• Korean Management Science Review
• /
• v.15 no.1
• /
• pp.137-148
• /
• 1998

We proposed a framework for computer-supported credit evaluation systems for the effective management of credit risks in Korean commercial banks. Especially for medium and small sized companies, credit evaluators used to depend much on past experience rather than formalized principles and rules. Therefore, we applied case-based reasoning. The credit grade of a company is roughly determined by searching for alreadygraded similar companies in terms of usually accepted evaluation items. And then the grade is refined and adjusted by considering additional information about exceptional facts or by reflecting other evaluation results from different methods or techniques. Booch's object-oriented analysis and design method, Visual Basic 5.0 and MS Access 97 are used for the development of this prototype system.

• Journal of Intelligence and Information Systems
• /
• v.3 no.1
• /
• pp.111-142
• /
• 1997

정보 시스템 대한 유지 보수 문제는 소프트웨어 유지 보수 분야에서 지속적으로 존재하는 문제 중의 하나이며, 특히 이러한 정보 시스템들이 아주 오래 전에 COBOL이나 계측형 데이터베이스와 같은 기술을 바탕으로 개발되었음에도 불구하고 대부분의 조직에서 중요한 역할을 담당하고 있는 것이 현실이다. 따라서 이들 정보 시스템에 대한 효율적이고, 신속한 유지 보수는 조직에 있어 매우 중요한 업무임에도 불구하고, 대부분의 조직에서 이를 제대로 수행하고 있지 못하다. 체계적이고 효과적인 정보 시스템에 대한 유지 보수업무 수행을 위해 본 연구에서는 과거 유지 보수 사례를 이용하여 사례 지식을 축적할 수 있는 유지보수 사례의표현 방법 및 유사성 평가 방법과 이를 바탕으로 새로운 유지보수 요구에 적합한 과거 사례와 유지보수 대상 코드를 제안해 주는 사례 기반 유지 보수 대상 인식 방법론을 제시하였다. 이들 제안된 방법들의 타당성과 성과는 한국전력의 실제 정보 시스템을 대상으로 검증되었으며, 현장 업무에 적용되고 있다.

• Asia pacific journal of information systems
• /
• v.8 no.1
• /
• pp.1-26
• /
• 1998

본 연구에서는 사례기반추론, 인공신경망, 선형계획법 모형을 결합한 새로운 개념의 지능적인 경영전략수립 및 상충관계 해결 추론메카니즘을 제안한다. 본 연구에서 제안한 경영전략추론 메카니즘의 타당성을 검증하기 위하여 (1) 과거 문헌조사 결과와 (2) 비쥬얼 베이직 언어로 구현한 프로토타입인 CANNIE-SP (CAse-based Neural Network Inference Engine for Strategic Planning)를 제시하였다. 특히 본 연구에서 제안하는 인공신경망은 순방향 추론과 역방향 추론이 가능하도록 설계하여서 What-If분석 및 Goal-Seeking분석이 가능하도록 하였다. 또한 사례기반추론기관은 마이크로 소프트사의 데이터베이스 엔진인 엑세스(Access)를 사용하였다. 본 연구에서 제안하는 추론 메카니즘의 타당성을 검증하기 위하여 우리나라 화장품 시장의 실제자료를 가지고 실험하였으며 그 결과 매우 의미가 있음을 확인하였다.

• IE interfaces
• /
• v.16 no.1
• /
• pp.1-7
• /
• 2003

Today's manufacturing enterprise relies heavily on the collaboration and coordination among the distributed manufacturing systems. The effective exchange of the various manufacturing information among the distributed organizations contributes a great deal to their productivity. An Internet-Based Manufacturing Desk is developed for the production of the press dies in the automobile industry in order to solve the manufacturing problems among the distributed organizations, to maintain their smooth and immediate information flow, and to increase their productivity finally. The CBR(Case-Based Reasoning) method is applied to achieve those effects. Using the method, the solutions and methods of the predetermined case-bases are retrieved and applied to solve a newly introduced problem. The developed system is implemented and applied successfully.

