• Proceedings of the Korea Information Processing Society Conference
• /
• 2021.05a
• /
• pp.443-446
• /
• 2021

의약품에 대한 안전성 정보 수집과 관리는 온라인, 오프라인을 통해 약물 이상 사례를 보고받는 형태로 진행되고 있다. 하지만 소비자들의 자발적인 참여로 이루어지므로 실제 발생하는 약물 부작용보다 데이터가 현저히 적다는 단점이 존재한다. 본 논문에서는 약물 이상 데이터 희소성 문제를 해결 할 수 있도록 소셜 미디어에서 약물 부작용 표현을 찾을 수 있도록 하였다. 소셜 미디어의 경우에는 표준 약물 부작용 용어를 사용하기보다는 일반인들이 자연어로 표현한 경우가 많으므로 개체명 인식 기법을 이용해 부작용을 추출할 수 있는 모델을 개발하였다. 또한 추출된 부작용 표현을 표준용어로 분류할 수 있는 모델을 제시하였다. 실험 결과 제안한 두 가지 모델은 0.9 이상의 정확도를 얻을 수 있었으며, 일반 사용자들이 자연어로 표현한 약물 부작용 표현을 효과적으로 찾아내고 표준 부작용 용어로 매핑할 수 있음을 보여준다.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.16 no.6
• /
• pp.4056-4066
• /
• 2015

For understanding of terminology related to u-Health and activating u-Health industry, it is required to develop u-Health standard terminology for communication. The purpose of this study is to develop u-Health standard terminology and provides guidelines for terminology standardization in order to develop the u-Health standard terminology. We finally developed the 187 u-Health standard terminology through the process of data acquisition, term extraction, term refinement, term selection and term management based on reports, glossary and Telecommunications Technology Association (TTA) standards about u-Health. As a result, the standard terminology and guidelines of u-Health optimized to the domestic environment were suggested. They included details of definition, classification, components, the methods and principles of the process for u-Health standard terminology. Presented in this study, u-Health standard terminology and guidelines for terminology standardization would assist the cost-reducing of employing terminology and management of it, while making information transfer easy. This would make possible promoting efficient development of u-Health industry in general.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2004.10a
• /
• pp.423-426
• /
• 2004

인트라넷에서는 증가하는 웹문서의 검색을 목적으로 웹 검색엔진의 도입이 활발히 진행 중이며 대부분 찾아야할 키워드를 알고 접근하는 검색엔진 형태이다. 그러나 사용자가 무엇을 찾아야 하는지 모르는 경우 웹문서 분류체계는 효율적인 방법을 제시할 수 있다. 일부 구축되어 있는 분류체계는 수작업에 의한 분류로 인해 증가하는 웹문서의 양에 효율적으로 대처하기 곤란하므로 자동분류기법을 활용한 분류가 더 효율적일 것이다. 본 논문에서는 국방인트라넷의 수작업으로 구축된 분류체계를 대상으로 용어 가중치를 계산하는 방법을 달리하여 다양한 분류기법을 적용하여 성능을 비교평가하고 웹문서 자동분류시스템에 적용하여 분류성능의 향상을 도모하고자 한다.

• Journal of the Korean earth science society
• /
• v.41 no.1
• /
• pp.40-47
• /
• 2020

The purpose of this study was to analyze the terms used in the Information Boards of Geosites at Jeonbuk West Coast National Geopark. Among the terms used in the Information Boards, nouns were extracted and listed based on the Standard Korean Language Dictionary, a glossary of earth and the data for the development of textbooks according to the 2015 revision of curriculum, by which eight types were classified. Seventy-one nouns (10.8%) of the extracted terms were not listed in any glossary. Most of these terms were compound words derived by combining [noun]+[noun] or [noun]+[affix] so that they were not easy to comprehend. In addition, two hundred fifty-six nouns (46%) of the terms were identified as jargons used in specific disciplines. Therefore, it is strongly suggested that when creating the National Geopark Information Boards, the academic jargon embedded terminologies be explained with annotation for general public visitors and students to understand without difficulty.

