This paper considers a paternity and kinship analysis system(PKAS) being currently used in real sites. A knowledge-based expert system is proposed to improve the performance of PKAS in terms of accuracy, speed, training time, and satisfaction, which are common measures for evaluation. The knowledge base, one of the most important components in the knowledge-based expert system(KBES), consists of a rule made from random matching algorithm, decision rules of allele types and guide rules of options. The last two rules are learning incrementally from sample data. The results show that PKAS armed with the expert system ensures the better performance with regard to these criteria than the existing system. Especially as far as speed is concerned, as the sample size increases, it outperforms the existing one. As the number of samples increases, while processing time increases nearly exponentially in the existing PKAS, it does linearly in our proposed system.

In this paper, the expert system to reduce the amount of food waste is proposed. The method of material flow analysis (MFA) is applied. Proper handling of waste beyond the terms of the need for proactive research been mentioned before, but actually cause the waste generator research focuses on consumer behavior and the business community to analyze the flow of materials within the study are insufficient . In this paper, the type of food consumption and food waste, look at the relationship between the occurrence of secondary schools in the diet is provided for students to examine the preferences of the target model diet expert system was reconfigured . Preference for leaving the food in the diet leads to the important information that is Each diet recipes that make up the target material flow analysis (MFA) was constructed to perform all the database . This database is currently being generated from the rain while cooking diet edible plants and materials to reflect the self-esteem following the recommended diet is used to create . Reducing food waste is actually being used currently in research knowledge to the knowledge base was constructed . Future Home Smart System was developed in conjunction with the system to the user , by providing guidelines for the utilization can be expected.

This paper’s aim is to suggest the Expert System for analyzing relative combat power in ground operations. Since relative combat power analysis in terms of comparing combat power of friendly forces with one of the enemy can determine how the commander and staffs operate their unit afterwards, it requires fast and rational decision-making process. However, it has relied on manual method so far though Tactical Information Communications Network(TICN) into which numbers of applications can be loaded has been developed over a decade. The Expert System that will be built using EXSYS Corvid tool is expected to lessen error rate, provide faster decision- making, and reflect intangible combat power as well as tangible one by using an appropriate weights in analyzing relative combat power.

This research is to develop an expert system utilizing virtual reality and 3D image technologies for minimizing damages from natural disaster, especially storm and flood, which could be used as a training kid for people including the old. It also develops an expert system for storm and flood on very limited region, 3D animation application technology using optical motion capture techniques for heavy storm and flood, and 3D-based rendering technology using virtual reality techniques. This data based expert system should work exactly like real experts by adapting all expert knowledge and experience, so that users, especially the old and vulnerable residents not familiar with computer systems, could easily use the system by several button selections. The animated character based program will also be developed for the old and vulnerable residents to learn and understand what to do quite easily.

전문가시스템의 성공을 좌우하는 지식추출은 주요 애로공정 중의 하나로 알려져 있다. 설상가상으로 전문가의 부재, 새로운 또는 복잡한 문제 등 영역의 특성상 전문가시스템 개발은 실패할 수 있다. 이러한 문제점을 극복하기 위하여 본 논문에서는 KACE구조를 제안하였다. 본 구조는 작업 발생기, 작업 실행기, 작업 평가기, 규칙 발생기와 전문가시스템 등 5개의 주요 요소로 구성되어 있다. 이 구조를 이용하여 NP-complete인 일정계획 문제에 대한 전문가시스템이 어떻게 구축될 수 있는가를 예시하였다.

The purpose of this thesis addresses a development of an expert system to support a decision making of the vender selection. The researches related to the vender selection problems have been studied and they provide 23 criteria to select proper venders. In this thesis, 8 criteria have been used to construct a knowledge base of the expert system. The system in this thesis consists of 6 steps in its procedure. Step 1 decides a specification that satisfies customer's needs and Step 2 chooses a part supplied by a vender. The type of an outside order is decided in Step 3 and some venders satisfying the customer's needs are selected in Step 4. Some of the venders chosen from step 4 which do not satisfy the fatal cirteria(that is Quality, Delivery, Price) can be deleted in Step 5. In the last step, 8 cirteria is used to select 3 venders according to their ranking. Consequently, this program provides for a man, who does not have the experiances, an efficient way to select appropriate venders in the vender selection problems.

Expert systems are popular ways to solve very complex and hard problems. However, it is well-known that knowledge acquisition is a bottleneck process to develop them. Furthermore, the development of the systems can fail because there is no expert or an expert less qualified. In order to overcome the problems that they possess, this thesis focuses on an extended architecture of the expert systems. A simulator and an induction system are added to the existing architecture of expert systems. An expert system for schedule-based material requirements planning(SBMRP) has been implemented to show how the extended architecture works, and produces better results than existing SBMRP systems.