• Korean Journal of Computational Design and Engineering
• /
• v.4 no.3
• /
• pp.224-237
• /
• 1999

This paper proposes a case-based approach to the conceptual design of mechanism, especially of the generation of design alternatives in function generation and motion transmission tasks. The aim of this work is to generate and provide various design alternatives by utilizing the previous design concepts underling in the existing design cases. The approach is based on the basic idea that the whole design concepts or sub-concepts extracted from different design cases can be merged to generate a variety of new design alternatives. The notion of virtual function generator is introduced to conceptualize and represent all possible underlying design concepts in the prior design cases. The virtual function generators are extracted in advance from the existing mechanism and serve as new conceptual building blocks for the synthesis of mechanism. Various design alternatives are generated basically by merging tow virtual function generators that partially match the specified function. By utilizing the design concepts that have been effectively used in the previous design cases. he proposed approach could efficiently produce more feasible design concepts than from-scratch ones. The approach proposed in this paper is illustrated with a design example.

• Proceedings of the Korea Inteligent Information System Society Conference
• /
• 2001.01a
• /
• pp.164-168
• /
• 2001

This paper introduces an agent system that assists in user's work on the Internet. First, the agent receives requests from the user or other agents. Since there are various kinds of requests, it is difficult to describe a completes set of request -handling rules in advance. Therefore, the agent makes a plan referring to old cases. The agent executes the plane which is a sequence of basic operation. If the agent fails to execute basic operation or to create a plan. then it makes a new plan by interacting with the user or other agent. Finally the agent stores this new case with user's evaluation score into the case base.

• The Journal of Society for e-Business Studies
• /
• v.11 no.2
• /
• pp.31-48
• /
• 2006

Commercial internet auction systems have been successfully used recently. In those systems, because auction prices of auction items are given by sellers only, the success bid rate can be decreased due to the large difference between the reserve price and the normal price. In this paper, we propose an agent that generates auction prices to sellers based on past auction data and item prices gathered from the web Through performance experiments, we show that the successful bid rate increases by preventing sellers from making unreasonable reserve prices. Using the pricing agent, we design and implement an XML-based auction system on the web.

• Journal of Intelligence and Information Systems
• /
• v.14 no.4
• /
• pp.179-200
• /
• 2008

We develop a feature selection method that can improve both the efficiency and the effectiveness of classification technique. In this research, we employ case-based reasoning as a classification technique. Basically, this research integrates the two existing feature selection methods, i.e., the univariate analysis and the LVF algorithm. First, we sift some predictive features from the whole set of features using the univariate analysis. Then, we generate all possible subsets of features from these predictive features and measure the inconsistency rate of each subset using the LVF algorithm. Finally, the subset having the lowest inconsistency rate is selected as the best subset of features. We measure the performances of our feature selection method using the data obtained from UCI Machine Learning Repository, and compare them with those of existing methods. The number of selected features and the accuracy of our feature selection method are so satisfactory that the improvements both in efficiency and effectiveness are achieved.

• Journal of the Korea Society of Computer and Information
• /
• v.12 no.3
• /
• pp.95-103
• /
• 2007

Existing human resources dispatch systems face various limits for managing increasing information derived from the work-place as it required much time managing the basic data created at the work-place and the data input methods are complicated. This study focuses on how to solve the above mentioned problems by utilizing the cellular phone system, which provides vital connection between the organizations using the dispatched human resources and the resources. The study offers building of a necessary work history data base and its management through development of a mobile human resources dispatch system. In order to optimally place the given resources, the system utilizes deductive analytical process. Utilizing the intelligent, deductive analytical process in properly planning the placing of the right human resources to do the job will result satisfaction in human resources dispatch and management.

• Journal of Korean Society for Geospatial Information Science
• /
• v.16 no.3
• /
• pp.87-94
• /
• 2008

In this study, deals with selection of monitoring objects to handle emergency cases of multi-modal transfer stations and information required for emergency surveillance, recognition, verification, propagation, processing and situation closing. Furthermore, this article suggests integrated management scheme for the above information and methods which offer appropriate information required for situation handling decisions at each stage of situation changes. The transfer station which consists of facilities, passengers, and transportations has limitations in required monitoring information. So, for the situation recognition and handling strategy, case-based reasoning of the expert system was used to apply experience, knowledge, and past cases of situation handling experts. The article also suggests methods to control facilities which are operated at transfer stations and these methods can minimize spatial confusions and damages at the emergency situation. The real time situation information will be shared by proper facility controls to support services from external institutions.