• Journal of Korean Library and Information Science Society
• /
• v.39 no.4
• /
• pp.283-304
• /
• 2008

This is to develop Intelligent Retrieval System which can automatically present early query's category terms(association terms connected with knowledge structure of relevant terminology) through learning function and it changes searching form automatically and runs it with association terms. For the reason, this theoretical study of Intelligent Automatic Indexing System abstracts expert's index term through learning and clustering algorism about automatic classification, text mining(categorization), and document category representation. It also demonstrates a good capacity in the aspects of expense, time, recall ratio, and precision ratio.

• Journal of the Society of Disaster Information
• /
• v.14 no.2
• /
• pp.194-202
• /
• 2018

Purpose: It is necessary to set up a standardized method for classifying mixed soil layer that contains sand, gravel and boulder for engineering purposes. Method: Different size of soils was classified mixed soil layer by suggests unified soil classification method. Results: This paper suggests unified soil classification model for different size of soils where many authorities have their own system. Conclusion: Soil stratum classification method using appearing frequencies of gravels and weight ratio of boulders could be used to judgement in many cases.

• Korean Journal of Plant Taxonomy
• /
• v.44 no.4
• /
• pp.288-297
• /
• 2014

The aim of this study is to analyse misinformation about gymnosperm taxon used for over 57 years, since 1957 when plant biology as a discipline was established in our country. That is, terminologies and descriptions of the reproductive structure (flower) of angiosperms (flowering seed plants) have been incorrectly applied to the reproductive structures (typically cones and pollen grain) of gymnosperms (non-flowering seed plants) by numerous and various media such as text books, dictionaries, and internet websites for plant biology. Thus, these resources have been misleading teachers, students, and other people interested in plant biology in general and taxonomy in particular by describing gymnosperm reproductive structures as if they are the same as angiosperms. Such a practice has an especially adverse effect on plant biology education at all levels of instruction, with teachers and students confused in their understanding of the concept and definition of a flower. In this paper, these incorrect expressions for the reproductive structures of gymnosperms from the various media are analysed and discussed in terms of cladogram, anatomy of reproductive structures, and historical context of classification systems.

• Proceedings of the Korean Society for Information Management Conference
• /
• 1998.08a
• /
• pp.235-238
• /
• 1998

본 연구에서는 기존의 분석합성형 분류체계(BC2)로부터 개념과 관계를 추출하여 작성한 자모순 시소러스에 패싯도구를 삽입하여 용어의 개념과 관계를 정확하게 이해할 수 있도록 제시하는데 그 목적이 있다. 그리고, 이러한 과정을 통해 기존의 분류체계나 시소러스가 지니고 있는 한계를 개선하고자 한다.

• Proceedings of the Korean Information Science Society Conference
• /
• 2007.10d
• /
• pp.550-555
• /
• 2007

본 논문에서는 한국통신(KT)에서 사용되는 주요 용어들을 추출하여 추출된 용어들 간의 고유성과 관계성을 기초로 한 용어 온토로지를 구축하였다. 또한 생성된 용어 온토로지를 이용한 검색질의 예를 통해서 기업의 다양한 분야를 관리하는데 도움을 줄 수 있는 방안을 모색했다. 온토로지 구축 툴로는 은토로지 에디터, Protege를 사용하였으며. 온토로지는 최상위 클래스 Organization(기관), Employee(직원), Product(상품), Technique(기술) 등 4가지로 분류하여 구축하였다. 본 연구를 기초로 한국통신(KT)의 다양한 지식정보를 체계화하고 KT 데이터베이스를 효과적으로 관리할 수 있을 것이다. 또한 구축된 온토로지를 이용한 미래의 KT 시멘틱 검색시스템 구축에 기초가 되기를 기대한다.

• Journal of the Speleological Society of Korea
• /
• no.75
• /
• pp.35-39
• /
• 2006

There was known as Wetlands that the area was covered with the water. There are three conditions that is hydrology, soil, vegetation in the study of wetlands. The terminology are swamps, marshes, bogs, fens etc in foreign land. In Korea, there are many names for example mot. sotacji, noup, soubwon, soubji etc. But it should be defined the terminology of wetlands on the interpretation of foreign terminology or the unification of wetlands study inland.