• Communications for Statistical Applications and Methods
• /
• 제22권1호
• /
• pp.55-67
• /
• 2015

An important problem in cluster analysis is the selection of variables that define cluster structure that also eliminate noisy variables that mask cluster structure; in addition, outlier detection is a fundamental task for cluster analysis. Here we provide an automated K-means clustering process combined with variable selection and outlier identification. The Automated K-means clustering procedure consists of three processes: (i) automatically calculating the cluster number and initial cluster center whenever a new variable is added, (ii) identifying outliers for each cluster depending on used variables, (iii) selecting variables defining cluster structure in a forward manner. To select variables, we applied VS-KM (variable-selection heuristic for K-means clustering) procedure (Brusco and Cradit, 2001). To identify outliers, we used a hybrid approach combining a clustering based approach and distance based approach. Simulation results indicate that the proposed automated K-means clustering procedure is effective to select variables and identify outliers. The implemented R program can be obtained at http://www.knou.ac.kr/~sskim/SVOKmeans.r.

• 한국의상디자인학회지
• /
• 제2권1호
• /
• pp.51-74
• /
• 2000

The purposes of the study were to investigate the differences of female students' clothing selection criteria and their life styles according to their demographic data and to examine the differences of their clothing selection criteria according to their life styles. The data were collected from 400 female college students in Chungju city through self-administerd questionnaires, and were analyzed by frequencies, Cronbach' s α, F­test, Factor Analysis, Cluster Analysis, one way ANOVA and Duncan Test. The results of the study were as follows: There were significant differences between variables of clothing selection criteria according to student's major, father's education level, family's monthly income, student's monthly expenditure on clothing and her companion when purchasing her clothing. Life styles were classified five types. The dimensions of life style were significantly different according to student's major and monthly expenditure on clothing. There were significantly different between life style dimensions and clothing selection criteria.

• 한국지진공학회논문집
• /
• 제21권4호
• /
• pp.171-179
• /
• 2017

For estimating the seismic demand of buildings, most seismic design provisions permit conducting linear and nonlinear response history analysis. In order to obtain reliable results from response history analyses, a proper selection of input ground motions is required. In this study, an accurate algorithm for selecting and scaling ground motions is proposed, which satisfies the ASCE 7-10 criteria. In the proposed algorithm, a desired number of ground motions are sequentially scaled and selected from a ground motion library without iterations.

• 한국조리학회지
• /
• 제10권3호
• /
• pp.119-134
• /
• 2004

Now days, the life style of people is getting more scientific and more specialized, so food habit as well as food culture are a measure of cultural level of a country. Studies on consumer behavioral model show that food habit is closely related to consumer preference due to changing life pattern and increasing family income. Therefore, The definition of the impact of menu characteristics on customer menu selection is the object of this study. For that purpose, some attempts are made: First, discuss the theories on Korean food and customer purchasing behavior as a standard of analysis. Second, find out if there are any differences in customer menu-selection factors for Korean restaurantin in a hotel. Third, make an empirical analysis of menu-selection factors for Korean in a hotel to suggest which direction it should go forward. Fourth, analyze the relationship between demographic characteristics and menu-selection factors.

• 한국관광식음료학회지:관광식음료경영연구
• /
• 제15권2호
• /
• pp.203-218
• /
• 2004

The purpose of this study was to identify the selection attributes of family restaurants according to the consumers' use types with the main focus on the family restaurants in the Busan. Area Nine factors in total were generated in order to verify the hypotheses of this study through the factor analysis of the selection attributes of the family restaurants. The differences between the various selection factors for the family restaurants according to the decision-making, the preparation period, and the visiting frequency through the analysis of the diffcrence from the selection factors for the family restaurants according to the use types.

• 산업경영시스템학회지
• /
• 제38권2호
• /
• pp.82-90
• /
• 2015

Location selection of distribution centers is a crucial task for logistics operators and key decision makers of an organization. This is a multi-criteria decision making (MCDM) process which includes both quantitative and qualitative criteria. In order to propose an optimized location selection model, this research suggests a hierarchical group of evaluation criteria : 5 major criteria with 15 sub-criteria. The MCDM approach presented in this research, by integrating Grey Relational Analysis (GRA) with Analytic Hierarchy Process (AHP), tends to rectify the overall quality and uncertainty of the values of evaluation criteria. An example of a location selection case in Korea is illustrated in this study to show the effectiveness of this method.

