• 정보관리학회지
• /
• 제25권1호
• /
• pp.211-233
• /
• 2008

로치오 알고리즘에 기반한 자동분류의 성능 향상을 위하여 두 개의 실험집단(LISA, Reuters-21578)을 대상으로 여러 가중치부여 기법들을 검토하였다. 먼저, 가중치 산출에 사용되는 요소를 크게 문헌요소(document factor), 문헌집합 요소(document set factor), 범주 요소(category factor)의 세 가지로 구분하여 각 요소별 단일 가중치부석 기법의 분류 성능을 살펴보았고, 다음으로 이들 가중치 요소들 간의 조합 가중치부여 기법에 따른 성능을 알아보았다. 그 결과, 각 요소별로는 범주 요소가 가장 좋은 성능을 보였고, 그 다음이 문헌집합 요소, 그리고 문헌 요소가 가장 낮은 성능을 나타냈다. 가중치 요소 간의 조합에서는 일반적으로 사용되는 문헌 요소와 문헌집합 요소의 조합 가중치(tfidf or ltfidf)와 함께 문헌 요소를 포함하는 조합(tf*cat or ltf*cat) 보다는, 오히려 문헌 요소를 배제하고 문헌 집합 요소를 범주 요소와 결합한 조합 가중치 기법(idf*cat)이 가장 좋은 성능을 보였다. 그러나 실험집단 측면에서 단일 가중치와 조합 가중치를 서로 비교한 결과에 따르면, LISA에서 범주 요소만을 사용한 단일 가중치(cat only)가 가장 좋은 성능을 보인 반면, Reuters-21578에서는 문헌집합 요소와 범주 요소간의 조합 가중치(idf*cat)의 성능이 가장 우수한 것으로 나타났다. 따라서 가중치부여 기법에 대한 실제 적용에서는, 분류 대상이 되는 문헌집단 내 범주들의 특성을 신중하게 고려할 필요가 있다.

• International Journal of Contents
• /
• 제1권2호
• /
• pp.26-30
• /
• 2005

According to the fast growth of information on the Internet, it is becoming increasingly difficult to find and organize useful information. To reduce information overload, it needs to exploit automatic text classification for handling enormous documents. Support Vector Machine (SVM) is a model that is calculated as a weighted sum of kernel function outputs. This paper describes a document classifier for web documents in the fields of Information Technology and uses SVM to learn a model, which is constructed from the training sets and its representative terms. The basic idea is to exploit the representative terms meaning distribution in coherent thematic texts of each category by simple statistics methods. Vector-space model is applied to represent documents in the categories by using feature selection scheme based on TFiDF. We apply a category factor which represents effects in category of any term to the feature selection. Experiments show the results of categorization and the correlation of vector length.

• 한국의류학회지
• /
• 제35권12호
• /
• pp.1454-1465
• /
• 2011

Menswear body types are often labeled on garments (to indicate how the garments are designed to fit) with indicators of a size category such as regular, portly, and stout, athletic, or big and tall. A drop (relationships between the chest and waist girths) is related to the fit of a tailored suit. However, current standards are not designed for various drops or body types. There is not enough information of categorizing men's body shapes for the apparel sizing systems. In this article, a set of men's data from SizeUSA sizing survey was analyzed to investigate men's body shapes and drops. Factor analysis and a cluster analysis method were used to categorize men's body shapes. In the results, twenty-five variables were selected through the factor analysis and found four factors: girth factor, height factor, torso girth factor, and slope degree factor. According to the factor and cluster analysis, various body shapes were found: Slim Shape (SS - tall ectomorphy), Heavy Shape (HS - athletic, big & tall, endomorphy and mesomorphy), Slant Inverted Triangle Shape (SITS - regular, slight ectomorphy and slight mesomorphy weight range from normal to slightly overweight), Short Round Top Shape (SRTS - portly and stout, endomorphy). Body shapes were related to fitting categories. SS and HS were related to big & tall fitting category. SITS was related to regular. SRTS was related to portly and stout. Shape 1 (31%) and Shape 2 (26%) were related to current big & tall category. Shape 3 (34%) were related to regular. Shape 4 (9%) were in portly and stout category. ASTM D 6240 standard was the only available standard that presented a regular fitting category. Various drops were found within a same chest size group; however, this study revealed great variances of drops by body shape.

