• 한국지능시스템학회논문지
• /
• 제13권2호
• /
• pp.222-230
• /
• 2003

의료 시스템이 개발되면 시스템이 사용하는 knowledge source의 신뢰도가 시스템의 수행능력에 큰 영향을 미치게 되므로, knowledge source의 신뢰도를 검증해야한다. 본 논문은 의료 시스템 CLINAID의 knowledge source의 신뢰성 조사에 대한 연구의 방법과 결과를 발표하였다. 그 방법으로는 CLINAID에 사용된 Cardiovascular body system 데이터에 fuzzy relational method를 적용하여 구조적 분석을 통해 만들어진 인공의 syndrome을 knowledge base에 저장되어있는 의료 전문가의 syndrome과 비교하였다. 7 가지 fuzzy implication operator를 사용하여 거의 비슷한 결과들을 산출해 냈으며, 그 결과들이 전문가가 제공한 syndrome과 거의 일치하였다.

• Journal of the Korean Data and Information Science Society
• /
• 제8권1호
• /
• pp.1-7
• /
• 1997

전문가 시스템에서의 추론은 주로 IF-THEN 형태의 규칙을 기반으로 하는 지식베이스에 기초한다. 그러나, 한의 전문가 시스템의 지식은 불확실한 지식 특히 애매한 개념의 지식을 많이 포함하고 있으므로 이에 대한 처리가 요구된다. 본 논문에서는 한의 진단 과정을 추론에 기준하여 분석하고 한의 진단 과정에서 발생하는 불확실한 진단 지식을 제약 조건 논리 프로그래밍언어의 일종인 CLP( R ) 언어를 이용하여 표현하고 처리하는 방법을 제안하였다.

• International Journal of Control, Automation, and Systems
• /
• 제2권2호
• /
• pp.207-219
• /
• 2004

This paper presents the development of a knowledge-based control system operating via the Internet. With the synergy provided by the Internet, the central expert controller with its knowledge-base has the potential to serve a multitude of front-end clients located anywhere in the world provided they have Internet access. In this way, the operational span of the knowledge-based control system can be expanded to virtually anyplace within the reach of the Internet. This configuration has positive implications in improving the efficiency of distributed operations, thereby enabling plantwide optimization and costs savings. Datasocket technology is adopted to facilitate a more efficient data exchange between the knowledge-based central server and the front-end clients. A specific application in the remote monitoring and fault diagnosis of machines using the proposed control configuration is presented in the paper.

• 한국지능시스템학회:학술대회논문집
• /
• 한국퍼지및지능시스템학회 1996년도 추계학술대회 학술발표 논문집
• /
• pp.137-140
• /
• 1996

In order to solve the specific problems in system, the implementing of knowledge base suitable to the system architecture has to be expressed and leads to the resoning of the new facts. Not only the simple knowledge based on the bivalent logic but also the representation and acqusition of knowledge related to vague and imprecise linguistic variable is necessary to the knowledge in the real world,i.e the knowledge of which facts and rules are composed. In this point of view, this survey implements the inference and retrieval of the fuzzy linguistic variables so that it can process the ambiguous information which appears the imprecision of the linguistic boundary.

• 산업공학
• /
• 제2권2호
• /
• pp.51-62
• /
• 1989

A computer-aided simulation modeling system has been developed to allow the automatic construction of complete discrete simulation models for queueing systems. Three types of knowledge are used in the specification and construction of a simulation modeling: Knowledge of queueing system, simulation modeling, and a target simulation language. This knowledge has been incorporated into the underlying rule base in the form of extraction and construction rule, and implemented via the expert system building tool, OPS5. This paper suggested a knowledge based approach for automatic programming to enable a user who lacks modeling knowledge and simulation language expertize to quickly build executable models.

• 한국소성가공학회:학술대회논문집
• /
• 한국소성가공학회 1998년도 제2회 박판성형심포지엄 논문집 박판성형기술의 현재와 미래
• /
• pp.47-56
• /
• 1998

Designing Trim die block is a complicated and time-consuming process heavily resting on the experience of the designer. To reduce design time and human errors, a knowledge base is used to automated the design process. In this paper, a framework of the Rule-based CAD System is presented for trim die block design consisting of a rule-base, design process control module and geometric modeler (CATIA). The rule-base includes design rules and know-how of design specialist. CATIA is used as the overall CAD environment and rule-base and design control modules are developed by C++ language with an interface to CATIA. Using the rule-base, the designer can explore alternating designs fast by changing design parameters and the part-list is automatically created which avoids miscommunication.

