• International Journal of Fuzzy Logic and Intelligent Systems
• /
• 제10권4호
• /
• pp.253-258
• /
• 2010

The causal network represents the knowledge related to the dependency relationship between all attributes. If the causal network is available, the dependency relationship can be employed to estimate the missing values for improving the estimation performance. However, the previous method had a limitation in that it did not consider the bidirectional characteristic of the causal network. The proposed method considers the bidirectional characteristic by applying prior and posterior conditions, so that it outperforms the previous method.

• 지식경영연구
• /
• 제10권4호
• /
• pp.43-60
• /
• 2009

The current study attempts to provide the field of knowledge management with theoretical grounds from the perspective of social network, resource dependency, and institutional theory. Social network theory considers that knowledge management plays a critical role in organizational innovation through the process of knowledge sharing/creation, communication systems, and a cooperative culture and trust, whereas resource dependency perceives knowledge management as contributing to cost reduction through the process of knowledge capture/storage, database systems, and reward/incentive systems. Plus, from the perspective of institutionalization, this study discusses that organizations can not benefit from knowledge management if it is adopted with the motive of isomorphic change. Finally, this study compares and integrates the three perspectives, and discusses the implications and limitations.

• 한국콘텐츠학회논문지
• /
• 제10권11호
• /
• pp.30-37
• /
• 2010

특정 제품이나 서비스에 대한 네티즌의 의견들은 고객뿐만 아니라 기업 입장에서도 마케팅이나 경영전략을 수립하기 위한 중요한 자료가 될 수 있기 때문에 온라인 고객리뷰를 분석하는 것은 매우 중요하다. 본 논문에서는 온라인 고객리뷰를 분석하기 위한 도구인 종속성 네트워크 모델을 제안하였고 종속성네트워크 모델을 기반으로 한 분석시스템을 설계하고 개발하였다. 종속성 네트워크모델은 고객리뷰 내의 주관적 문장과 객관적 문장을 분석대상으로 하며, 명사들 사이의 상대적 중요성과 연관성을 나타낼 수 있다. 시스템구현 결과, 종속성네트워크 모델은 오피니언마이닝 기술에 의하여 도출할 수 없는 새로운 정보 즉, 추출된 특징들 사이의 상대적 중요성 및 연관관계 등을 추출할 수 있음을 알 수 있었다.

• 한국지반공학회:학술대회논문집
• /
• 한국지반공학회 2009년도 춘계 학술발표회
• /
• pp.456-463
• /
• 2009

The preconsolidation pressure has been commonly determined by oedometer test. However, it can also be determined by in-situ test, such as piezocone test with theoretical and(or) empirical correlations. Recently, Neural Network(NN) theory was applied and some models were proposed to estimate the preconsolidation pressure or OCR. However, since the optimization process of synaptic weights of NN model is dependent on the initial synaptic weights, NN models which are trained with different initial weights can't avoid the variability on prediction result for new database even though they have same structure and use same transfer function. In this study, Committee Neural Network(CNN) model is proposed to improve the initial weight dependency of multi-layered neural network model on the prediction of preconsolidation pressure of soft clay from piezocone test result. It was found that even though the NN model has the optimized structure for given training data set, it still has the initial weight dependency, while the proposed CNN model can improve the initial weight dependency of the NN model and provide a consistent and precise inference result than existing NN models.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2003년도 컴퓨터소사이어티 추계학술대회논문집
• /
• pp.211-214
• /
• 2003

In this paper, we intend to find user's TV program choosing pattern and, recommend programs that he/she wants. So we suggest item dependency map which express relation between chosen program. Using an algorithm that we suggest, we can recommend an program, which a user has not saw yet but maybe is likely to interested in. Item dependency map is used as patterns for association in hopfield network so we can extract users global program choosing pattern only using users partial information. Hopfield network can extract global information from sub-information. Our algorithm can predict user's inclination and recommend an user necessary information.

• 한국경영과학회지
• /
• 제14권1호
• /
• pp.88-96
• /
• 1989

General measure in the reliability is the k-terminal reliability, which is the probability that the specified vertices are connected by the working edges. To compute the k-terminal reliability components are usually assumed to be statistically independent. In this study the modeling and analysis of the k-terminal reliability are investigated when dependency among components is considered. As the size of the network increases, the number of the joint probability parameter to represent the dependency among components is increasing exponentially. To avoid such a difficulty the structured-event-based-reliability model (SERM) is presented. This model uses the combination of the network topology (physical representation) and reliability block diagram (logical representation). This enables us to represent the dependency among components in a network form. Computational algorithms for the k-terminal reliability in SERM are based on the factoring algorithm Two features of the ractoring algorithm are the reliability preserving reduction and the privoting edge selection strategy. The pivoting edge selction strategy is modified by two different ways to tackle the replicated edges occuring in SERM. Two algorithms are presented according to each modified pivoting strategy and illustrated by numerical example.

