• 한국정보과학회:학술대회논문집
• /
• 한국정보과학회 2005년도 한국컴퓨터종합학술대회 논문집 Vol.32 No.1 (B)
• /
• pp.673-675
• /
• 2005

The art psychotherapy expert system is a computer system which helps to analyse one's psychology through pictures. However we need a standard criterion because the psychology, the target of the art psychotherapy, does not only have a ambiguous criterion but also a vast range. We're going to suggest a criterion in the field of the art psychotherapy by constructing systematic database through knowledge acquirement of the art psychotherapy expert system. In this study we introduce a system which enables systematic classification and confirmation of symptoms according to mental analyses. The suggested system enables confirmation of a classical structure and systematic classification of knowledges through conversation by extracting nouns through sentence analysis from the knowledge of descriptive form based on the clinical purpose of sentence analysis.

• 한국지능시스템학회논문지
• /
• 제14권6호
• /
• pp.764-770
• /
• 2004

This paper presents a hybrid data mining mechanism to extract expert knowledge from historical data and extend expert systems' reasoning capabilities by using fuzzy neural network (FNN)-based learning & rule extraction algorithm. Our hybrid data mining mechanism is based on association rule extraction mechanism, FNN learning and fuzzy rule extraction algorithm. Most of traditional data mining mechanisms are depended ()n association rule extraction algorithm. However, the basic association rule-based data mining systems has not the learning ability. Therefore, there is a problem to extend the knowledge base adaptively. In addition, sequential patterns of association rules can`t represent the complicate fuzzy logic in real-world. To resolve these problems, we suggest the hybrid data mining mechanism based on association rule-based data mining, FNN learning and fuzzy rule extraction algorithm. Our hybrid data mining mechanism is consisted of four phases. First, we use general association rule mining mechanism to develop an initial rule base. Then, in the second phase, we adopt the FNN learning algorithm to extract the hidden relationships or patterns embedded in the historical data. Third, after the learning of FNN, the fuzzy rule extraction algorithm will be used to extract the implicit knowledge from the FNN. Fourth, we will combine the association rules (initial rule base) and fuzzy rules. Implementation results show that the hybrid data mining mechanism can reflect both association rule-based knowledge extraction and FNN-based knowledge extension.

• 대한안전경영과학회지
• /
• 제10권1호
• /
• pp.11-22
• /
• 2008

Humans are well-known for being adept at using intuition and expertise in many situations. However, human experts are still susceptible to errors in judgment or execution, and failure to recognize the limits of knowledge. This would happen especially in semi-structured situations, in multi-disciplinary settings, under time or other stress, under uncertainty, or when knowledge is outdated Human errors are caused by cognitive biases, attentional slips/memory lapses, cultural motivations, and missing knowledge. The purpose of this research is to study errors of human experts committed in judgment and the general idea of critiquing systems as corresponding plan. Compared to expert systems, critiquing systems are narrowly focused programs useful in limited situations for collaborating with and supporting experts in their task activities. It supports an expert by detecting the human's errors by deploying various strategies that stimulate humans to improve their performance. A variety of types of critiquing systems has spread through numerous application areas.

• 한국정보처리학회논문지
• /
• 제5권3호
• /
• pp.662-670
• /
• 1998

심볼레벨에서 개발된 1세대 전문가시스템의 문제점을 해결하기 위하여 최근 지식레벨에서 2세대 전문가시스템을 개발하기 위한 여러 가지 방법들이 제안되었으나, 대개 개념적인 모델링 기법을 제시하는 수준에 머무르고 있다. 본 논문에서는 이러한 개념적인 모델링 기법이 실용 가능한 개발기법이 될 수 있도록 기존의 연구 내용을 수정, 보완한 태스크 객체 모델링(TOM) 기법을 제시하였다. 이 기법에서 태스크 객체(TO)는 자신의 목표와 수행 조건, 실행할 행위 지식 등을 포함하는 하나의 지식 단위로 정의하고, TO의 구조적, 동적, 기능적 측면을 쉽게 도식화할 수 있는 태스크 객체 다이어그램(TOD)을 정의하였다. 또한, 각 TO의 행위 지식을 표현하는 기본 단위로서 추론유형(Inference Type)들을 정의하였다. 본 논문에서 제안한 TOM 기법이 단순히 개념적인 모델링 기법이 아니라 실용적인 2세대 전문가시스템 개발기법으로 활용될 수 있도록 TOD 에디터와 TO 에디터를 개발하고, TO의 상태 변화에 기반을 둔 TO 처리 알고리즘을 개발하였다. 또한, 정의된 추론유형들이 대표적인 전문가시스템 개발도구인 IRE(Intelligent Rules element)의 메소드로 자동 변환 될 수 있도록, 각각의 추론유형과 IRE의 메소드를 1: 1로 대응시킨 추론 유형 라이브러리를 구축하였다.

