• 한국산업융합학회 논문집
• /
• 제14권3호
• /
• pp.95-100
• /
• 2011

The modern society longing for the convenience of up-to-date technology, there are attempts of miniaturization and high reliance of power equipments in the effectiveness aspect of urban area's usage of space while requiring more electrical energy than now. Consequently, paper used to the Neral Network for a forcasting conservation system. A neral network is powerful asta modeling tool that is able to capture and represent complex input/output relationships. The true power and advantage of neral networks lies in their ability to learn these relationships directly from the data being modeled. Traditional linear models are simply inadequate when it comes to modeling data that contains non-linear characteristics. Form results of this study, the Neral Network is will play an important role for insulation diagnosis system of real site GIS and power eqipment using $SF_6$ gas.

• 한국조명전기설비학회:학술대회논문집
• /
• 한국조명전기설비학회 2007년도 춘계학술대회 논문집
• /
• pp.421-423
• /
• 2007

The paper used to the Neral Netwok for a forecasting conservation system A neural network is a powerful data modeling tool that is able to capture and represent complex input/output relationships. The motivation for the development of neural network technology stemmed from the desire to develop an artificial system that could perform "intelligent" tasks similar to those performed by the human brain. The true power and advantage of neural network lies in their ability to represent both linear and non-linear relationships and in their ability to learn these relationships directly from the data being modeled. Form results of this study, the Neral Netwok is will play an important role for insulation diagnosis system of real site GIS and power equipment using $SF_6$ gas.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2007년도 제38회 하계학술대회
• /
• pp.1428-1429
• /
• 2007

The paper used to the Neral Netwok for a forecasting conservation system. A neural network is a powerful data modeling tool that is able to capture and represent complex input/output relationships. The motivation for the development of neural network technology stemmed from the desire to develop an artificial system that could perform "intelligent" tasks similar to those performed by the human brain. The true power and advantage of neural network lies in their ability to represent both linear and non-linear relationships and in their ability to learn these relationships directly from the data being modeled. Form results of this study, the Neral Netwok is will play an important role for insulation diagnosis system of real site GIS and power equipment using Dry-Air gas.

• 한국정보통신학회:학술대회논문집
• /
• 한국정보통신학회 2021년도 추계학술대회
• /
• pp.394-396
• /
• 2021

특정 질병 진단을 위한 병리 검사는 필수적이며, 최근 이러한 분야의 시간적, 인적 자원의 필요성을 줄이기 위해 인공 지능을 활용한 암세포의 자동분류가 가능한 시스템 구축에 관련된 연구가 활발하게 진행되고 있다. 하지만, 이전 연구에서는 제한적인 심층학습 알고리즘에 기인한 비교적 낮은 정확도로 데이터 처리에 한계가 존재하였다. 본 연구에서는 심층 학습의 일종인 Convolution Neral Network를 통해 4종류의 암세포를 4 Class Classifciation을 시행하는 방법을 제안한다. EfficientNet, ResNet, Inception을 사용하였으며 여러 하이퍼 파라미터 튜닝을 통해 얻은 모델을 앙상블 하여 최종적으로 97.26의 정확도를 얻을 수 있었다.

• 한국시뮬레이션학회:학술대회논문집
• /
• 한국시뮬레이션학회 1994년도 추계학술발표회 및 정기총회
• /
• pp.12-12
• /
• 1994

Simulation output knowledge analysis is one of problem-solving and/or knowledge adquistion process by investgating the system behavior under study through simulation . This paper describes an approach to simulation outputknowldege analysis using fuzzy neural network model. A fuzzy neral network model is designed with fuzzy setsand membership functions for variables of simulation model. The relationship between input parameters and output performances of simulation model is captured as system behavior knowlege in a fuzzy neural networkmodel by training examples form simulation exepreiments. Backpropagation learning algorithms is used to encode the knowledge. The knowledge is utilized to solve problem through simulation such as system performance prodiction and goal-directed analysis. For explicit knowledge acquisition, production rules are extracted from the implicit neural network knowledge. These rules may assit in explaining the simulation results and providing knowledge base for an expert system. This approach thus enablesboth symbolic and numeric reasoning to solve problem througth simulation . We applied this approach to the design problem of broadband communication network.

• 한국정밀공학회:학술대회논문집
• /
• 한국정밀공학회 1997년도 춘계학술대회 논문집
• /
• pp.432-437
• /
• 1997

In this paper, Fuzzy ART which is one of the competitive learing neural networks is applied to machine-part cell formation problem. A large matrix and varios types of machine-part incidence matrices, especially including bottle-neck machines, bottle-neck parts, parts shared by several cells, and machines shared by several cells are used to test the performannce of Fuzzy ART neural network as a cell formation algorithm. The result shows Fuzzy ART neral network can be efficiently applied to machine-part cell formation problem which are large, and/or have much imperfection as exceptions, bottle-neck machines, and bottle-neck parts.

• 융합신호처리학회논문지
• /
• 제2권3호
• /
• pp.79-85
• /
• 2001

본 논문에서는 퍼지 보상기와 자기구성 신경회로망을 이용하여 3축 매니퓰레이터의 역 기구학 해를 구하는 방법을 제안한다. 가우시안 위치 함수를 활성화 함수로 사용하는 자기구성 신경회로망은 학습 시작시 1개의 은닉층 노드를 가지고 학습을 하면서 점차적으로 은닉층의 노드수를 증가시킴으로서 최적의 노드수를 얻을 수 있으며, 퍼지 보상기는 신경회로망의 양호한 학습비를 얻는다. 이와 같이 시스템을 구성하여 빠른 학습속도와 학습비의 개선 그리고 빠른 정상상태로의 수렴을 확인하였다.

• Communications for Statistical Applications and Methods
• /
• 제17권4호
• /
• pp.561-574
• /
• 2010

본 논문은 8가지 방법의 데이터 마이닝 알고리즘(CART, QUEST, CRUISE, 로지스틱 회귀분석, 선형판별분석, 이차판별분석, 신경망분석, 서포트 벡터 머신) 기법과 단일 알고리즘에 2가지 앙상블기법(배깅, 부스팅)을 적용한 16가지 방법을 바탕으로 총 24가지의 방법을 비교하였다. 알고리즘의 성능 비교를 위하여 13개의 이항반응변수로 구성된 데이터를 사용하였다. 비교 기준은 민감도, 특이도 및 오분류율을 사용하여 데이터 마이닝 기법의 성능향상에 대해 평가하였다.