• 대한산업공학회지
• /
• 제18권1호
• /
• pp.105-120
• /
• 1992

An expert system was developed as a framework of integrating diverse and multifactored ergonomic knowledge to investigate its effectiveness in ergonomic workplace design and evolution. Although numerous computer-assisted approaches have been made to overcome the lack of integrated design principles, those models being used require very specific information of various design activities that may not be available in the design stage. On the other hand, an expert system would be an effective design aid that is capable of guiding the designer to solve a problem. However, most expert systems lack detailed evaluation capabilities due to a qualitative nature of inference mechanisms. Furthermore, those approaches were independently developed, focusing mostly on a single aspect such as biomechanics, physiology, etc. In this paper, a design framework was developed which takes advantage of expert system metholologies, a relational data base and existing ergonomic models. The pattern-directed, rule-based expert system allows the designer to gradually formulate and subsequently evaluate workplace design. A comprehensive and modularized knowledge base was built incorporating biomechanics, physiology and psychophysics, which is, in turn, capable of accessing not only qualitative knowledge but complex analytic evaluation models and massive information in the data base through an interface. A conflict resolution strategy using multiple criteria decision-making schemes was also employed to reconcile multiple design alternatives.

• Transactions on Control, Automation and Systems Engineering
• /
• 제1권1호
• /
• pp.54-61
• /
• 1999

FCM(Fuzzy Cognitive Map) is proposed for representing causal reasoning. Its structure allows systematic causal reasoning through a forward inference. By using the FCM, authors have proposed FCM-based fault diagnostic algorithm. However, it can offer multiple interpretations for a single fault. In process engineering, as experience accumulated, some form of quantitative process knowledge is available. If this information can be integrated into the FCM-based fault diagnosis, the diagnostic resolution can be further improved. The purpose of this paper is to propose an enhanced FCM-based fault diagnostic scheme. Firstly, the membership function of fuzzy set theory is used to integrate quantitative knowledge into the FCM-based diagnostic scheme. Secondly, modified TAM recall procedure is proposed. Considering that the integration of quantitative knowledge into FCM-based diagnosis requires a great deal of engineering efforts, thirdly, an automated procedure for fusing the quantitative knowledge into FCM-based diagnosis is proposed by utilizing self-learning feature of neural network. Finally, the proposed diagnostic scheme has been tested by simulation on the two-tank system.

• 대한안전경영과학회지
• /
• 제1권1호
• /
• pp.101-110
• /
• 1999

QFD is a market driven design and development methodology for products and services to meet or exceed customer's needs and expectations, This method enables to specify clearly the customer's needs and then evaluate the product capability in terms of its impact on meeting those needs. Process of satisfying customers begins with effectively soliciting their different needs and wants which may be non-technical and imprecise in nature. Although the HoQ is a comprehensive tool for showing the relationships between attributes, it lacks the flexibility to deal with the inherent inexactness and vagueness in the voice of customer. In this paper, fuzzy theory is introduced to overcome this limitation. Qualitative customer requirements are interpreted quantitative data through fuzzy inference procedure, and then target value is determined.

• 산업경영시스템학회지
• /
• 제20권43호
• /
• pp.37-46
• /
• 1997

제품의 정성적 품질평가에서, 제품의 최종품질을 구성하는 다수의 특성에 대한 만족도가 언어로써 표현되어 소비자의 구매행동이란 의사결정으로 표출되는데, 이러한 주관적 평가에는 평가의 애매함(fuzziness)이 수반되므로 품질의 평가구조를 합리적으로 파악하기 위해서는 애매함의 존재를 고려에 넣지 않으면 안된다. 다수의 품질특성이 계층적(hierarchical)인 구조로 연결되어 최상위 품질특성으로 구성되며, 특성간의 중요도(relative importances)가 계층별로 결정되는 경우, 이들 개개의 특성에 대한 만족도의 평가로부터 어떤 구조적인 관계를 통해 그 제품에 대한 종합평가가 이루어지나, 개개의 특성에 대한 평가가 애매한 이상 최종 결과인 종합적 만족도도 애매한 것으로 된다. 즉, 평가모델의 구조도 평가의 패턴도 퍼지화되므로 이러한 평가에서 퍼지이론의 응용에 따른 효과를 가장 크게 기대할 수 있는 퍼지추론모델을 이용하여 계층간, 품질특성간의 퍼지관계와 특성의 중요도 및 언어변수(linguistic variables)의 형태로 주어지는 입력정보로써 품질구조를 명확히 하고, 패턴인식(pattern recognition)의 개념을 이용하여 평가자의 제품에 대한 평가결과를 언어로써 표현한다.

• 한국지능시스템학회:학술대회논문집
• /
• 한국퍼지및지능시스템학회 1993년도 Fifth International Fuzzy Systems Association World Congress 93
• /
• pp.887-890
• /
• 1993

By introducing the notion of constraint-oriented fuzzy inference, we will show that it provides us ways of fuzzy control methods that has abilities of adaptation, learning and self-organization. The basic supporting techniques behind these abilities are“hard”processing by Artificial Intelligence or traditional computational framework and“soft”processing by Neural Network or Genetic Algorithm techniques. The reason that these techniques can be incorporated to fuzzy control systems is that the notion of“constraint”itself has two fundamental properties, that is, the“modularity”property due to its declarativeness and the“logicality”property due to its two-valuedness. From the former property, the modularity property, decomposing and integrating constraints can be done easily and efficiently, which enables us to carry out the above“soft”processing. From the latter property, the logicality property, Qualitative Reasoning and Instance Generalization by Symbolic Reasoning an be carried out, thus enabling the“hard”processing.

