• 한국정보과학회:학술대회논문집
• /
• 한국정보과학회 2005년도 가을 학술발표논문집 Vol.32 No.2 (2)
• /
• pp.289-291
• /
• 2005

최근 유전자 칩의 발전으로 다양하고 방대한 양의 유전자 정보를 이용한 정확하고 신뢰성 높은 분류, 군집 및 질병을 예측하는 분석 기법이 증가하고 있다. 하지만 특징적인 유전자를 선택하는 Gene Selection 기법의 종류는 많지가 않으며 주로 통계적인 방법에 의존하여 유전자를 선택하는 기법을 많이 사용하고 있다. 본 논문에서는 유전자 알고리즘과 신경망의 결합을 통한 데이터마이닝을 기반으로 신뢰성 높은 특징적인 유전자를 선택하는 Gene Selection 기법에 대하여 연구을 진행하였다.

• 한국지능시스템학회:학술대회논문집
• /
• 한국퍼지및지능시스템학회 1997년도 춘계학술대회 학술발표 논문집
• /
• pp.18-21
• /
• 1997

Intelligent control technologies (fuzzy logic, neural network, chaos, and genetic algorithm) have been a great deal of influences and impact, especially in home appliances industry. As a result, products that utilize these technologies are pouring into the market from just about every companies. These products are getting good responses from the consumers, because they offer convenience and amenities through the intelligent self-control. In this article, the functionality of the intelligent control technologies will be explained, and how they are being applied to the consumer products developed in Samsung Electronics Co.

• International Journal of CAD/CAM
• /
• 제9권1호
• /
• pp.85-91
• /
• 2010

In this paper, we demonstrate an autonomous design of motion control of virtual creatures (called animated robots in this paper) and develop modeling software for animated robots. An animated robot can behave autonomously by using its own sensors and controllers on three-dimensional physically modeled environment. The developed software can enable us to execute the simulation of animated robots on physical environment at any time during the modeling process. In order to simulate more realistic world, an approximate fluid environment model with low computational costs is presented. It is shown that a combinatorial use of neural network implementation for controllers and the genetic algorithm (GA) or the particle swarm optimization (PSO) is effective for emerging more realistic autonomous behaviours of animated robots.

• 한국철도학회:학술대회논문집
• /
• 한국철도학회 2004년도 추계학술대회 논문집
• /
• pp.579-584
• /
• 2004

In development of the bogie, the fatigue strength of the bogie frame is an important design criteria. Also the bogie frame weight reduction is required in order to save energy and materials. In this study. structural analysis of bogie frame by using the finite element method has been performed for the various loading conditions according to the UIC standards and it has been attempted minimize the weight of bogie frame by back-propagation neural network and genetic algorithm. Finite element mesh generation and finite element analysis were performed by Altaire Hyper Mesh and ABAQUS.

• Journal of Information Technology Applications and Management
• /
• 제13권1호
• /
• pp.77-94
• /
• 2006

Case-based Reasoning (CBR) is widely used in business and industry prediction. It is suitable to solve complex and unstructured business problems. Recently, the prediction accuracy of CBR has been enhanced by not only various machine learning algorithms such as genetic algorithms, relative weighting of Artificial Neural Network (ANN) input variable but also data mining technique such as feature selection, feature weighting, feature transformation, and instance selection As a result, CBR is even more widely used today in business area. In this study, we investigated the usefulness of the CBR method in forecasting success in implementing ERP systems. We used a CBR method based on the feature weighting technique to compare the performance of three different models : MDA (Multiple Discriminant Analysis), GECBR (GEneral CBR), FWCBR (CBR with Feature Weighting supported by Analytic Hierarchy Process). The study suggests that the FWCBR approach is a promising method for forecasting of successful ERP implementation in Small and Medium sized Enterprises.

• 한국전산유체공학회지
• /
• 제14권4호
• /
• pp.31-40
• /
• 2009

Although optimization by sequentially refining metamodels is known to be computationally very efficient, the metamodel that can be used for this purpose is limited to Kriging method due to the difficulties related with sample points selections. The present study suggests a novel method for sequentially refining metamodels using Pareto Frontiers, which can be used independent of the type of metamodels. It is shown from the examples that the present method yields more accurate metamodels compared with full-factorial optimization and also guarantees global optimum irrespective of the initial conditions. Finally, in order to prove the generality of the present method, it is applied to a 2D transonic airfoil optimization problem, and the successful design results are obtained.

