예술 산업이 가장 집중되어 있는 서울을 대상으로 소비자가 관련시설이 있는 장소를 방문해야 하는 소비의 유사성을 지닌 갤러리와 영화 상영관의 각 사업체의 주소자료를 이용하여 커널밀도분석과 공간적 자기상관성(Spatial Autocorrelation)분석을 실시한다. 특히 LISA(Local Indicator of Spatial Association)를 적용하여 국지적 핫스팟을 확인한다. 분석 결과 갤러리와 영화 상영관의 분산 분포와 달리 공연장은 대학로 일대를 중심으로 응집된 단일 핫스팟이 나타난다. 대학로 일대를 중심으로 하는 공연장 밀집지역에는 공연예술 산업의 가치사슬을 구성하는 다양한 활동들이 인근에 밀집분포하며 공연예술 산업의 클러스터를 형성하는 입지적 특성이 파악된다. 또한 다중회귀분석을 통하여 공연장의 분포를 설명하는 경제활동을 파악하여 지역 경제경관과의 연계성을 분석한다.

• 한국정보통신학회:학술대회논문집
• /
• 한국정보통신학회 2012년도 춘계학술대회
• /
• pp.151-152
• /
• 2012

본 논문은 지역의 의사 결정 트리와 클러스터링을 사용하여 장면 전환 검출 방법을 제시한다. 지역 의사 결정 트리는 클러스터 경계선 검출 장면과 그 인접 프레임의 사이의 차이 값을 시간 유사분포를 비교하기 위해 같은 방식으로 검출하고, 그리고 클러스터 단위로 차이 값의 유사성과 그룹 프레임의 끊어지지 않는 시퀀스를 감지한다.

• 한국정보통신학회논문지
• /
• 제16권6호
• /
• pp.1199-1203
• /
• 2012

본 논문은 지역의 의사 결정 트리와 클러스터링을 사용하여 장면 전환 검출 방법을 제시한다. 지역 의사 결정 트리는 클러스터 경계 검출 장면과 그 인접 프레임의 사이의 차이 값을 시간 유사 분포를 비교하기 위해 같은 방식으로 검출하고, 그리고 클러스터 단위로 차이 값의 유사성과 그룹 프레임의 끊어지지 않는 시퀀스를 감지한다.

• 대한가정학회지
• /
• 제44권10호
• /
• pp.9-20
• /
• 2006

Due the globalization trends of industry environment, not only fashion companies of the developed countries but also those of NICs and the developing countries are pursuing to globalize their businesses. This study was conducted (i) to identify the characteristics of international marketing mix of Korean fashion companies operating in oversea fashion markets and (ii) to analyze the performance of Korean fashion companies related to international marketing mix. The data were collected from inter-Korean fashion enterprises. A questionnaire was distributed to a person in charge of international division/international trade division who doing business in domestic market and a person in charge of a local subsidiary in oversea market. The methods of analysis used in this study were factor analysis, cluster analysis, and one-way ANOVA. The results of this study are as follows: First, according to factor analysis and cluser analysis, Korean fashion companies were classified in four (4) clusters. The fashion companies in Cluster I put their priority on price. The companies in Cluster II are traditional fashion companies which have relatively low power of product and price. The companies in Cluster III put their priority on product, and the companies in Cluster IV put their priority on local market. Second, according to ANOVA, a growth rate of sales make significant difference among 4 clusters and Clusters II and III were comparatively high in performance.