• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2000.05a
• /
• pp.207-210
• /
• 2000

학습법칙은 신경회로망의 성능을 좌우하는 중요한 요소의 하나이다. Kohonen의 합습법칙등이 개발되어 사용되어 왔으나 Underutilization 문제가 있어 실제 사용사에 문제가 있어 왔다. 본 논문에서 제시하는 학습법칙은 이를 부분적으로 해결하였다. 또한 이 학습법칙을 ART(Adaptive Resonance Theory)-1과 Kohonen의 자기 구조 특징 지도의 장점을 조합한 개선된 IAFC(Integrated Adaptive Fuzzy Clustering) 신경회로망에 적용하였고, 성능을 평가하기 위해 가우시안 분포의 데이터와 IRIS 데이터를 각각 사용하여 실험하였다.

• The Monthly Technology and Standards
• /
• s.71
• /
• pp.11-12
• /
• 2007

"TPM 법칙"은 글로벌 경영환경 속에서 중소기업이 생존해 나가는데 필요한 하나의 프로세스(process)이자 전략(strategy)이고, 정책(policy )이자 동시에 법칙(law)이다.

• The Journal of the Acoustical Society of Korea
• /
• v.13 no.4
• /
• pp.60-68
• /
• 1994

In this paper we propose a new Hybrid learning rule applied to multilayer feedforward neural networks, which is constructed by combining Hebbian learning rule that is a good feature extractor and Back-Propagation(BP) learning rule that is an excellent classifier. Unlike the BP rule used in multi-layer perceptron(MLP), the proposed Hybrid learning rule is used for uptate of all connection weights except for output connection weigths becase the Hebbian learning in output layer does not guarantee learning convergence. To evaluate the performance, the proposed hybrid rule is applied to classifier problems in two dimensional space and shows better performance than the one applied only by the BP rule. In terms of learning speed the proposed rule converges faster than the conventional BP. For example, the learning of the proposed Hybrid can be done in 2/10 of the iterations that are required for BP, while the recognition rate of the proposed Hybrid is improved by about $0.778\%$ at the peak.

• Journal of Korea Game Society
• /
• v.9 no.5
• /
• pp.25-41
• /
• 2009

The objective of this study is to develop an analytic framework to code systematically the gamer's behaviour in MMO(Massively Multi-player Online) gameplay experience, to explore their gameplay as a problem solving procedure empirically. Previous studies about model human processor, content based protocol, and procedure based protocol are reviewed in order to build the outline of the analytic framework related to MMO gameplay. The specific gameplay actions and contents were derived by using concurrent protocol analysis method through the empirical experiment executed in MMORPG gameplay. Consequently, gameplay are divided into six actions : kinematics, perception, function, representation, simulation, and rule (heuristics, following, and transcedence). The analytic framework suitable for MMO gameplay was built. As a result of this study, we found three rule spaces in the problem solving domain of gameplay that are an heuristics, a following of the rule, and a transcendence of the rule. 'Heuristics' denotes the rule action that discovers the rule of game through trial-and-error. 'Following' indicates the rule action that follows the rule of game embedded in game by game designers. 'Transcendence' presents the rule action that transcends that. The new discovered rule spaces where 'Following' and 'Transcendence' actions occur and the gameplay pattern in them is provided with the key basis to determine the level design elements of MMO game, such as terrain feature, monster attribute, item, and skill et cetera. Therefore, this study is concludes with key implications to support game design to improve the quality of MMO game product.

• Proceedings of the KAIS Fall Conference
• /
• 2010.11b
• /
• pp.684-687
• /
• 2010

본 논문은 복합사이클 발전플랜트의 폐열회수 보일러 최적운전 및 최적설계에 대한 새로운 접근 방법을 도출하기 위해 폐열회수 보일러에서 발생되는 증기로 증기터빈을 구동하는 하부사이클 효율을 검토하였다. 열역학 제1법칙 해석을 통해 하부사이클 에너지 평형을 검토하였고, 열역학 제2법칙을 통해 엑서지 평형을 검토하였다. 하부사이클 효율이 최대가 되는 폐열회수 보일러를 설계하기 위해서는 열역학 제1법칙을 해석할 경우 하부사이클 전체를 해석하여야 함을 알 수 있다. 하지만, 열역학 제2법칙을 통한 엑서지 해석을 행할 경우 하부사이클 효율이 최대가 되는 증발온도와 폐여회수 보일러에서 소모되는 엑서지가 최소가 되는 점이 일치함을 알 수 있었다. 따라서 본 논문을 통해 폐열회수 보일러에서 소모되는 엑서지 해석을 통해 하부사이클 효율이 최대가 되는 폐열회수 보일러 최적화가 가능함을 알 수 있다.