• 한국정보과학회:학술대회논문집
• /
• 한국정보과학회 2001년도 봄 학술발표논문집 Vol.28 No.1 (B)
• /
• pp.475-477
• /
• 2001

본 논문은 사용자의 구매 패턴을 찾아서 사용자가 원하는 상품을 추천하는 알고리즘을 제안하고자 한다. 제안하고 있는 item dependency map은 구매된 상품간의 관계를 수식화 하여 행렬의 형태로 표현한 것이다. Item dependency map의 값은 사용자가 A라는 상품을 구매한 후 B 상품을 살 확률이다. 이런 정보를 가지고 있는 item dependency map은 홉필드 네트웍(Hopfield network)에서 연상을 위한 패턴 값으로 적용된다. 홉필드 네트웍은 각 노드사이의 연결가중치에 기억하고자 하는 것들을 연상시킨 뒤 어떤 입력을 통해서 전체 네트워크가 어떤 평형상태에 도달하는 방식으로 작동되는 신경망 중의 하나이다. 홉필드 네트웍의 특징 중의 하나는 부분 정보로부터 전체 정보를 추출할 수 있는 것이다. 이러한 특징을 가지고 사용자들의 일반적인 구매패턴을 일부 정보만 가지고 예측할 수 있다. Item dependency map은 홉필드 네트웍에서 사용자들의 그룹별 패턴을 학습하는데 사용된다. 따라서 item dependency map이 얼마나 사용자 구매패턴에 대한 정보를 가지고 있는지에 따라 그 결과가 결정되는 것이다. 본 논문은 정확한 item dependency map을 계산해 내는 알고리즘을 주로 논의하겠다.

• Journal of the Korean Data and Information Science Society
• /
• 제25권5호
• /
• pp.1107-1116
• /
• 2014

In this paper, we review recent developments in network analysis using the graph theory, and introduce ongoing research area with relevant theoretical results. In specific, we introduce basic notations in graph, and conditional and marginal approach in constructing the adjacency matrix. Also, we introduce the Marcenko-Pastur law, the Tracy-Widom law, the white Wishart distribution, and the spiked distribution. Finally, we mention the relationship between degrees and eigenvalues for the detection of hubs in a network.

• International journal of advanced smart convergence
• /
• 제8권1호
• /
• pp.133-140
• /
• 2019

In this paper, we present an algorithm for adjusting degree of belief for consistency on the evidence dependency network where various sets of evidence support different sets of hypotheses. It is common for experts to assign higher degree of belief to a hypothesis when there is more evidence over the hypothesis. Human expert without knowledge of uncertainty handling may not be able to cope with how evidence is combined to produce the anticipated belief value. Belief in a hypothesis changes as a series of evidence is known to be true. In non-monotonic reasoning environments, the belief retraction method is needed to clearly deal with uncertain situations. We create evidence dependency network from rules and apply the evidence retraction algorithm to refine belief values on the hypothesis set. We also introduce negative belief values to reflect the reverse effect of evidence combination.

• 한국정보과학회 언어공학연구회:학술대회논문집(한글 및 한국어 정보처리)
• /
• 한국정보과학회언어공학연구회 2018년도 제30회 한글 및 한국어 정보처리 학술대회
• /
• pp.19-22
• /
• 2018

본 논문에서는 기존 Stack Pointer Network의 의존 파싱 모델을 확장한 Bi-Stack Pointer Network를 제안한다. Stack Pointer Network는 기존의 Pointer Network에 내부 stack을 만들어 전체 문장을 읽어 dependency tree를 구성한다. stack은 tree의 깊이 우선 탐색을 통해 선정되고 Pointer Network는 stack의 top 단어(head)의 자식(child)을 선택한다. 제안한 모델은 기존의 Stack Pointer Network가 지배소(head)정보로 의존소(child)를 예측하는 부분에 Biaffine attention을 통해 의존소(child)에서 지배소(head)를 예측하는 방향을 추가하여 양방향 예측이 가능하게 한 모델이다. 실험 결과, 제안 Bi-Stack Pointer Network모델은 UAS 91.53%, LAS 90.93%의 성능을 보여주어 기존 최고 성능을 개선시켰다.