• 정보관리학회지
• /
• 제23권4호
• /
• pp.215-231
• /
• 2006

패스파인더 네트워크를 사용하여 지적 구조의 분석과 규명을 시도한 여러 연구가 발표되었다. 패스파인더 네트워크는 다차원척도법에 비해서 여러 장점을 가지고 있지만 구축 알고리즘의 복잡도가 매우 높아서 실행 시간이 오래 걸리며, 전통적인 지적 구조 분석에 유용하게 사용되어온 군집분석을 함께 적용하기가 어려운 것이 단점이다. 이 연구에서는 이와 같은 패스파인더 네트워크의 약점을 보완할 수 있는 새로운 기법으로 병렬최근접이웃클러스터링(PNNC) 기법을 제안하였다. PNNC 기법의 클러스터링 성능을 전통적인 계층적 병합식 클러스터링 기법들과 비교해본 결과 효과성과 효율성 양면에서 기존 기법보다 우세한 것으로 확인되었다.

• 한국복식학회:학술대회논문집
• /
• 한국복식학회 2001년도 19th International Costume Association Congress
• /
• pp.105-106
• /
• 2001

• 대한한의진단학회지
• /
• 제15권2호
• /
• pp.141-148
• /
• 2011

Objectives: In comparison with functional dyspepsia, food accumulation is known to have wider concept. On this study, we will make a proposal on the concept of food accumulation by a statistical comparison between pyungweesan questionnaire and health related questionnaires. Methods: We studied the similarities between six factors of pyungweesan questionnaire and four health related questionnaires(Rome II criteria of functional dyspepsia, subjective symptoms of fatigue test, beck depression inventory, state-trait anxiety inventory, etc.) using multidimensional scaling. Results and Conclusions: 1. Physical-emotional axis and acute-chronic axis were labelled in a two-dimensional scaling solution. 2. Seup-dam(濕痰) factor and sik-che(食滯) factor of food accumulation were closely related to fatigue. 3. Bi-seup(脾濕) factor of food accumulation was closely related to depression and anxiety. 4. The findings suggest that a concept of food accumulation reflects some aspects of physical fatigue and emotional depression as well as dyspepsia.

• Journal of the Korean Data and Information Science Society
• /
• 제25권6호
• /
• pp.1241-1251
• /
• 2014

국내 28개 국공립대학교를 대상으로 대학정보공시제에 근거하여 제시된 교육지표 중 연구성과에 관련된 4개의 양적평가 우량성속성 (1인당 연구비 수혜금액, 1인당 연구재단등재지 (KCI) 실적, 1인당 SCI/SCOUP급 실적, 1인당 저역서 실적)에 대해, 유사한 속성을 지닌 대학들을 유사성있는 군집끼리 분류 및 세분화하고 다차원 공간상에 시각적으로 배치시켰다. 이를 통해서 국내 28개 국공립대학은 4개 군집으로 유형화가 가능하며, 각 군집간 또는 군집내에 속한 대학들 간의 유형 및 특성을 평가할 수 있다.

• 한국윤활학회:학술대회논문집
• /
• 한국윤활학회 2000년도 제31회 춘계학술대회
• /
• pp.54-61
• /
• 2000

A method and results of classification of 4 types metallic wear debris were presented by using their color features. The color image of wear debris was used (or the initial data, and the color properties of the debris were specified by HSI color model. Particle was characterized by a set of statistical features derived from the distribution of HSI color model components. The initial feature set was optimized by a principal component analysis, and multidimensional scaling procedure was used for the definition of classification plane. It was found that five features, which include mean values of H and S, median S, skewness of distribution of S and I, allow to distinguish copper based alloys, red and dark iron oxides and steel particles. In this work, a method of probabilistic decision-making of class label assignment was proposed, which was based on the analysis of debris-coordinates distribution in the classification plane. The obtained results demonstrated a good availability for the automated wear particle analysis.

• 한국경영과학회:학술대회논문집
• /
• 한국경영과학회 1997년도 추계학술대회발표논문집; 홍익대학교, 서울; 1 Nov. 1997
• /
• pp.63-66
• /
• 1997

This paper is concerned with the current status and the prospectus of environmental investments in the manufacturing sector. A questionnaire survey was made to identify the concentrated fields of the investments. The collected data were analyzed by a multidimensional scaling method in order to provide a reasonable interpretation on the major factors which characterize the current situation and the prospectus of the investments as well as the relative position of each respondent company in a spatial map. The result tells us most respondents tend to concentrate their attention on end-of-pipe solutions due to technological tangibility and economic efficiency, etc.