• Proceedings of the Korea Inteligent Information System Society Conference
• /
• 2005.05a
• /
• pp.186-189
• /
• 2005

본 논문에서는 LVQ를 퍼지화한 새로운 퍼지 학습 법칙들을 제안하였다. 퍼지 LVQ 학습법칙 1은 기존의 학습률 대신에 퍼지 학습률을 사용하였는데 이는 조건 확률의 퍼지화에 기반을 두고 있다. 퍼지 LVQ 학습법칙 2는 클래스들 사이에 존재하는 입력벡터가 결정 경계선에 대한 정보를 더 가지고 있는 것을 반영한 것이다. 이 새로운 퍼지 학습 법칙들을 improved IAFC(Integrted Adaptive Fuzzy Clustering)신경회로망에 적용하였다. improved IAFC신경회로망은 ART-1 (Adaptive Resonance Theory)신경회로망과 Kohonen의 Self-Organizing Feature Map의 장점을 취합한 퍼지 신경회로망이다. 제안한 supervised IAFC 신경회로망 1과 supervised IAFC neural 신경회로망 2의 성능을 오류 역전파 신경회로망의 성능과 비교하기 위하여 iris 데이터를 사용하였는데 Supervised IAFC neural network 2가 오류 역전파 신경회로망보다 성능이 우수함을 보여주었다.

• The KIPS Transactions:PartB
• /
• v.10B no.1
• /
• pp.27-32
• /
• 2003

The rule induction system generates a set of inductive rules, and the task of selecting an optimal rule subset is one of the important problem in the area of rule induction. This paper proposes a new learning method which combines rule induction system with the paradigm of genetic algorithm. This paper shows that genetic algorithm can be effectively applied to optimal rule selection problem. The proposed system was evaluated using a set of different machine learning data sets and, showed better performance in all cases than other traditional methods.

• Journal of the Korean Society of Mechanical Technology
• /
• v.13 no.4
• /
• pp.23-30
• /
• 2011

본 연구는 산업용 열교환기 및 상용 파이프의 최적 설계를 위하여 열교환기 내의 사각형 단면 파이프의 shear-thickening 비뉴톤 유체의 압력강하 및 대류 열전달률을 수치해석적으로 수행하였다. shear-thickening 유체의 구성 방정식은 기존의 비뉴톤 유체 멱법칙을 보완한 확장 멱법칙 모델을 채택하였다. 파이프 내의 압력강하를 의미하는 마찰계수와 확장 레이놀즈 수의 곱은 기존 연구의 비교자료와 비교할 때 뉴톤 유체 영역과 멱법칙 영역에서 각각 0.018% 및 0.06% 내에서 일치함을 보였고, 대류 열전달률을 의미하는 뉴셀트 수는 문헌치와 비교할 때 뉴톤 유체 영역과 멱법칙 영역에서 각각 0.025% 및 0.14% 내에서 일치함을 보였다. 비뉴톤 확장 멱법칙 유체 모델의 형태를 띠는 shear-thickening 유체를 열교환기 또는 상용파이프 내의 사각형 단면 파이프 내에서 사용하면 유동지수(n)에 따라서 뉴톤 유체보다 최대 160%의 압력강하를 증가시켰고 최대 14%의 대류 열전달 감소를 발생시킬 수 있었다.

• Journal of the Korean Society for Aeronautical & Space Sciences
• /
• v.37 no.7
• /
• pp.701-708
• /
• 2009

The flight control law of developed flight control computer(DFLCC) is developed based on operation flight program of advanced trainer aircraft full scale development final configuration. The flight control law design is used common use development tool in GUI(Graphic User Interface) environment. The flight control law transformed to C-Code is reflected in OFP. The OFP is verified by the standardized verification process. But, before standardized verification process, we need preliminary verification process such as similarity of flight control law and reliability of developed HILS. Similarity of flight control law is verified by comparing the aircraft response of advanced trainer aircraft and those of the developed control law. Also, reliability of developed HILS is verified by comparing the aircraft response of HILS and Non-real time simulation result. This paper verifies similarity of developed control law and reliability of HILS environment as comparing aircraft response.

• Journal of the Korean Society for Aeronautical & Space Sciences
• /
• v.36 no.7
• /
• pp.712-718
• /
• 2008

This paper deals with a development of flight control law switching system which can be used for flight test of the research control law by switching control law during flight. Through this research program, fader logic and integrator stabilization design has been introduced to minimize the transient response of aircraft caused by flight control law switching and to prevent the divergence of the integrator included in the control law in standby mode. MIL-STD-1553B communication was applied to transfer the data between the two control laws. This paper introduce the control law switching system architecture and major design concept and include the system verification and validation result performed on the flying quality simulator of the advanced trainer.