• Asia pacific journal of information systems
• /
• 제6권2호
• /
• pp.77-105
• /
• 1996

The accuracy of knowledge is a major concern for expert system developers and users. Machine learning approaches have recently been found to be useful in knowledge acquisition for expert systems. However, the accuracy of concept acquired from machine learning could not be analyzed in most cases. In this paper we develop a comprehensive knowledge error analysis methodology for practical use of expert systems. Decision tree induction is an important type of machine learning method for business expert systems. Here we start to analyze with knowledge acquired from decision tree induction method, and extend the results to develop error analysis methodology for general machine learning methods. We give several examples and illustrations for these results. We also discuss the applicability of these results to multistrategy learning approaches.

• 한국정밀공학회:학술대회논문집
• /
• 한국정밀공학회 2006년도 춘계학술대회 논문집
• /
• pp.633-634
• /
• 2006

Recently we started a development of the digital meister expert system for the product design supporting in manufacturing industry. Knowledge representation is of major importance in digital moister expert system. This rule-based expert system-knowledges are designed for a certain type of knowledge representation such as rules or logic. The way in which a rule-based expert system represents knowledge affects the development, efficiency, speed, and maintenance. Eventually, this digital moister system is used to the engineer in manufacturing industry for the process control, production management and system management. In this paper, we propose the digital moister system knowledge representation method for product design supporting in manufacturing industry and we present introduction and contents of rule-based knowledge representation supporting tool.

• 동의생리병리학회지
• /
• 제23권4호
• /
• pp.745-750
• /
• 2009

The goal of this study is to examine on reasoning and search for construction of diagnosis ontology as a knowledge base of diagnosis expert system in oriental medicine. Expert system is a field of artificial intelligence. It is a system to acquire information with diverse reasoning methods after putting expert's knowledge in computer systematically. A typical model of expert system consists of knowledge base and reasoning & explanatory structure offering conclusion with the knowledge. To apply ontology as knowledge base to expert system practically, consideration on reasoning and search should be together. Therefore, this study compared and examined reasoning, search with diagnosis process in oriental medicine. Reasoning is divided into Rule-based reasoning and Case-based reasoning. The former is divided into Forward chaining and Backward chaining. Because of characteristics of diagnosis, sometimes Forward chaining or backward chaining are required. Therefore, there are a lot of cases that Hybrid chaining is effective. Case-based reasoning is a method to settle a problem in the present by comparing with the past cases. Therefore, it is suitable to diagnosis fields with abundant cases. Search is sorted into Breadth-first search, Depth-first search and Best-first search, which have respectively merits and demerits. To construct diagnosis ontology to be applied to practical expert system, reasoning and search to reflect diagnosis process and characteristics should be considered.

• 대한전기학회논문지
• /
• 제39권1호
• /
• pp.16-21
• /
• 1990

A Knowledge based expert system is a computer program that emulates the reasoning process of a human expert in a specific problem domain. Expert system has the potential to solve a wide range of problems which require knowledge about the problem rather than a purely analytical approach. This papaer presents the application of knowledge based expert system to power system fault diagnosis. The contents of expert system develpped in this paper is judgement of fault section from a given alarm sets and production of all possible hypothesis for the single fault. Both relay failures and circuit breaker failures are considered simultaneously. Although many types of relay are used in actual system, experts recognize ones as several typical signals corresponding to the fault types. Therefore relays are classified into several types. The expert system is written in an artificial intelligence language "PROLOG" . Best-first search method is used for problem solving. Both forward chaining and backward chaining schemes are used in reasoning process. The application to a part of actual power system proves the availability of the developed expert system.

• Journal of Advanced Marine Engineering and Technology
• /
• 제20권1호
• /
• pp.13-23
• /
• 1996

Weld defects degrade the strength and safety of astructure and are resulted from the various cases. The complexity of causal relation of weld defects requires an expert for the analysis of weld defects and the measures counter to them. An expert system has the intelligent functions such as the representation of knowledge and the inference. On this research, weld defect are systematically analysed and their causal model is developed. This information is saved to the knowledge base. The suitable inference algorithm for the diagnosis of weld defects is developed and realized with C++ programming.