• 한국정밀공학회지
• /
• 제12권6호
• /
• pp.37-44
• /
• 1995

Grinding is used for machining high precision parts with high additional value. However, the grinding operation needs high skill and long experience of an operator because of a lack of the scientific knowledge and engineering principles. Also, the wheel and grinding conditions affect grinding results. For these reasons, it is difficult to construct computer integrated manufacturing system(CIMA). Therefore, it is necessary for Expert System to be informed of qualitative knowledge of grinding expert's skills and experiences. In this research, the Grinding Expert System is constructed by Fuzzy Decision Making Algorithm. Using this system, unskilled workers will be able to use the knowledge and experience of an expert.

• 한국수자원학회논문집
• /
• 제37권6호
• /
• pp.449-460
• /
• 2004

본 논문에서는 월 댐유입량을 예측하는데 있어서 기상예보정보를 활용한 뉴로-퍼지 시스템의 적용성을 검토하였다. 뉴로-퍼지 알고리즘으로 퍼지이론과 신경망이론의 결합형태인 ANFIS(Adaptive Neuro-Fuzzy Inference System)을 이용하여 모형을 구성하였다. ANFIS의 공간분할에 의한 제어규칙의 선정에 있어 퍼지변수가 증가함에 따라 제어규칙이 기하급수적으로 증가하는 단점을 해결하기 위해 퍼지 클러스터링(Fuzzy Clustering)방법 중 하나인 차감 클러스터링(Subtractive Clustering)을 사용하였다. 또한 본 연구에서는 정성적인 기상예보정보를 정량화 시키는 방법을 제안하였다. AMFIS를 이용하여 월 댐유입량 예측 시, 관측자료만으로 구성된 모형에 의한 예측결과와 관측자료에 기상예보정보를 더하여 구성된 모형에 의한 예측결과를 비교하였다. 그 결과 ANFIS는 기상예보정보를 활용하여 댐유입량을 예측했을 때가 관측자료만으로 예측했을 때보다 예측능력이 더욱 정확함을 보였다.

• 실천공학교육논문지
• /
• 제10권1호
• /
• pp.63-72
• /
• 2018

본 연구는 상담수퍼비전에서 수퍼바이저와 수퍼바이지의 관계인 작업동맹의 중요성에 주목하여 최근 국내 연구 동향을 분석하고, 향후 연구의 방향을 제시하기 위해 수행되었다. 이를 위해 분석대상 12편의 논문에 대해 연도별, 연구대상과 상담자 요인, 연구방법에 따라 분석하였다. 그 결과를 살펴보면 첫째, 2006년을 시작으로 총 12편의 연구가 진행되어 매우 부족함을 알 수 있었다. 둘째, 연구대상은 수퍼바이지(83.3%)로 편중되어 수퍼바이저와 수퍼바이지(16.7%), 수퍼바이저(0%) 대상 연구는 부족하였다. 또한 상담자 특성에 대한 연구도 수퍼바이저(17.3%)는 추론된 상태(8.3%), 추론된 특성(3.5%)이 높았다. 수퍼바이지 (82.5%)도 추론된 상태(56.3%)와 추론된 특성(27.1%)으로 연구되어 관찰가능한 상태와 특성에 대한 연구는 매우 미흡함을 알 수 있었다. 셋째, 연구방법으로는 양적 연구(100.0%)로 이루어져 질적연구가 매우 부족한 실정임을 알 수 있었다. 끝으로, 이러한 결과에 대한 논의, 연구의 제한점, 향후 연구에 대해 제언하였다.

• 한국의류학회지
• /
• 제29권3_4호
• /
• pp.425-437
• /
• 2005

The purpose of this study was to identify the categories and contents of the cognitive inferences of both men and women regarding the style and color of clothing. The study was conducted by survey method, using open-ended questions. The data were collected from 420 male/female university students and analyzed by the qualitative method. The main results are as follows: First, cognitive inferences are formed from stereotypes that fall into six categories--appearance, personality, background, behavior, situation, and reaction. Second, there are some differentiations in these stereotypes depending on clothing style and color. Specifically, the amount of exposure represented in the clothing style is a salient features, one that shows situational attribution. Third, the strength of stereotype differs depending on the sex of perceivers: women indicate a stronger tendency to stereotype-based on clothing-than do men. In conclusion, each of cognitive inferences occurs between wearer and the actual perceiver. Stereotypes are important determining factors fDr making cognitive inferences.

• 한국생물정보학회:학술대회논문집
• /
• 한국생물정보시스템생물학회 2005년도 BIOINFO 2005
• /
• pp.202-205
• /
• 2005

Cell phenotypes are determined by the concerted activity of thousands of genes and their products. This activity is coordinated by a complex network that regulates the expression of genes. Understanding this organization is crucial to elucidate cellular activities, and many researches have tried to construct gene regulatory networks from mRNA expression data which are nowadays the most available and have a lot of information for cellular processes. Several computational tools, such as Boolean network, Qualitative network, Bayesian network, and so on, have been applied to infer these networks. Among them, Bayesian networks that we chose as the inference tool have been often used in this field recently due to their well-established theoretical foundation and statistical robustness. However, the relative insufficiency of experiments with respect to the number of genes leads to many false positive inferences. To alleviate this problem, we had developed the algorithm of MONET(MOdularized NETwork learning), which is a new method for inferring modularized gene networks by utilizing two complementary sources of information: biological annotations and gene expression. Afterward, we have packaged and improved MONET by combining dispersed functional blocks, extending species which can be inputted in this system, reducing the time complexities by improving algorithms, and simplifying input/output formats and parameters so that it can be utilized in actual fields. In this paper, we present the architecture of MONET system that we have improved.