• 한국콘크리트학회:학술대회논문집
• /
• 한국콘크리트학회 2006년도 추계 학술발표회 논문집
• /
• pp.909-912
• /
• 2006

This paper examined the applicability of convex hull, which is defined as the minimal convex polygon including all points, to assessment model for effective region. In order to validate the applicability of the convex hull to assessment model for effective region, a genetic algorithm was adopted as a optimum technique, and an artificial neural network was adopted as a prediction model for material properties. The mix-proportion obtained from the proposed technique is more reasonable than that obtained from previous work.

• 한국지능시스템학회:학술대회논문집
• /
• 한국퍼지및지능시스템학회 1993년도 Fifth International Fuzzy Systems Association World Congress 93
• /
• pp.887-890
• /
• 1993

By introducing the notion of constraint-oriented fuzzy inference, we will show that it provides us ways of fuzzy control methods that has abilities of adaptation, learning and self-organization. The basic supporting techniques behind these abilities are“hard”processing by Artificial Intelligence or traditional computational framework and“soft”processing by Neural Network or Genetic Algorithm techniques. The reason that these techniques can be incorporated to fuzzy control systems is that the notion of“constraint”itself has two fundamental properties, that is, the“modularity”property due to its declarativeness and the“logicality”property due to its two-valuedness. From the former property, the modularity property, decomposing and integrating constraints can be done easily and efficiently, which enables us to carry out the above“soft”processing. From the latter property, the logicality property, Qualitative Reasoning and Instance Generalization by Symbolic Reasoning an be carried out, thus enabling the“hard”processing.

• 한국표면공학회:학술대회논문집
• /
• 한국표면공학회 2006년도 추계학술발표회 초록집
• /
• pp.2-3
• /
• 2006

본 논문에서는 신경망 모델링을 통하여 HDP-CVD를 이용한 실리콘 산화막 형성에 영향을 주는 다섯 가지 공정 장비 변수와 그에 따른 두 가지 출력 파라미터 Deposition rate과 Uniformity와의 관계를 동시에 고려한 특성결과를 분석하고， 최적의 recipe를 Genetic Algorithm을 통해 제시하였다. 실험계획법을 사용하여， 필요한 실험의 횟수를 최소화 하였으며 그 실험결과를 신경망 모델링을 통하여 입력변수와 출력파라미터의 관계를 3차원의 반응표면 곡선으로 분석하였다. 이 과정을 통해 Deposition rate과 Uniformity을 동시에 고려한 두 출력파라미터를 만족하는 최적의 입력변수 값들을 제시하였다.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 1999년도 하계학술대회 논문집 G
• /
• pp.2830-2832
• /
• 1999

신경망은 선형 시스템 뿐 만 아니라 비선형 시스템에 있어서도 탁월한 모델링 및 예측 성능을 갖고 있다. 하지만 좋은 성능을 갖는 신경망을 구현하기 위해서는 최적화 해야할 파라미터들이 있다. 은닉층의 뉴런의 수, 학습율, 모멘텀, 학습오차 등이 그것인데 이러한 파라미터들은 경험에 의해서, 또는 문헌들에서 제시하는 값들을 선택하여 사용하는 것이 일반적인 경향이다. 하지만 신경망의 전체적인 성능은 이러한 파라미터들의 값에 의해서 결정되기 때문에 이 값들의 선택은 보다 체계적인 방법을 사용하여 구하여야 한다. 본 논문은 유전 알고리즘을 이용하여 이러한 신경망 파라미터들의 최적 값을 찾는데 목적이 있다. 유전 알고리즘을 이용하여 찾은 파라미터들을 사용하여 학습된 신경망의 학습오차와 예측오차들을 심플렉스 알고리즘을 이용하여 찾은 파라미터들을 사용하여 학습된 신경망의 오차들과 비교하여 본 결과 유전 알고리즘을 이용하여 찾을 파라미터들을 이용했을 때의 신경망의 성능이 더욱 우수함을 알 수 있다.