• 한국컴퓨터정보학회논문지
• /
• 제4권1호
• /
• pp.21-27
• /
• 1999

본 논문은 단어들의 유사도를 이용하여 문서들을 자동으로 분류하는 새로운 방법을 제안한다. 단어들 중에서 의미있는 단어들을 찾아내기 위하여 자동색인 방법을 이용하였으며. 두 번째로 본 논문에서 제안한 확률 모델을 이용하여 각 단어들의 문서와의 연관관계를 분석하였다. 이를 토대로 분류를 가능하게 하기 위한 프로파일을 생성한다. 본 논문에서는 유전자 알고리즘과 신경망에 관련된 10개의 문서에 대하여 실험하여 유전자 알고리즘과 신경망에 해당하는 프로파일을 생성하였다.

• 한국정보과학회논문지:소프트웨어및응용
• /
• 제32권1호
• /
• pp.1-9
• /
• 2005

본 논문에서는 패턴 분류를 위한 수정된 퍼지 최대최소 신경망 모델을 제안하고 그의 유용성을 고찰한다. 이를 위하여 하이퍼박스 내에서 각 특징들에 대하여 가중치 요소론 갖는 새로운 하이퍼큐브 소속함수를 정의한다. 이 가중치 요소는 분류과정에서 임의의 클래스에 대한 각 특징의 상대적인 기여도를 반영한다. 본 연구에서는 이를 위하여 새롭게 정의된 하이퍼박스 생성, 확장 및 축소의 3단계로 이루어지는 학습 방법론을 소개한다. 또한 제안된 모델을 기반으로 하여 학습된 분류기로부터 하이퍼박스 소속함수와 연결가중치를 사용하여 주어진 클래스에 대한 특징의 연관도를 산출하는 형태의 이른바 특징 분석 기법을 제안한다. 이를 위하여 세부적으로 각 특징에 대하여 연관도 척도와 퍼지 소속함수간의 유사도 척도를 정의한다. 또한 실제 패턴 분류문제에 적용한 실험결과를 통하여 제안된 이론의 타당성을 평가한다.

• 지역연구
• /
• 제11권2호
• /
• pp.53-63
• /
• 1995

Changes in transport are reflected in the accessibility of a place, which is denoted as the inherent advantageous characteristics of a place with respect to overcoming spatial friction, and affect the land use ultimately. A composite accessibility measurement scheme is developed and applied to the subway network in Seoul, which has been constructed in 1972. Changes in the transport network are reflected in the spatial structure of accessibility and affect ultimately the land use pattern. Therefore, it is of relevance to examine the changes in the spatial structure of accessibility, which allows to forecast the direction of changes in the land use pattern.

• 교육시설 논문지
• /
• 제21권2호
• /
• pp.25-32
• /
• 2014

Many Korean university campuses are located on hilly terrain where the hierarchy of the path system is unclear. Therefore, it is difficult to analyze the pedestrian network through space syntax, in which only horizontal direction changes are considered as depths of space. The purpose of this study is to compare pedestrian movement patterns and space syntax analysis in order to find their relevance to each other and the relationship between them. We conducted a survey regarding the most-visited buildings and pathways at S-University, which is located on a hilly area in Seoul. The survey results were compared with the Space Syntax integration map by regression analysis. For the segments where the relationship between pedestrian volume and integration was weak, field observations were conducted. As a result, topographical aspects, functional aspects, and location aspects were observed as the main influential factors. In addition, the research proposes that adding an extra axial line per vertical directional change can potentially compensate for the low relevance of stairs. This study suggests the possibility and the necessity of three-dimensional space syntax programs and emphasizes the importance of campus planning for the pedestrian environment.

• 대한본초학회지
• /
• 제38권6호
• /
• pp.73-91
• /
• 2023

Objectives : This study used a network pharmacology approach to elucidate the efficacy and molecular mechanisms of Daehwangmokdanpitang (DHMDPT) on Psoriasis. Methods : Using OASIS databases and PubChem database, compounds of DHMDPT and their target genes were collected. The putative target genes of DHMDPT and known target genes of psoriasis were compared and found the correlation. Then, the network was constructed using Cytoscape 3.10.1. The key target genes were screened by Analyzer network and their functional enrichment analysis was conducted based on the Gene Ontology (GO) enrichment analysis and Kyoto Encyclopedia of Genes and Genomes (KEGG) Pathways to predict the mechanisms. Results : The result showed that total 30 compounds and 439 related genes were gathered from DHMDPT. 264 genes were interacted with psoriasis gene set, suggesting that the effects of DHMDPT are closely related to psoriasis. Based on GO enrichment analysis and KEGG pathways, 'Binding', 'Cytokine Activity', 'Receptor Ligand Activity' 'HIF-1 signaling pathway', 'IL-17 signaling pathway', 'Toll-like receptor signaling pathway', and 'TNF signaling pathway' were predicted as functional pathways of 16 key target genes of DHMDPT on psoriasis. Among the target genes, IL6, IL1B, TNF, AKT1 showed high correlation with the results of KEGG pathways. Additionally, Emodin, Acetovanillone, Gallic acid, and Ferulic acid showed a high relevance with key genes and their mechanisms. Conclusion : Through a network pharmacological method, DHMDPT was predicted to have high relevance with psoriasis. This study could be used as a basis for studying therapeutic effects of DHMDPT on psoriasis.