• 한국관광식음료학회지:관광식음료경영연구
• /
• 제16권1호
• /
• pp.93-112
• /
• 2005

The purpose of this study was to identify the selection attributes of family restaurants according to the consumers' use types with the main focus on the family restaurants in Busan Area. Nine factors in total were generated in order to verify the hypotheses of this study through the factor analysis of the selection attributes of the family restaurants. The differences between the various selection factors for the family restaurants according to the decision-making, the preparation period, and the visiting frequency through the analysis of the difference from the selection factors for the family restaurants according to the use types.

• 한국컴퓨터정보학회논문지
• /
• 제24권2호
• /
• pp.171-177
• /
• 2019

This paper aims to find the most effective feature selection method for the sake of opinion mining tasks. Basically, opinion mining tasks belong to sentiment analysis, which is to categorize opinions of the online texts into positive and negative from a text mining point of view. By using the five product groups dataset such as apparel, books, DVDs, electronics, and kitchen, TF-IDF and Bag-of-Words(BOW) fare calculated to form the product review feature sets. Next, we applied the feature selection methods to see which method reveals most robust results. The results show that the stacking classifier based on those features out of applying Information Gain feature selection method yields best result.

• 한국유기농업학회지
• /
• 제25권4호
• /
• pp.663-677
• /
• 2017

As Korean food service franchise companies sought to advance into around 2,000 new foreign markets, the importance of global management was emphasized. They intensively expanded into Chinese and American markets in 2015 and these two markets account for approximately 40% of total food service franchise companies in foreign countries. Although Japan has huge franchise market, Korean food service franchise companies in Japan only account for 5% of total franchise companies in Asian countries. The purpose of this study is to analyze the relationship between food service franchise selection factors, brand loyalty, and revisit intention of Japanese consumers using Korean food service franchise companies in Japanese food service market, and based on the analysis results, draw the implications for the expansion of Korean food service franchise companies into the Japanese market. Food service franchise selection factors is defined as service and cleanliness, taste, safety and reliability, cost and convenience, and professionalism. The study results can be summarized as follows. First, analysis was performed to identify the effects of food service franchise selection factors on the brand loyalty, it showed that five food service franchise selection factors including professionalism, service and cleanliness, cost and convenience had positive (+) effects on the brand loyalty. One of the most important factors influencing the brand loyalty is professionalism. In order to raise food service franchise's professionalism, it is necessary for the food service franchise companies to establish stronger strategies containing professional operation systems and services compared to general restaurants. Second, analysis was performed to identify the effects of food service franchise selection factors on revisit intention, five food service franchise selection factors, service and cleanliness, safety and reliability, and cost and convenience had positive (+) effects on revisit intention. One of the most important factors influencing revisit intention is safety and reliability. Thus, in order to raise safety and reliability it is important to form trust with consumers by properly utilizing systems of food hygiene and food safety accreditation.

• 정보처리학회논문지B
• /
• 제14B권2호
• /
• pp.135-140
• /
• 2007

특징선택은 문제 영역에서 관찰된 다차원데이터로부터 데이터가 묘사하는 구조를 잘 반영하는 속성을 선택하여 효과적인 실험 데이터를 구성하는 데이터 준비과정이다. 이 과정은 문서분류, 영상인식, 유전자 선택 분야에서의 같은 분류시스템의 성능향상에 중요한 구성요소로서 상관관계 기법, 차원축소 및 상호 정보 처리 등의 통계학이나 정보이론의 접근방법을 중심으로 연구되어왔다. 이와 같은 선택 분야의 연구는 다루는 데이터의 양이 방대해지고 복잡해지면서 더욱 중요시 되고 있다. 본 논문에서는 데이터가 가지는 특성을 반영하면서 새로운 데이터에 대하여 일반화 할 수 있는 특징선택 방법을 제안하고자 한다. 준비된 데이터의 각 속성 데이터에 대하여 퍼지 클러스터 분석에 의하여 최적의 클러스터 정보를 얻고 이를 바탕으로 근접성과 분리성의 경로를 측정하여 그 값에 따라 특징을 선택하는 매카니즘을 제공한다. 제안된 방법을 실세계의 컴퓨터 바이러스 분류에 적용하여 기존의 대비에 의한 휴리스틱 방법에 의해 선택된 데이터를 가지고 분류한 것과 비교하고자 한다. 이를 통하여 주어진 특징에 시연을 부여할 수 있고 효과적으로 특징을 선택하여 시스템의 성능을 향상 시킬 수 있음을 확인한다.