• 한국전자거래학회지
• /
• 제12권1호
• /
• pp.99-122
• /
• 2007

규칙 기반 시스템은 업무 담당자의 비즈니스 노하우 및 전문 지식에 대한 처리는 물론, 기업의 비즈니스 로직까지 처리하여 새로운 비즈니스 모델 변화와 개선요구에 대해 즉각적으로 대응할 수 있는 규칙 기반 추론 엔진으로, 최근 다양한 산업으로의 적용이 시도되고 있다. 이에 이 논문에서는 규칙 기반 시스템 적용 사례의 일환으로, 다양한 소비자 니즈, 수많은 종류의 상품, 그리고 시시각각 변하는 대내외 환경에 민감하게 영향을 받는 보험 산업에서의 효율적인 보험 상품 추천과 설계를 위한 규칙 기반의 보험 상품 추천 및 설계 시스템을 설계하고 구현하고자 한다. 개발된 시스템은 퍼지추론 과정을 통해 고객의 개인정보와 기존 가입고객의 가입정보를 이용하여 보험상품 설계를 원하는 고객에게 맞춤형 보험상품을 추천하고 설계하고자 한다. 이러한 시도는 향후 보험 산업에 있어서 상품에 대한 다양한 고객들의 니즈를 즉각적으로 판단하고 대응하여 보다 정확하고, 고객 개개인의 욕구에 맞는 맞춤형 상품추천 및 설계를 위한 핵심 기술로서 자리 잡을 수 있을 것으로 기대된다.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2001년도 하계학술대회 논문집 D
• /
• pp.2308-2310
• /
• 2001

In the adaptive fuzzy sliding mode control, from a set of a fuzzy IF-THEN rules adaptive fuzzy sliding mode control whose parameters are adjusted on-line according to some adaptation laws is constructed for the purpose of controlling the plant to track a desired trajectory. Most of the research works in nonlinear controller design using fuzzy systems consider the affine system with fixed grid-rule structure based on system state availability. The fixed grid-rule structure makes the order of the controller big unnecessarily, hence the on-line fuzzy rule structure and fuzzy observer based adaptive fuzzy sliding mode controller is proposed to solve system state availability problems. Therefore, adaptive laws of fuzzy parameters for state observer and fuzzy rule structure are established implying whole system stability in the sense of Lyapunov.

• International Journal of Control, Automation, and Systems
• /
• 제1권3호
• /
• pp.321-331
• /
• 2003

Experimental software datasets describing software projects in terms of their complexity and development time have been the subject of intensive modeling. A number of various modeling methodologies and modeling designs have been proposed including such approaches as neural networks, fuzzy, and fuzzy neural network models. In this study, we introduce the concept of the Rule-based fuzzy polynomial neural networks (RFPNN) as a hybrid modeling architecture and discuss its comprehensive design methodology. The development of the RFPNN dwells on the technologies of Computational Intelligence (CI), namely fuzzy sets, neural networks, and genetic algorithms. The architecture of the RFPNN results from a synergistic usage of RFNN and PNN. RFNN contribute to the formation of the premise part of the rule-based structure of the RFPNN. The consequence part of the RFPNN is designed using PNN. We discuss two kinds of RFPNN architectures and propose a comprehensive learning algorithm. In particular, it is shown that this network exhibits a dynamic structure. The experimental results include well-known software data such as the NASA dataset concerning software cost estimation and the one describing software modules of the Medical Imaging System (MIS).

• 전자공학회논문지B
• /
• 제28B권7호
• /
• pp.557-565
• /
• 1991

The activated sludge process is a commonly used method for terating sewage and waste waters. The process is chatacterized by a lack of measurement instrumentations and control goals that are not always clear and not well understood. In such process, fuzzy control concept may be able to be adapted, do this paper presents a design method for fuzzy controller based on a selected sub-rule set from the total rule set and a multivariable fuzzy reasoning algorithms. In order to achievesystematic and efficient control of the activated sludge process under a great deal of disiutbances and a variety of perfotmance characteristics, a top-level rule-based fuzzy controller os proposed which provises lower-controllers with the suitable set-points according tothe onput-output states of the process.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2002년도 하계종합학술대회 논문집(2)
• /
• pp.209-212
• /
• 2002

As the mask design rules get smaller, the probability of the process failure becomes higher doc to the narrow overlay margin between the contact and metal interconnect layers. To obtain the minimum process margin, a tabbing and cutting method Is applied with the rule based optical\ulcorner proximity correction to the metal layer, so that the protection to bridge problems caused by the insufficient space margin between the metal layers can be accomplished. The side-lobe phenomenon from the attenuated phase shift mask with the tight design rule is analyzed through the aerial image simulation for test patterns with variation of the process parameters such as numerical aperture, transmission rate, and partial coherence. The corrected patterns are finally generated by the rules extracted from the side-lobe simulation.

