• 한국지능시스템학회논문지
• /
• 제5권3호
• /
• pp.92-100
• /
• 1995

Fuzzy reasoning has been applied to analysis of traffic problems on urban arterial road. As the analysis on factors of route choice has been already carried out, its result can be used for construction of the model. Route choice rate estimation by fuzzy reasoning was discussed from its structure and accuracy. The major objective of the study is to introduce some kinds of methods with fuzzy reasoning and to make their feature obvious. First, the production system model is introduced with consideration of reality to actual travel behavior. Second, overlapping areas of fuzzy language function are investigated. Finally, process of fuzzy reasoning was also considered. Five kinds of Fuzzy reasoning are compared to investigate in relation between shapes of membership function and estimation validity.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 1999년도 하계학술대회 논문집 B
• /
• pp.543-545
• /
• 1999

In this paper, the composition method of global and local fuzzy reasoning concepts is researched for reducing the number of rules, not losing the performance for fuzzy controller. A new method is proposed in details that controls the interaction between global reasoning and local reasoning. In order to automatically acquire and optimize the method, the DNA coding algorithm is introduced to the local fuzzy reasoning of the proposed composition fuzzy reasoning method. The method is applied to the real liquid level control system for the purpose of evaluating the Performance. The simulation results show that the proposed technique can produce the fuzzy rules with higher accuracy and feasibility than the conventional methods.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• 제8권4호
• /
• pp.254-259
• /
• 2008

Uncertainty of result of context awareness always exists in any context-awareness computing. This falling-off in accuracy of context awareness result is mostly caused by the imperfectness and incompleteness of sensed data, because of this reasons, we must improve the accuracy of context awareness. In this article, we propose a novel approach to model the uncertain context by using ontology and context reasoning method based on Bayesian Network. Our context aware processing is divided into two parts; context modeling and context reasoning. The context modeling is based on ontology for facilitating knowledge reuse and sharing. The ontology facilitates the share and reuse of information over similar domains of not only the logical knowledge but also the uncertain knowledge. Also the ontology can be used to structure learning for Bayesian network. The context reasoning is based on Bayesian Networks for probabilistic inference to solve the uncertain reasoning in context-aware processing problem in a flexible and adaptive situation.

• 한국지능시스템학회:학술대회논문집
• /
• 한국퍼지및지능시스템학회 1993년도 Fifth International Fuzzy Systems Association World Congress 93
• /
• pp.1145-1150
• /
• 1993

In this paper, two methods of fuzzy modeling are prsented to describe the input-output relationship effectively based on relation characteristics utilizing simplified reasoning and neuro-fuzzy reasoning. The methods of modeling by the simplified reasoning and the neuro-fuzzy reasoning are used when the input-output relation of a system is 'crisp' and 'fuzzy', respectively. The structure and the parameter identification in the modeling method by the simplified reasoning are carried out by means of FCM clustering and the proposed GA hybrid scheme, respectively. The structure and the parameter identification in the modeling method by the neuro-fuzzy reasoning are carried out by means of GA and BP algorithm, respectively. The feasibility of the proposed methods are evaluated through simulation.

• 한국해양공학회지
• /
• 제11권1호
• /
• pp.36-43
• /
• 1997

Weld bead shape is an important measure for evaluation of weld quality. Many welding parameters have influence on the weld bead shape. The quantitative relationship between welding parameters and bead shape, however, is not determined yet because of their high complexity and many unknown factors. Fuzzy expert system is an advanced expert system which uses fuzzy rules and approximate reasoning. It is a vert useful tool for welding technology because is can process rationally the uncertain and inexact information such as the welding information. In this paper, the empirical and the qualitative relationship between welding parameters and bead shape are analyzed and represented by fuzzy rules. They are converted to the quantitative relationship by use of approximate reasoning of fuzzy expert system. Weld bead shape is estimated from the welding parameters using fuzzy expert system. The result of comparison between measured values of weld bead by welding experiments and the estimates values by fuzzy expert system shows a good consistancy.