• 제어로봇시스템학회논문지
• /
• 제5권1호
• /
• pp.54-61
• /
• 1999

Objective of the research is to put the vast and complex fault tracking knowledge of human experts in semiconductor production line into the knowledge base of computer system. We mined the fault tracking knowledge of domain experts(engineers of production line) for the construction of knowledge base of the expert system. Object oriented fact models which increase the extensibility and reusability have been built. The rules are designed to perform the fault diagnosis of the items in production device. We have exploited the evidence accumulation method to assign check priority in rules. The major contribution is in the overall design and implementation of the nile base and related facts of the expert system in object oriented paradigm for the application of the system in fault diagnosis in semiconductor production line.

• 대한기계학회논문집
• /
• 제18권3호
• /
• pp.777-784
• /
• 1994

A design expert system for the ship structural design is developed to support inexperienced designers. To establish the knowledge-base, an expert system development shell, Nexpert, is used. Knowledge is extracted from the rules of a classification society of ships, and also from an existing ship structural program that is being used by ship designers. This knowledge is systematized using the objectoriented concept. The design support system is constructed by adding additional functions which are required for the conventional engineering design work. Added functions are; calculation of longitudinal strength, database of existing ship designs, graphical user interface, and visualization of design results. It is observed that visualizing the relationships among the rules, which are activated to draw a certain design decision, is helpful. The system can easily be updated according to changes of the rule books of ship classification societies.

• 지능정보연구
• /
• 제7권2호
• /
• pp.65-81
• /
• 2001

본 논문에서는 전문가 시스템 개발에 있어서 체계적인 규칙추출을 위하여 지식베이스 구축에 관한 분석/설계단계까지를 5개 단계로 세분화하여 지식획득과정을 강화하였다. 또한 각 단계별로 지식공학자가 수행해야 하는 프로세스와 각 프로세스별로 지식공학자가 실질적인 작업을 통해 결과를 산출하는 태스크를 정형화하였다. 본 논문에서는 제안한 체계적인 규칙추출 방법론을 이용하여 아군 화력자산의 파괴율을 고려하고, 지휘관의 의도에 부합하는 아군 화력자산을 배분하는 STAFS 전문가시스템의 지식베이스 모듈 개발에 관한 연구를 수행하였다.

• 정보관리연구
• /
• 제36권4호
• /
• pp.199-215
• /
• 2005

과학기술 전문가 커뮤니티로서 가장 성공적인 모델인 '한민족과학기술자네트워크(이하 KOSEN)'를 대상으로 정책 네트워크의 분석방법을 이용하여 네트워크가 갖는 고유의 특성을 유형별로 분석해 보고자 한다. 과학기술 전문인력을 대상으로 하는 KOSEN을 사례로 정책 네트워크 분석을 적용, 지식전문가 네트워크의 유형을 구분해 보았다. KOSEN에 대한 개괄적인 특성분석과 더불어 참여자의 특성에 따라 전문가 그룹 네트워크를 정책공동체의 핵심 및 주변공동체와 이슈 네트워크로 세분화했다. 정책 네트워크의 분석수준과 관련하여 본 연구는 네트워크의 속성을 개인의 행위로 환원시켜서 이해하는 미시적 접근에 초점을 두었다.

• 지능정보연구
• /
• 제11권1호
• /
• pp.65-93
• /
• 2005

미술진단을 위한 전문가 시스템에는 (1)그림의 특징 (2) 환자의 심리증상 (3)그림 특징과 환자 심리증상 간의 관계 (4) 전문가의 진단과정 (5)지식의 표출 및 표현 방법 둥 다양한 분야에서 광범위한 지식이 필요하다. 이 지식들은 현장의 그림진단 치료사와 함께, 심리학자, 심리치료사, 그리고 미술진단을 컴퓨터에 구현할 지식공학자들로부터 얻어진다. 전문가는 다양한 요인들을 복합적으로 고려하는 매우 복잡한 진단과정을 거치며, 관련되는 방대한 지식들은 성격상 모호하고, 일관성이 부족하며, 때에 따라서는 상충적이기도 하다. 이 논문에서는 전문가의 진단과정을 모델링하여, 전문가 시스템의 구조를 설립하고, 지식들을 분석하여 분류한다. 분류에 따라 지식 획득과 표현에 적합한 방법을 선정하며, 온톨로지(ontoloty) 개념에 의한 프로티지(Protege) 2000을 도구로 사용하여 이 지식들을 체계적으로 정리한다. 실제 예제를 통하여 이 시스템의 사용가능성과 적합성을 보인다.