• 한국BIM학회 논문집
• /
• 제12권1호
• /
• pp.42-54
• /
• 2022

BIM facilitates data transparency and consistency through three-dimensional parametric modeling and promotes the accurate managing and sharing of project information. In Korea, however, BIM-based detailed design of architectural interior finishes required during the Construction Documents phase increases the burden on architectural firms due to frequent design changes and manual workload. Therefore, the purpose of this study was to establish rule-based modules using parametric modeling that automates repetitive tasks that occur during the detailed design of interior finishing. Interviews with practitioners were conducted to analyze the major finishing elements. Of these floors, walls, and ceilings, which were the most rudimentary and common items, were selected as the subjects of the study. The modules developed in this study have two functions. One is to create new finish types, and the other is the automatic modeling of new types into rooms. For these functions, parameters that belonged to each finish and room element in a BIM model were analyzed and valid parameters directly used for parametric modeling were derived. Then, based on these parameters, rule-based modules for three elements, I.e., floors, walls, and ceilings were constructed with Revit Dynamo, and the effectiveness of the modules was verified with a pilot test. In conclusion, this study suggested a series of processes for automatic finishing to improve the efficiency of BIM-based architectural detailed design of finishes and to contribute in solving the chronic problems occuring during current design processes.

• Journal of Smart Tourism
• /
• 제3권1호
• /
• pp.41-47
• /
• 2023

Tourism and hospitality have encountered significant changes in recent years as a result of the rapid development of information technology (IT). Customers now expect more expedient services and customized travel experiences, which has intensified competition among service providers. To meet these demands, businesses have adopted sophisticated IT applications such as ChatGPT, which enables real-time interaction with consumers and provides recommendations based on their preferences. This paper focuses on the AI support-prompt middleware system, which functions as a mediator between generative AI and human users, and discusses two operational rules associated with it. The first rule is the Information Processing Rule, which requires the middleware system to determine appropriate responses based on the context of the conversation using techniques for natural language processing. The second rule is the Information Presentation Rule, which requires the middleware system to choose an appropriate language style and conversational attitude based on the gravity of the topic or the conversational context. These rules are essential for guaranteeing that the middleware system can fathom user intent and respond appropriately in various conversational contexts. This study contributes to the planning and analysis of service design by deriving design rules for middleware systems to incorporate artificial intelligence into tourism services. By comprehending the operation of AI support-prompt middleware systems, service providers can design more effective and efficient AI-driven tourism services, thereby improving the customer experience and obtaining a market advantage.

• 한국IT서비스학회지
• /
• 제9권3호
• /
• pp.123-144
• /
• 2010

As knowledge becomes a critical success factor of companies nowadays, lots of rule-based systems have been and are being developed to support their activities. Large number of rule-based systems serve as Web sites to advise, or recommend their customers. They usually use a backward chaining inference algorithm based on backtrack to implement those interactive Web-enabled rule-based systems. However, when the users like customers are using these systems interactively, it happens frequently where the users do not know some of the answers for the questions from the rule-based systems. We are going to design a backward chaining inference methodology considering unknown facts based on backtrack technique. Firstly, we review exact and inexact reasoning. After that, we develop a backward chaining inference algorithm for exact reasoning based on backtrack, and then, extend the algorithm so that it can consider unknown facts and reduce its search space. The algorithm speeded-up inference and decreased interaction time with users by eliminating unnecessary questions and answers. We expect that the Web-enabled rule-based systems implemented by our methodology would improve users' satisfaction and make companies' competitiveness.

• 한국CDE학회논문집
• /
• 제15권6호
• /
• pp.440-448
• /
• 2010

At the early design stage, a designer would develop a design through reviewing various alternatives. However, the limitation of human information handling capacity restricts what makes various alternatives. A way to overcome the limitation is to create the alternatives with computer power and the generative design concept with computer has been used. For the generative design, even if a great deal of methodologies has been presented, the core of methodologies would be the process of shapes which examine interrelationship among shapes and how shape can be changed with the interrelationship. The interrelationship can be represented as rules. To represent the rule, the shape grammar is suggested by Stiny in 1972 with the article of "Shape Grammars and the Generative Specification of Painting and Sculpture". The aim of this paper is to present a way of using generative design based on shape grammar for generating alternatives in 3D manner.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 1992년도 하계학술대회 논문집 A
• /
• pp.261-264
• /
• 1992

In designing the fuzzy rule-based system, it has effected by the four significant factors such as the choice of membership function, scaling factor, the numbers of fuzzy control rule, the method of defuzzification. In this paper we design the fuzzy rule based system and evaluate by three factors, as followes reaching time, overshoot, and amplitude. And then we wiII show that the significant factors are the choice of scaling factor and the numbers of fuzzy control rule, and the system performance can be improved by the proper selection of the scaling factors.