• 한국멀티미디어학회논문지
• /
• 제4권2호
• /
• pp.171-181
• /
• 2001

기존의 베이지만 문서 분류를 위한 단어 군집 방법은 많은 시간과 노력을 요구하며, 단어 간의 의미 관계를 정확하게 반영하지 못하는 문제점이 있다. 본 논문에서는 마이닝 기법으로 구축된 연관 단어 지식 베이스를 기반으로 하는 베이지안 문서 분류 방법을 제안한다. 제안된 베이지안 문서 분류 방법은 문서를 분류하기 전에 훈련 문서를 사용하여 가중치가 부여된 연관 단어 지 식 베이스를 구축한다. 그 다음으로, 베이지안 확률을 이용하는 분류자는 구축된 연관 단어 지식 베이스를 기반으로 문서를 클래스별로 분류한다. 제안된 방법의 성능을 평가하기 위해, 상호 정보 계산에 의한 단어 사전을 이유한 가중치가 부여된 베이지안 문서 분류 방법, 가중치가 부여된 베이지안 분류 방법, 기존의 단순 베이지안 분류 방법과 비교하였다. 그 결과, 연관 단어 지식 베이스에 기반한 가중치가 부여된 베이지안 분류 방법이 상호 정보에 의한 단어 사진을 이용하는 가중치가 부여된 베이지안 분류 방법보다는 0.87%, 가중치가 부여된 베이지안 분류 방법보다는 2.77%, 단순 베이지안 방법보다는 5.97% 높은 성능 차이를 보였다.

• 한국과학교육학회지
• /
• 제17권2호
• /
• pp.163-178
• /
• 1997

The purpose of this study is to investigate the effect of categorizing activities in lessons on improving critical thinking to meet energy environment issues in every day situation, supposing that there are not only scientific concepts but also critical thinking ability in scientific literacy to meet social controversies related with science intelligently. Categorizing Activity Program was developed and applied to the 10th grades(n=51) in Seoul for about one month. The program was consisted of two domains. They studied science concepts of various aspects of science, technology and society related with energy and environment in the first and second domain repectively, in the while, two critical tasks which include articles from newspapers and magazines were assigned to them for the development and evaluation of critical thinking abilities. The scores of critical thinking ability, the cognitive element, and critical thinking inclination, the affective element, were increased meaningfully(p<.05). In conclusion, categorizing activity as a strategy of concept attainment was effective in improving critical thinking for seeing various aspects with various view points needed in controversial issues related with energy and environment.

• 한국지능정보시스템학회:학술대회논문집
• /
• 한국지능정보시스템학회 2000년도 춘계정기학술대회 e-Business를 위한 지능형 정보기술 / 한국지능정보시스템학회
• /
• pp.333-340
• /
• 2000

Research on group decisions and electronic meeting systems have been increasing rapidly according to the widespread of Internet technology. Although various issues have been raised in empirical research, we will try to solve an issue on idea categorizing in the group decision making process of electronic meeting systems. Idea categorizing used at existing group decision support systems was performed in a top-down procedure and mostly b participants; manual work. This resulted in tacking as long in idea categorizing as it does for idea generating clustering an idea in multiple categories, and identifying almost similar redundant categories. However such methods have critical limitation in the electronic meeting systems, we suggest an intelligent idea categorizing methodology which is a bottom-up approach. This method consists of steps to present idea using keywords, identifying keywords' affinity, computing similarity among ideas, and clustering ideas. This methodology allows participants to interact iteratively for clear manifestation of ambiguous ideas. We also developed a prototype system, IIC (intelligent idea categorizer) and evaluated its performance using the comparision experimetn with other systems. IIC is not a general purposed system, but it produces a good result in a given specific domain.

• 지능정보연구
• /
• 제6권2호
• /
• pp.63-76
• /
• 2000

Research on group decisions and electroinc meeting systems have been increasing rapidly according to the widespread of Internet technology. Although various issues have been raised in empirical research, we will try to solve an issue on idea categorizing in the group decision making process of elecronic meeting systems. Idea categorizing used at existing group decision support systems was performed in a top-down procedure and mostly participants\` by manual work. This resulted in tacking as long in idea categorizing as it does for idea generating, clustering an idea in multiple categories, and identifying almost similar redundant categories. However such methods have critical limitation in the electronic meeting systems, we suggest an intelligent idea categorizing methodology which is a bottom-up approach. This method consists of steps to present idea using keywords, identifying keywords\` affinity, computing similarity among ideas, and clustering ideas. This methodology allows participants to interact iteratively for clear manifestation of ambiguous ideas. We also developed a prototype system, IIC (intelligent idea categorizer) and evaluated its performance using the comparision experimetn with other systems. IIC is not a general purposed system, but it produces a good result in a given specific domain.