• 대한조선학회논문집
• /
• 제36권3호
• /
• pp.93-106
• /
• 1999

본 연구에서는 에이전트 기본 아키텍쳐를 설계하였고 다른 에이전트에게 관심있는 정보를 등록하는 메시지, 처리할 수 있는 업무를 표시하는 메시지, 정보를 알려주는 메시지, 정보에 대해 질문하는 메시지를 처리하는 KQML 처리기의 기본적인 알고리즘을 구현하였다. 에이전트 기본 아키텍쳐는 KQML 처리기가 KIF 번역기, 제어코드(Flow control code)로 구성되어 있다. 에이전트는 전달하고자 하는 지식을 KIF(Knowledge Interchange Format)로 표현하여 메시지 통신을 위한 외부 언어인 KQML(Knowledge Query and Manipulation Language)을 통해 실어나르는데 KQML 처리기가 메시지 통신을 관리한다. KQML 처리기를 통해 전달된 메시지의 내용은 KIF 번역기에 의해 저장되고 해석된다. 제어 코드는 프로그램의 수행 순서 및 정보의 흐름을 제어하여 실제 목표하는 일을 수행하는 프로그램 코드이며 KIF 번역기의 지식 베이스(Knowledge Base)에서 필요한 정보를 얻어서 내부 실행 코드와 외부 프로그램을 관리한다.

• 한국문헌정보학회지
• /
• 제49권1호
• /
• pp.341-360
• /
• 2015

본 논문에서는 과학 저널리즘의 대표적인 성공 사례로 평가되고 있는 KISTI의 과학향기 칼럼에 대한 반자동 지식화 방안과 이를 기반으로 과학기술 인포그래픽 기반의 서비스 체제를 제안한다. 전문가나 특정 분야 과학자를 대상으로 하는 전문 정보와는 달리 과학향기 콘텐트는 일반 대중을 대상으로 알기 쉬운 과학 상식을 제공하고 있다. 이러한 특성을 바탕으로 과학향기 데이터베이스를 지식화하기 위한 방법론 즉, 지식 유형, 지식 추출 방법 및 절차 등을 세부적으로 살펴본다. 또한 과학향기 지식베이스를 기반으로 과학기술 인포그래픽 서비스 체제를 새롭게 정의하고 이에 대한 세부적인 구성도, 방법론 및 특징 등을 기술한다. 이를 통해서 미래의 과학 저널리즘 서비스가 나아가야 할 발전적 방향을 제안한다.

• 대한전기학회논문지:전력기술부문A
• /
• 제53권12호
• /
• pp.637-644
• /
• 2004

This paper proposes an expert system with the knowledge learning capability which can enhance the safety and effectiveness of substation operation in the automated substation as well as existing substation by inferring multiple events such as main transformer fault, busbar fault and main transformer work schedule under multiple inference mode and multiple objective mode and by considering totally the switch status and the main transformer operating constraints. Especially inference mode includes the local minimum tree search method and pattern recognition method to enhance the performance of real-time bus reconfiguration strategy. The inference engine of the expert system consists of intuitive inferencing part and logical inferencing part. The intuitive inferencing part offers the control strategy corresponding to the event which is most similar to the real event by searching based on a minimum distance classification method of pattern recognition methods. On the other hand, logical inferencing part makes real-time control strategy using real-time mode(best-first search method) when the intuitive inferencing is failed. Also, it builds up a knowledge base or appends a new knowledge to the knowledge base using pattern learning function. The expert system has main transformer fault, main transformer maintenance work and bus fault processing function. It is implemented as computer language, Visual C++ which has a dynamic programming function for implementing of inference engine and a MFC function for implementing of MMI. Finally, it's accuracy and effectiveness is proved by several event simulation works for a typical substation.

• 한국실내디자인학회논문집
• /
• 제7호
• /
• pp.70-78
• /
• 1996

Artificial Intelligence is generally concerned with tasks whose execution appears to involve some intelligence if done by humans, and knowledge-based system ( in other word, expert system) is the research about the specific domain. This concept also can be applied to interior design field. So the purpose of this study is in reconstructing the accomplishment of artificial Intelligence and knowledge engineering, searching basic theories and cased to knowledge engineering , searching basic theories and cases to formulate knowledge -based design system, and testing the posibilities how the design information can be dealt in computer system. Given that recognition , two major problems must be solved before knowledge-based CAD systems could be come practical : Firstly , identification of the interior of designers use .Secondly , representing this knowledge in a computationally effective manner. I had discussed the basic concepts on which to base a knowledge- based design model, knowledge representation schemes, and problem solving, I could find the possibility which the knowledge-based system can be applied to the interior design according to this study. But there are non-deductive, often irrational and now easily computerized design process in interior design. Those are problems which are relevant to the machine learning and the creativity in design. So there should be a lot of research about the machine learning and the creatively in design in order to construct successfully intelligent knowledge-based design system.