Many researches and analyses have been focused on industrial accidents in order to predict and reduce them. As a similar endeavor, this paper is to develop an expert system for prevention of industrial accidents. Although various previous studies have been performed to prevent industrial accidents, these studies only provide managerial and educational policies using frequency analysis and comparative analysis based on data from past industrial accidents. As an initial step for the purpose of this study, this paper provides a comparative analysis of 4 kinds of algorithms including CHAID, CART, C4.5, and QUEST. Decision tree algorithm is utilized to predict results using objective and quantified data as a typical technique of data mining. Enterprise Miner of SAS and Answer Tree of SPSS will be used to evaluate the validity of the results of the four algorithms. The sample for this work was chosen from 10,536 data related to manufacturing industries during three years(2002~2004) in korea. The initial sample includes a range of different businesses including the construction and manufacturing industries, which are typically vulnerable to industrial accidents.

급속도로 발전하는 산업의 고도화와 이에 따른 업종의 다양화, 이에 동반되는 예상치 못한 산업재해는 불특정 다수에게 인적, 물적 피해를 야기 시키고 있다. 산업재해 예방을 위해 다양한 선행 연구들이 진행되었으나 이들 연구는 기존의 산업재해 데이터를 토대로 빈도분석, 비교분석을 통한 관리적, 교육적 등치 대책만을 제시하고 있다. 본 연구에서는 산업재해 예방을 위해 객관적이고 정량화된 데이터를 통한 예측 분석이 가능한 데이터마이닝을 적용하여 대표적인 기법인 의사결정나무의 CHAID, CART, C4.5, QUEST 4가지 알고리즘 비교분석하여 산업재해 예방 및 전문가 시스템 구축을 위해 적용할 수 있는 최적의 알고리즘을 제시하도록 한다.

The purpose of this study was to develop an algorithm in which human arousal and pleasant level can be judged using measured physiological signals. Fuzzy theory was applied for mathematical handling of the ambiguity related to evaluation of human sensibility, and the degree of belonging to a certain sensibility dimension was quantified by membership function through which the sensibility evaluation was able to be done. Determining membership function was achieved using results from a physiological signal database of arousal/relaxation and pleasant/unpleasant that was generated from imagination. To induce one final result (arousal and pleasant level) based on measuring the results of more than 2 physiological signals and the membership function of each physiological signal, Dempster-Shafer's rule of combination in evidence was applied, through which the final arousal and pleasant level was inferred.

Visual FoxPro를 사용하여 한글 사용과 대용량 정보처리에 문제가 없고 비전문가의 사용이 용이한 전문가 시스템을 개발하였다. 본 시스템에서는 추론 방식으로 패턴매칭을 이용한 순방향 추론을 채택하였으며, 지식베이스는 IF∼THEN 규칙으로 표현하였다. 또한 추론결과의 확신도 계산에는 MYCIN 규칙을 이용하였으며, 윈도우에서의 추론을 위한 제반 자료와 규칙의 수정과 보완이 용이하도록 컨트롤 기능을 채택하였다. 개발된 추론엔진, 데이터베이스 그리고 사용자 인터페이스를 기반으로 모이와 토마토를 대상으로 한 생육장해진단 관련 데이터 베이스를 구축하여, 농민과 같은 비전문가의 활용이 용이한 생육장해 진단용 전문가 시스템을 개발하였다. 개발한 시스템의 사용상 편리성과 정확성을 농민과 농업 종사자들을 대상으로 조사한 결과, 사용자에 따라서 결론의 확신도에는 약간씩 차이가 있었으나 관행의 장해 진단방법과 비교할 때 유용한 것으로 나타났다. 또한 개발된 전문가 시스템의 기본 구조 및 추론엔진은 오이와 토마토 이외의 농작물 생육장해 진단에도 해당 데이터 베이스의 변경을 통하여 직접 응용이 가능할 것으로 기대된다.

To keep an enterprise's competitiveness on the condition of the automatic manufacturing system such as FA, FMS and CIM, all the maintenance problems should be considered seriously In not only in production and maintenance but also in related industrial safety. As we analyze in the surveys the maintenance management of domestic enterprises and the causes of Industrial accident, there will be necessity of drawing up countermeasures for preventing industrial accidents and for ensuring expertise maintenance technologies. Based on these analyses, the safety information system, maintenance management information system, and the machinery condition diagnosis technique are studied by using of the knowledge-based system under the real-time computer-operating environment and using fuzzy linguistic variable. This computer system based knowledge-based diagnosis can easily provide not only the knowledge of expert system about deterioration phenomenon of industrial robots, but also the knowledge of relating safety and facility all the time. Therefore, it is expected to improve the efficiency of business processes in the production and safety when we use this system.

The fault diagnosis is a systematic and unified method to find based on the observing data resulting in noises. This paper presents the fault prediction and diagnosis using fuzzy expert system technique to manipulate the uncertainties efficiently in predi