• 한국의류학회지
• /
• 제16권4호
• /
• pp.371-377
• /
• 1992

The purposes of the study were 1) to extend the cognitive categorization theory in an attempt to explain the of garment category, fashionability, and wearer's body types on impression formation, and 2) to find out structures of wearer's impressional dimension and wearer's professional image. The research included a quasi-experiment and survey. The experimental design was a $2^{3}$full factorial design of 3 independent variables. The experimental materials developed for the study were a set of stimuli and a response scale. The stimuli consisted of 8 drawings made by 3 independent variables (garment category, fashion level, wearer's body type). Result were as follows: 1) Garment category, fashionability and wearer's body type had significant effects on impression of the 5 factors-evaluation, potency, appearance, sociability and good-bad, with exception of wearer's body type which was nonsignificant to the potency factor. 2) Garment category was most effective on the evaluation and the potency. However wearer's body type was most effect on the appearance factor and fashionability variable was most effective on the good-bad factor. It was conclued that the results supported the cognitive categorization theory on impression formation and a cognitive categorization hypothesis of clothes.

• Journal of Information Processing Systems
• /
• 제16권4호
• /
• pp.784-794
• /
• 2020

In order to effectively evaluate the urban water security, the study investigates a novel system to assess factors that impact urban water security and builds an urban water poverty evaluation index system. Based on the contribution rates of Resource, Access, Capacity, Use, and Environment, the study adopts the Water Poverty Index (WPI) model to evaluate the water poverty levels of 14 cities in Gansu during 2011-2018 and uses the least variance method to evaluate water poverty space drive types. The case study results show that the water poverty space drive types of 14 cites fall into four categories. The first category is the dual factor dominant type driven by environment and resources, which includes Lanzhou, Qingyang, Jiuquan, and Jiayuguan. The second category is the three-factor dominant type driven by Access, Use, and Capability, which includes Longnan, Linxia, and Gannan. The third category is the four-factor dominant type driven by Resource, Access, Capability, and Environment, which includes Jinchang, Pingliang, Wuwei, Baiyin, and Zhangye. The fourth category is the five-factor dominant type, which includes Tianshui and Dingxi. The driven types impacting the urban water security factors reflected by the WPI and its model are clear and accurate. The divisions of the urban water security level supply a reliable theoretical and numerical basis for an urban water security early warning mechanism.

• 보건의료산업학회지
• /
• 제5권2호
• /
• pp.77-89
• /
• 2011

This study conducted a secondary analysis by using original data of performed by Korea Institute for Health and Social Affairs to know factors affecting determinants of health using Lalonde model for the adults aged over 19 years living in Korea. The survey was conducted in 2009 and it evaluated finally 5,867 cases by excluding cases with no answer or a wrong answer. This study model adopted two categories of instrument measure health were objective (Average remaining lifetime) and subjective(EQ-5D) health status. The health determinants included in this study could be divided in to four categories, which were human biology, environment, lifestyle, and health care organization. The results were as follows. In the factors affecting average remaining lifetime, human biology were sex, ages, BMI, showed statistically significant difference, environment category were merry status, education showed statistically significant difference, lifestyle category were exercise, drunks showed statistically significant difference and health care organization category were vaccination, health screening showed statistically significant difference. In the factors affecting EQ-5D, human biology category and health care organization category showed with same average remaining lifetime, environment category were merry status, education, income showed statistically significant difference and lifestyle category were exercise, drunks, stress showed statistically significant difference. The results demonstrated that the best powerful factor was life style category and environment category, the least factor was health care organization category. So lifestyle style and environment category should be considered for the future health plan, budget allocation and the priority in the health care.

• 한국경영과학회지
• /
• 제33권4호
• /
• pp.1-12
• /
• 2008

The study suggests an answer to the question of what determines category diversification of Internet portals in Korea. First, as external factors, competition intensity and market growth are hypothesized to have influence on the degree of category diversification. Second, an internal factor, user loyalty to portals, is hypothesized to influence negatively category diversification. The study performed empirical analysis based on weekly portal-specific panel data of eighteen internet portals in Korea during the period between 2001 and 2004. The result shows that category diversification increases as competition intensity increases, and that category diversification decreases as user loyalty increases. There was no effect of market-level growth rate on category diversification.