• 한국자동차공학회논문집
• /
• 제4권6호
• /
• pp.153-163
• /
• 1996

An expert system to design compressor valve systems has been developed. Design process is viewed as a chain of devisions based on the results of necessary analyses. Actual design is implemented by the interaction between the expert system and the user. In this work, it is demonstrated how a final design is achieved by utilizing the rule bases and analysis capability of the system. The structure of the rule bases and related parameter studies are also explained. Advantages of using an expert system approach for valve designs are explained using a practical example.

• 대한전기학회논문지
• /
• 제41권9호
• /
• pp.960-972
• /
• 1992

This paper deals with the development of expert system in distribution system which combined with graphic user interface. The proposed expert system can recognize and adjust to the system change, and includes the rule bases of security monitoring. Also it provides load transfer algorithm for efficient load distribution. The graphic user environment for expert system is implemented in the mouse-oriented user interface with overlapped window functions and pull-down menus. Therefore, the developed graphic integrated expert system can afford to assist system operators very conveniently through the various graphic function in proposing an optimal plan of load transfer for fault restoration and outage schedule.

• 한국안전학회지
• /
• 제7권4호
• /
• pp.95-99
• /
• 1992

The attraction of using expert system in operator support systems for modern plant is that it offers a way of dealing with the problem of information overload that can occur during a severe disturbance at a modern industrial plant. During such a disturance the volume of information presented to operators may be such that they are unable to decide quickly what is important and what is not. Therefore, arriving at a correct diagnosis of the initialling fault may be delayed. An expert system operator sup-port system is a means of focusing attention on what really matters and cutting out the rest. This paper presents the development of prototype expert system which detect the fault part, machine, system and decide action priority. This prototype expert system has 6 sub- system which is Interface Manager, Decision Maker, Inference Engine, Knowledge base, Simulatio, and D.P System ( Diagnosis and predictor)

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 1997년도 추계학술대회 논문집 학회본부
• /
• pp.190-192
• /
• 1997

In this paper we developed an object-based expert system for electric power system fault diagnosis. The object corresponds to a hardware or event in real world and they are independent each other. The expert system is designed to estimate the fault sections and identify the false operation, nonoperation of protective devices. The expert system was developed using C++ language in pentium PC. We applied the expert system in various sample systems and showed that making up a knowledge base is easier and diagnosis was done in a approximately real time.

• 한국군사과학기술학회지
• /
• 제8권4호
• /
• pp.50-57
• /
• 2005

This paper describes an expert system for soldiers psychology diagnosis. In the field warfare, platoon leaders or company commanders have to diagnose his soldier's condition correctly. The expert systems, a field of artificial intelligence, can be appropriate approach for ill-structured paradigm. This use an UNIK system. This UNIK system is composed of UNIK-FRAME, UNIK-BWD, UNIK-WBI, UNIK-INDUCE and UNIK-Interface. Especially, UNIK-WBI system is very useful to display soldiers psychology diagnosis and so easy to use it. Any leader or commander can easily do this. This paper data is based on DSMIV. Through This expert system, combat power can be kept and accidents be protected.

• Journal of Welding and Joining
• /
• 제12권3호
• /
• pp.71-81
• /
• 1994

Laser cutting is experiencing a rising worldwide acceptance in the industry. Expert systems are necessary for the systematic arrangement and searching of experimental data existing in journal papers, job handbooks, etc.. This paper proposes an expert system for the selection of the appropriate laser cutting variables from the available database. Optimum cutting conditions according to the given cutting velocity were searched and qualitative comments which are difficult to be used as database variables were shown at each velocity using the binary and fuzzy inference. These comments could be informative to unskilled operators of the laser cutting process. Typical cutting conditions of the mild steel and stainless steel were included and the working range and quality variations were displayed graphically. The proposed algorithm was implemented in an IBM compatible personal computer as an expert system for CO$_{2}$ laser cutting to derive the optimum cutting conditions by using the turbo prolog.