• IMMUNE NETWORK
• /
• 제9권1호
• /
• pp.8-11
• /
• 2009

There is mounting evidence that autophagy is involved in diverse physiological and pathological processes that have immense relevance in human development, diseases and aging. Immunity and inflammation are not exceptions. Here, the role of autophagy in the control of immune processes particularly that related to cell death and inflammation is discussed.

• ETRI Journal
• /
• 제40권5호
• /
• pp.604-612
• /
• 2018

To solve the problem of unbalanced loads and the short network lifetime of heterogeneous wireless sensor networks, this paper proposes a node-selection algorithm based on energy balance and dynamic adjustment. The spacing and energy of the nodes are calculated according to the proximity to the network nodes and the characteristics of the link structure. The direction factor and the energy-adjustment factor are introduced to optimize the node-selection probability in order to realize the dynamic selection of network nodes. On this basis, the target path is selected by the relevance of the nodes, and nodes with insufficient energy values are excluded in real time by the establishment of the node-selection mechanism, which guarantees the normal operation of the network and a balanced energy consumption. Simulation results show that this algorithm can effectively extend the network lifetime, and it has better stability, higher accuracy, and an enhanced data-receiving rate in sufficient time.

• 한국도서관정보학회지
• /
• 제26권
• /
• pp.505-540
• /
• 1997

The library collects relevant documents, organizes these documents, retrieves and provides relevant documents, and helps the user use provided documents. These library activities are the distribution process of relevant documents in a society, and the role of library science is to deal with several problems in this process. This process is to facilitate the production of socially relevant documents, to select documents relevant to an individual user, and to enable the user to use the selected documents. As a result, this process should be based on the concept of "relevance". As a result, the academic role of library science should be considered based on "relevance". "Relevance" is getting more important to meet the change of the environment of library services, which is getting more complex and changing rapidly because of the computer and the computer network. It is true that these are very important tool for document distribution. However, the problems in the document distribution can not be solved only by the simple development of these tools because these have been caused by the simple development of these tools. These problems can be solved only through many studies of the user, which is the destination of document distribution, and through a n.0, pplying the results of these studies to designing these tools.dies to designing these tools.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2001년도 추계학술발표논문집 (상)
• /
• pp.363-366
• /
• 2001

It is very difficult to maintain the performance of estimation models for the new breed of projects since the computing environment changes so rapidly in terms of programming languages, development tools, and methodologies. So, we propose to use the relevant cases for a neural network model, whose cost is the decreased number of cases. To balance the relevance and data availability, the qualitative input factors are used as criteria of data classification. With the data sets that have the same value for certain qualitative input factors, we can eliminate the factors from the model making reduced neural network models. So we need to seek the optimally reduced neural network model among them. To find the optimally case-selective neural network, we propose the search techniques and sensitivity analysis between data points and search space.

• 한국정보과학회논문지:소프트웨어및응용
• /
• 제29권3호
• /
• pp.145-155
• /
• 2002

내용 기반 영상 검색에서 대부분의 기존 방법들은 서로 다른 특징들 사이의 선형 관계를 가정하고 또 사용자가 직접 각 특징의 가중치를 설정하도록 한다 허나 특징들 사이의 관계가 선형적으로 가정된 하에서는 고차원의 개념과 인간의 지각 주관성을 충분히 표현할 수 없는 단점이 있다. 본 논문에서는 신경망에 기반한 영상 검색 모델이 제안된다. 이는 RBFN을 이용한 내용 기반 영상 검색 기법과 인간컴퓨터 상호작용의 접근 방법을 기반으로 구축되었다. RBFN을 이용하여 특징들 사이의 비선형적 관계를 추출해낼 수 있고 사용자가 처음에 질의 영상을 선택하고 관련성 피드백을 통하여 점차적으로 목표 영상을 찾아나가도록 함으로써 영상의 비교를 더 정확하게 할 수 있다. 실험은 145개의 클래스로 구분되며 1,015개의 영상을 포함하는 데이타베이스를 사용하여 재생과 정도를 계산하였다. 실험 결과는 제안된 방법의 재생과 정도가 각각 93.45%과 80.61%로서, 기존의 선형 결합 방법이나 순위 기반 방법 그리고 역전파 알고리즘에 기반한 방법보다 더 뛰어난 검색 성능을 지님을 보여준다.