• 지식경영연구
• /
• 제6권2호
• /
• pp.105-118
• /
• 2005

The future will see all industries become technology-driven in the competitive global market place. Firms with deep technological roots and innovation strategies have some advantages. Business valuation of technology is critical to the future of firm's business. In this situation widely used scoring valuation is not enough to evaluate relative business competitiveness associated with technology and to assign its relative ranking category. Therefore, a more useful and comprehensive new valuation approach, which is called business composite index, is needed to complement and to enhance the existing scoring valuation approach. In this research, statistical factor analysis is applied to determine the common factors and to estimate associated weights. And business composite index, which is a kind of weighted scoring method, is derived based on the results of factor analysis. This research shows that business composite index is considered very useful to measure the business relative strength of individual technology and also to assign its relative ranking category instead of absolute ranking based on scoring valuation approach.

• 부동산연구
• /
• 제27권4호
• /
• pp.7-20
• /
• 2017

본 연구는 노후산업단지의 쇠퇴영향요인을 진단하고 그 특성을 바탕으로 노후산업단지를 유형화하였으며 연구 결과를 노후산업단지의 재생방안으로 연계하고자 하였다. 이를 위해 전국 산업단지를 대상으로 착공시점을 기준으로 20년이 경과한 94개소 노후산업단지에 대해 17개 지표를 측정 및 분석하였으며, 그 중 장치산업단지 5개소를 제외한 89개소 노후산업단지의 15개 지표에 대해 요인분석을 실시하였다. 요인분석 결과, 15개 지표는 5개 요인으로 분류되었으며 요인1은 '시가화 가능성', 요인2는 '생산 효율성', 요인3은 '기반시설 쾌적성', 요인4는 '입지 잠재성', 요인5는 '지원시설 충족성'으로 구분할 수 있었다. 이를 이용하여 5개 요인점수의 하위 25%에 해당하는 산업단지를 추출하고 어떠한 쇠퇴영향요인이 잠재하고 있는지를 살펴보았다. 요인분석 결과 시사점은 '시가화 가능성'은 산업단지내 입주 기업업종과 토지이용과의 관련성을 내포하고 있다. '생산효율성'분야는 기업들의 생산성을 높일 수 있는 효율적인 지원방안이 모색될 필요가 있다. '기반시설 쾌적성'요인은 자생적인 재생유도보다는 정부 및 지자체가 직접 관여하여 물리적 정비가 이루어져야 할 것이다. '입지잠재성' 요인은 광역급 인프라 구축, 산단내 기반시설의 개선 및 정비, 지가상승 등을 복합적으로 고려하여 고부가가치 산업 유치를 고려하거나 산업구조고도화를 위한 업종변경 등 장기적이고 전략적인 접근이 필요할 것이다. 마지막으로 '지원시설 충족성'은 필요한 지원시설 공급을 위해 노후산업단지의 정확한 쇠퇴진단을 통해서 유휴부지를 발굴하거나 국 공유지를 활용할 수 있는 방안이 모색될 필요가 있겠다.

• Nutrition Research and Practice
• /
• 제6권2호
• /
• pp.162-168
• /
• 2012

Vitamin D deficiency is a risk factor for metabolic syndromes. We examined whether vitamin D deficiency altered the prevalence of cardiovascular disease (CVD) in older Koreans. Cross-sectional analysis of data from the Korean National Health and Nutrition Examination Survey IV 2008-2009 was used to examine the association between serum 25-hydroxyvitamin D (25(OH)D) levels and the prevalence of CVD in a representative population-based sample of 5,559 men and women aged ${\geq}50$ years. CVD was defined as angina pectoris, myocardial infarction, or stroke. The prevalence of CVD (7.0%) in the older Korean population was lower than that in the older US population, although average serum 25(OH)D levels were much lower in the Korean population. Additionally, serum 25(OH)D levels did not differ significantly between the CVD and non-CVD groups. However, subjects in the lowest category (< 25 nmol/l) of serum 25(OH)D level had the greatest prevalence of CVD, about two-fold higher than subjects in the highest category (> 75 nmol/l), after adjusting for age, gender, body mass index, education level, residence location, and region. The prevalence of other risk factors for CVD, including higher waist circumference, fasting glucose, low-density lipoprotein (LDL) cholesterol, and triglyceride levels and lower high-density lipoprotein (HDL) cholesterol levels, was also higher among subjects in the lowest category than among those in the highest category. In conclusion, low serum 25(OH)D may be an independent risk factor for CVD in older Koreans.