• 디지털콘텐츠학회 논문지
• /
• 제12권3호
• /
• pp.339-345
• /
• 2011

군집화는 주어진 데이터를 분할하여 데이터 속에 숨겨져 있는 의미를 자동으로 발견하는 방법이다. k-means는 간단하고 빠른 군집화 알고리즘 중의 하나이다. 군집의 수 k는 군집화를 수행하는데 매우 중요한 요소이며, k의 값에 의해 군집화 결과가 달라진다. 본 논문에서는 반복적인 k-means 수행과 군집의 품질을 평가하는 외부 군집 연관 기준 정보를 결합하여 최적의 군집수를 결정하는 방법을 제안한다. 실험 결과 기존의 방법들에 비하여 제안하는 방법이 군집수의 정확성 측면에서 우수한 성능을 보였다.

• 복식문화연구
• /
• 제10권4호
• /
• pp.364-376
• /
• 2002

The Main objective of this study was to investigate the relationship between shopping orientations and Knit wear Buying Behavior of college female students. A questionnaire was developed to measure knit wear purchasing motives, fashion information sources of knit wear, evaluation criteria of knit wear product, and general clothing buying behavior. The questionnaire was administered to 505 college female students in Chonbuk and Chonnam. The data was analyzed using percentage, frequency, mean, factor analysis, Cluster Analysis and ANOVA, Duncan Multiple Range test. The results of the study were as follows: 1. The college female students were classified into fifth subdivisions by the cluster analysis; convenient shopping group, recreational shopping group, self-confident shopping group, those of Fashion-pursuit group, economic shopping group. 2. The knit wear purchasing motives of consumers were significantly different according to shopping orientation subdivision in social, personal, rational. 3. In the case of fashion information sources of knit wear, significant differences were found according to shopping orientation subdivision in mass media information, information by marketer, mail order advertisements, information by consumer. 4. The evaluation criteria of knit wear product of consumers were significantly different depending on shopping orientation subdivision in esthetic, practicality, individual expression, external criterion. 5. In the case of dissatisfactory factors for wearing knit wear product, significant differences were found according to shopping orientation subdivision. 6. In the case of asking factors to the manufactures of knit wear product, significant differences were found according to shopping orientation subdivision.

• 한국의류학회지
• /
• 제29권2호
• /
• pp.298-306
• /
• 2005

The Main objective of this study was to investigate the relationship between lifestyle and clothing buying behavior of college female students in Japan. A questionnaire was developed to measure clothing urchasing motives, fashion information sources, evaluation criteria of clothing, store attribute and lifestyle, The questionnaire was administered to 131 female college students in Tokyo of Japan. the data was analyzed using percentage, frequency, mean, factor analysis, Cluster Analysis and ANOVA, Duncan Multiple Range test. The results of the study were as follows : 1. The female college students were classified into fourth subdivisions by the cluster analysis; rational group, economic group, progressive group, fashion-oriented group. 2. The clothing purchasing motives o consumers were significantly different according to lifestyle subdivision in social, personal. 3. In the case of fshion information sources, significant differences were found according to lifestyle subdivision in mass media information, information by marketer, information by consumer. 4. The evaluation criteria of clothing were significantly different depending on lifestyle subdivision in esthetic, quality and management, external criterion. 5. The store attribute were significantly different depending on lifestyle subdivision in convenience, service and atmosphere of store.

• 한국의류학회지
• /
• 제27권6호
• /
• pp.601-611
• /
• 2003

The main objective of this study was to investigate the relationship between benefits segmentation and knitwear purchasing behavior of college female students. A questionnaire was developed to measure benefits segmentation, knit wear purchasing behavior. The questionnaire was administered to 505 college female students in Chonbuk and Chonnam. The data was analyzed using percentage, frequency, mean, factor analysis, cluster analysis and ANOVA, Duncan multiple range test. The results of the study were as follows: The college female students were classified into four subdivisions by the cluster analysis: recreation pursuit group, fashion pursuit group, individuality pursuit group, self-improvement pursuit group on the basis of pursuit benefit factors. The knitwear purchasing motives of consumers were significantly different according to pursuit benefit subdivision. The individuality pursuit group was the highest user of mass media fashion information sources. The fashion pursuit group used purchasing experience and advice of others less than other groups. Consumers' evaluation criteria of knitwear products were significantly different depending on pursuit benefit subdivision in design and coordination, goods traits, practicality, individual expression, and external criterion. The other groups used purchasing experience and advice of others more than the fashion pursuit group.