• 한국철도학회:학술대회논문집
• /
• 한국철도학회 2009년도 춘계학술대회 논문집
• /
• pp.581-588
• /
• 2009

With the development of IT industry and formation of web-based knowledge sharing platform, a variety of railway-related information services on the web have emerged, ranging from personal blogs to dedicated portal sites, as in the other sectors. These services are contributing to advancing railway industry after all. As far as it is concerned with specific areas such as railway sector, the internet users are hardly expected to avail satisfactory results in acquiring customized information from the access, as the information served varies on the intension of the web site operator or relevant agency, and indexing categories and sub-categories is not easy to work out in a straight manner. This study will review on the feasibility of standardizing categories and sub-categories for railway industry information on the web, and present optimum categorization and sub-categorization approach for the most satisfactory results when searched, ultimately aiming at laying a foundation to satisfy the wide spectrum of users' need for railway information.

• 한국의사학회지
• /
• 제32권2호
• /
• pp.79-90
• /
• 2019

In many periods of Korean history, state-sponsored medical books played a crucial role in terms of distributing medical knowledge as well as systemizing medical information. This study uses comparative analysis to examine the tables on contents of state-sponsored medical publications in Korea. These tables of contents reveal the placement and categorization of medical knowledge, which implicates the ways in which diseases were classified. Historically, Korean medicine has been influenced by Chinese medicine, and at the same time, it has made steady efforts to localize Chinese medicine. This paper argues that Korean medicine adopted the Chinese styles of categorizing medical knowledge in the middle of 15th century for the first time and shows the tendency to Koreanize medical knowledge through the early 17th century. In the 18th century the Complete Records of Medicine (醫部全錄) shows the trace of referring the style of Korean medical book, the Treasured Mirror of Eastern Medicine (東醫寶鑑) in terms of categorizing medical knowledge.

• 한국초등수학교육학회지
• /
• 제21권2호
• /
• pp.365-389
• /
• 2017

본 연구에서는 초등 영재학생들의 원순열 과제 해결 과정을 분석하여 교수학적 시사점을 도출하는 데 목적을 두었다. 구체적으로, 본 연구에서는 초등 영재학생들에게 원순열 과제를 제공하여 이 학생들의 해결 과정을 표현, 세기 과정, 결과 집합구성 방식을 통하여 분석하였다. 연구 결과 원순열 과제를 해결하는 과정에서 일부 학생들이 유추를 활용하는 장면이 확인되었으며, 학생들은 가능한 결과들의 범주화와 재범주화 과정에서, 그리고 유추의 적절하지 않은 활용으로 인하여 원순열 과제해결에 어려움을 겪는 것으로 확인되었다.

• 한국실내디자인학회논문집
• /
• 제26호
• /
• pp.42-48
• /
• 2001

This study is on the relations between space boundary system and spatial effects. The system is consist of circulation axis & territory and vision axis & vision limit. The former is the spatial characteristic and the later is the time one. The purpose of this case study is confirm the correlation of the both and the spatial effect which is caused by space boundary system. Boundary is enable us to cognize 'territory' and intermediary of each territories. The facts that forms space boundary system are circulation axis & territory and vision axis & vision limit. The space boundary system could be categorized by congregation of these facts. and categorizing is determined with agreement degree of each couple of facts. Categorizing facts on the space boundary system are relevant to spatial effect, especially territory, directness, continuity and concentration.

• 한국농림기상학회:학술대회논문집
• /
• 한국농림기상학회 2014년도 추계 학술발표논문집
• /
• pp.61-73
• /
• 2014

• 한국전자거래학회지
• /
• 제25권3호
• /
• pp.15-40
• /
• 2020

모바일 애플리케이션 서비스 시장의 폭발적으로 성장함에 따라 애플리케이션 서비스를 고객과 개발자 관점에서 분류하는 것이 필요한 실정이다. 그러나 모바일 애플리케이션 서비스의 체계적 분류에 관한 연구는 제한적이다. 이에 본 연구에서는 네트워크 모듈성 분석을 통하여 모바일 애플리케이션 서비스의 분류하고 하위 카테고리를 제안하고자 한다. 구글플레이(GooglePlay)를 통해 총 1,607개의 헬스케어 관련 애플리케이션 서비스를 수집한 후 각 애플리케이션 서비스의 설명(description) 텍스트를 활용하여 유사도를 측정하고 이를 바탕으로 네트워크 분석을 수행하였다. 모듈성 분석을 수행하여 전체 네트워크의 커뮤니티를 탐지한 후, 각 클러스터를 기반으로 서비스 분류법을 도출한다. 이번 연구는 모바일 애플리케이션 서비스를 체계적으로 탐색하고자 하는 고객과 모바일 애플리케이션 서비스의 트렌드를 분석하고자 하는 개발자 모두에게 도움이 되는 서비스 분류에 대한 체계적인 접근방식이 될 것으로 기대된다.