• 정보처리학회논문지B
• /
• 제15B권1호
• /
• pp.45-52
• /
• 2008

최근 IT 서비스 발달과 함께 고장제어, 고장의 원인분석 등의 복잡한 문제에 대하여 적합한 해결책을 제시할 수 있는 효과적인 진단시스템의 필요성이 커지고 있다. 따라서 본 논문에서는 지능형 진단 시스템분야에서의 시스템의 성능을 향상시키고, 최적의 진단을 수행하고자 사례기반추론과 인공신경망을 혼합한 지능형 진단 시스템을 제안 한다. 사례기반추론은 과거의 사례(경험)를 통해 현재의 제시된 문제를 해결하는 추론방식으로, 지식 획득이 덜 복잡하고, 정형화되기 어려운 규칙이나 문제영역이 불분명한 분야를 효율적으로 추론할 수 있다. 하지만 사례기반추론만을 이용해 추론된 사례는 증상에 대해 다수의 원인을 추론하게 된다. 이때 추론된 증상에 따른 다수의 원인은 동일한 가중치를 가져 불필요한 원인까지 진단해야 하는 문제점이 있다. 이러한 문제를 해결하고자 인공신경망의 오류역전파 학습 알고리즘을 이용하여 증상에 대한 원인들의 쌍을 학습 시킨 후 각각의 증상에 대한 원인의 가중치를 구해 제시된 증상에 대해 가장 발생 가능성이 높은 원인을 찾아내어, 보다 명확하고 신뢰성 있는 진단을 하는 데 그 목적이 있다.

• 지능정보연구
• /
• 제8권1호
• /
• pp.159-173
• /
• 2002

사출금형 공정계획이란 금형설계를 완료한 후에 설계된 금형을 경제적, 효율적으로 생산하기 위하여 수행하는 제조공정에 대한 계획이다. 이러한 공정계획은 전문가의 수작업에 의한 수립에 의한 문제, 전문가의 양성과 부족현상, CAD/CAM 시스템 보급 및 생산형태의 다품종소량화 현상에 의해 자동화가 필요하다. 본 연구에서는 사례기반추론(Case-Based Reasoning)을 이용하여 IIMPPS(Intelligent Injection Mold Process Planning System)라는 사출금형 공정계획시스템을 개발하였다. 사출금형 공정계획을 자동화하기 위해서 사례기반 추론을 사용한 이유는 사출금형이라는 제품은 금형의 종류와 구조 등에 따라 공정계획이 매우 다양하게 수립되지만, 성형품의 용도나 품명이 같은 경우에는 공정이 거의 유사하여, 과거에 수립된 공정계획이 새로운 금형의 공정 계획에 매우 유용하게 사용될 수 있기 때문이다. 그리고 본 연구에서는 IIMPPS의 타당성을 평가하기 위하여 전문가의 정성적인 평가와 공정계획의 정확도 평가를 수행하였다.

• 한국해양공학회지
• /
• 제21권2호
• /
• pp.81-86
• /
• 2007

This paper presents a computer aided process planning system integrating case-based reasoning and expert system for block assembly in shipbuilding. Expert rules are extracted from the case-base where cases are represented as a set of constraint-satisfaction problems. Rules for the expert system are extracted by generalizing the constraints. In generalizing the constraints, parts are generalized as variables or as part-types. The system was developed with CLIPS, an expert system shell. As more cases are collected, more rules will be extracted and the existing rules will be updated.

• 한국지능시스템학회논문지
• /
• 제13권1호
• /
• pp.31-36
• /
• 2003

기존의 점수와 석차로서 학생을 평가하여 발생하는 문제점을 해결하기 위하여 서술식의 성적평가가 도입되고 있다. 그러나, 이 서술식으로 이루어지는 성적 평가는 업무를 증가시키고 또 교사의 주관적인 성 적평가로 인해 성 적 처리의 일관성이 유지되기 어려운 문제점이 있다. 본 논문에서는 교사가 학생의 성적평가를 효과적으로 하기 위하여 퍼지 추론을 이용한 서술식 성적평가 시스템을 제안한다. 교사로부터 수행평가요소의 결과를 입력받아, 과목의 최종적인 평가를 퍼지 추론에 적용하여 객관적인 성적평가를 한 후, 추론규칙의 적합도를 이용하여 성적평가 문장을 추출하여 서술식 평가 문장을 생성한다.

• 산업경영시스템학회지
• /
• 제21권46호
• /
• pp.181-196
• /
• 1998

The aim of this research is the development of a CAPP system which can use the old experience of process planning to generate a process plan for a new part and learn from its own experience using the concept of stratified case-based reasoning(CBR). A process plan is determined through the hierarchical process planning procedure that is based on the hierarchical feature structure of a part. Each part and case have their own multiple abstractions that are determined by the feature structure of the part. Retrieving the case in stratified case-based process planning is accomplished by retrieving the abstraction that is most similar to the input part abstraction in each abstraction level of the case-base. A new process plan is made by the adaptation that translates the old case's process plan into the process plan of a new part. Operations, machines and tools, setups and operation sequence in each setup are determined in the adaptation of abstraction using some algorithms and the reasoning based on knowledge-base. By saving a new part and its process plan as a case, the system can use this new case in the future to generate a process plan of a similar part. That is, the system can learn its own experience of process planning. A new case is stored by adding the new abstractions that are required to save as the new abstraction to the existing abstractions in the case-base.