• 보건행정학회지
• /
• 제5권2호
• /
• pp.127-154
• /
• 1995

The Korean hospital industry is rapidly changing along with the competition among hospitals. Until recently it was easy for hospitals to profit even without efficient management and competitive strategies. However, the increasingly intensive competition endanger their profits but also their survivals. Hospital managers have no choice but to seriously consider competitive management and marketing strategies to remain alive and prosper. This study introduces a useful methodology--perception map drawn using multidimensional scaling--for developing competitive strategies, and illustrates its application to developing a perception map of 9 Seoul-based general hospitals. We also suggest the concepts and examples of positioning strategies and patient satisfaction management system. One of the interesting findings is that the Samsung medical center which opened less than a year ago is ranked first in most aspects such as kindness, facilities, waiting time, and parking, and the second in clinical performance just after the Seoul National University Hospital.

• Communications for Statistical Applications and Methods
• /
• 제22권3호
• /
• pp.265-276
• /
• 2015

In this paper, we propose hierarchical cluster analysis and multidimensional scaling for joint distribution valued data. Information technology is increasing the necessity of statistical methods for large and complex data. Symbolic Data Analysis (SDA) is an attractive framework for the data. In SDA, target objects are typically represented by aggregated data. Most methods on SDA deal with objects represented as intervals and histograms. However, those methods cannot consider information among variables including correlation. In addition, objects represented as a joint distribution can contain information among variables. Therefore, we focus on methods for joint distribution valued data. We expanded the two well-known exploratory methods using the dissimilarities adopted Hall Type relative projection index among joint distribution valued data. We show a simulation study and an actual example of proposed methods.

• 한국의류학회지
• /
• 제26권1호
• /
• pp.83-94
• /
• 2002

This study was intended to identify fabric impact on decision-making process for clothing purchase, to determine evaluation factors of clothing, and to analyze consumer's preference for fabric on clothing purchase. 396 questionnaires distributed to college students were analyzed by descriptive statistics, oneway ANOVA, correlation, factor analysis and multidimensional scaling. The results are as follows; (1) Fabric impacted on the pre-purchase evaluation and the post-purchase process. (2) 4 factors - physical properties, outer-consciousness, self-satisfaction, and appropriateness- were determined as evaluation factors. Though fabric was included in the physical properties, fabric presented high correlations with other evaluative elements. (3) The most preferred fabric was being composed of natural fiber in fiber contents and having softness in sensation. As a result of multidimensional scaling, 2 dimensions of fabric sensation were developed as 'soft-hard'and 'thin-thick'.

• 한국HCI학회:학술대회논문집
• /
• 한국HCI학회 2008년도 학술대회 2부
• /
• pp.399-404
• /
• 2008

사용자 중심의 메뉴 기반 인터페이스를 설계하기 위해서는 인간의 지식 구조를 이해하는 것이 중요하다. 인간의 지식 구조를 이해하게 되면, 인터페이스를 통해서 전달된 자극들이 만들어낸 개념들이 어떠한 관계를 가지고 정신 모형(mental model)을 형성하고 있는지 알 수 있다. 인간의 지식 구조는 MDS (Multidimensional Scaling)과 Trajectory Mapping을 이용하여 Visual Concept Map 으로 나타낼 수 있고, 이것을 바탕으로 인간의 지식구조를 시각적으로 이해할 수 있다. MDS 는 인간의 머릿속에 자리잡고 있는 개념들의 상대적 위치를 알려주고, Trajectory Mapping 은 개념들 간의 연결 상태를 보여준다. 즉, Trajectory Mapping 을 통하여 개념들 간악 인지적 정보를 알 수 있다. 본 연구에서는 MDS 와 Trajectory Mapping 을 이용하여 핸드폰 메뉴로부터 전달 받은 시각적 자극들에 악해 형성된 개념들에 대한 인간의 지식 구조를 Visual Concept Map 으로 시각화하였다. 그리고 이렇게 시각화된 지식 구조를 바탕으로 메뉴 구조를 개발하였다. 본 연구 결과, MDS 와 Trajectory Mapping 을 이용한 인간의 지식 구조의 시각화는 사용자 중심의 메뉴 기반 인터페이스를 설계하는데 유용하게 쓰일 수 있을 것으로 보인다.