• 한국데이터정보과학회:학술대회논문집
• /
• 한국데이터정보과학회 2003년도 추계학술대회
• /
• pp.57-72
• /
• 2003

This article provides integrated neural network models for the interest rate forecasting using change-point detection. The model is composed of three phases. The first phase is to detect successive structural changes in interest rate dataset. The second phase is to forecast change-point group with data mining classifiers. The final phase is to forecast the interest rate with BPN. Based on this structure, we propose three integrated neural network models in terms of data mining classifier: (1) multivariate discriminant analysis (MDA)-supported neural network model, (2) case based reasoning (CBR)-supported neural network model and (3) backpropagation neural networks (BPN)-supported neural network model. Subsequently, we compare these models with a neural network model alone and, in addition, determine which of three classifiers (MDA, CBR and BPN) can perform better. For interest rate forecasting, this study then examines the predictability of integrated neural network models to represent the structural change.

• Journal of the Korean Data and Information Science Society
• /
• 제14권3호
• /
• pp.641-651
• /
• 2003

This study suggests the hybrid models for interest rate forecasting using structural changes (or change points). The basic concept of this proposed model is to obtain significant intervals caused by change points, to identify them as the change-point groups, and to reflect them in interest rate forecasting. The model is composed of three phases. The first phase is to detect successive structural changes in the U. S. Treasury bill rate dataset. The second phase is to forecast the change-point groups with data mining classifiers. The final phase is to forecast interest rates with backpropagation neural networks (BPN). Based on this structure, we propose three hybrid models in terms of data mining classifier: (1) multivariate discriminant analysis (MDA)-supported model, (2) case-based reasoning (CBR)-supported model, and (3) BPN-supported model. Subsequently, we compare these models with a neural network model alone and, in addition, determine which of three classifiers (MDA, CBR and BPN) can perform better. For interest rate forecasting, this study then examines the prediction ability of hybrid models to reflect the structural change.

• 한국지능정보시스템학회:학술대회논문집
• /
• 한국지능정보시스템학회 2005년도 공동추계학술대회
• /
• pp.258-263
• /
• 2005

Haplotype-based analysis using high-density SNP markers have gained a great attention in evaluating genes in gene analysis and various clinical situations. However, there has been no research on disease diagnostic modeling based on SNPs analysis to our knowledge. The purpose of this study is to explore how knowledge discovery techniques are applied in medical informatics area and proposes a Case Based Reasoning (CBR) technique for diagnosis of gastric caner using Single Nucleotide Polymorphism(SNP).

• Asia pacific journal of information systems
• /
• 제12권2호
• /
• pp.179-195
• /
• 2002

In this research, we developed an efficient Hangul document classification system for text mining. We mean 'efficient' by maintaining an acceptable classification performance while taking shorter computing time. In our system, given a query document, k documents are first retrieved from the document case base using the k-nearest neighbor technique, which is the main algorithm of case-based reasoning. Then, TFIDF method, which is the traditional vector model in information retrieval technique, is applied to the query document and the k retrieved documents to classify the query document. We call this procedure 'CB_TFIDF' method. The result of our research showed that the classification accuracy of CB_TFIDF was similar to that of traditional TFIDF method. However, the average time for classifying one document decreased remarkably.

• 한국소음진동공학회:학술대회논문집
• /
• 한국소음진동공학회 2000년도 춘계학술대회논문집
• /
• pp.1046-1050
• /
• 2000

The necessity of diagnosis of the rotating machinery which is widely used in the industry is increasing. If rotating machinery has fault, we can detect fault using vibration or noise. But, in diagnosing rotating machinery, the end user who doesn't have expert knowledge needs the help of vibration diagnosis expert. However, vibration diagnosis experts who well satisfy the demand of end user are rare. So, this paper propose a development of the case-based reasoning system for abnormal vibration diagnosis of rotating machinery we construct the past experiences of vibration diagnosis expert into case base and shear the experiences of diagnosis expert with the end user. In this paper, we describe that process of structured system and adapting result of abnormal vibration diagnosis of electric motor.

• 디지털콘텐츠학회 논문지
• /
• 제12권2호
• /
• pp.217-223
• /
• 2011

인공지능(AI : Artificial Intelligence)은 지능을 만들 수 있는 방법론이나 실현 가능성 등을 연구하는 컴퓨터 공학 및 정보기술과학 분야이다. 오델로(Othello) 게임은 다른 게임에 비해 규칙이 간단하며 $8{\times}8$인 제한적인 공간에서 이루어지기 때문에 AI로 제작되는 사례가 많다. 기존의 알고리즘은 추후에 발생하는 모든 경우의 수를 탐색하거나 룰을 이용하여 처리하기 때문에 처리시간이 오래 걸리며 새로운 상황에 대처하는데 효율적이지 않다. 본 연구에서는 이런 단점을 보안하고자 오델로 게임에 AI의 한 분야인 사례기반추론(CBR : Case-based Reasoning)알고리즘을 도입한다. CBR알고리즘 이란 주어진 문제를 해결하기 위해 과거에 있었던 유사한 문제를 검색하여 상황에 맞는 해결방법을 제시하는 방식을 의미한다. 지금까지 오델로 게임에 여러가지 AI기술을 이용하였으나 CBR알고리즘을 적용한 사례가 없었다. 본 연구에서는 CBR알고리즘을 오델로 게임에 적용하여 보다 빠른 연산속도로 다음 작업을 처리할 수 있으며 기존의 사례가 충분할 때는 새로운 상황에 효율적으로 대처할 수 있을 뿐 아니라 사용자로 하여금 보다 어려운 오델로 게임을 만들 수 있는 시스템을 제안한다.

• 지능정보연구
• /
• 제17권3호
• /
• pp.43-61
• /
• 2011

본 연구는 사용자의 정적, 외부환경과 연관된 동적 상황정보와 사회적 관계와 연관된 개인적 상황정보들을 의사결정 요소로서 고려한 의사결정의 동적 변환(Dynamic Adaptation)을 제안한다. 즉, 의사결정자의 정적, 외재적 정보보다 과거의 경험, 주관적 선호도 및 사회적 관계와 연관된 상황정보(Social Context)를 의사결정에 동적으로 반영하고 동시에 의사결정 해의 사용시점에서의 가용성에 따라 유용 가능한 대안을 추출하는 방법론을 제안하고자 한다. 이를 위해, 정적, 외재적 및 사회적 상황정보를 이용하여 의사결정 추론한다. 추론은 의사결정자의 과거 경험에 기반한 사례기반 추론과 해당 의사결정 결과가 가용하지 않을 경우 수정을 위한 제약식 만족추론으로 이루어진다. 이를 위해 개인적 경험 등의 정보에 기반한 '문제상황 온톨로지'(Problem Context Ontology)와 집단의 경험적 지식에 기반한 '솔루션 온톨로지'(Solution Ontology)를 구축하였다. 의사결정단계는 상황정보 인식 및 문제상황 온톨로지에 매핑하는 단계, 경험적 사례로부터 문제상황에 가장 적합한 사례를 선택하는 단계, 생성된 솔루션이 가용하지 않을 경우 솔루션 온톨로지와 제약식 만족추론을 통해 새로운 대안을 생성하는 단계로 이루어진다. 본 방법론을 모임에 적합한 식당을 제안하는 예제를 적용함으로써 타당성을 검증하였다. 또한 실험을 통해 사회적 상황정보를 고려하여 생성된 의사결정대안이 그렇지 않은 경우보다 의사결정자의 만족도를 향상시켰으며, 생성된 의사결정대안이 가용하지 않은 경우 제약조건식과 솔루션 온톨로지를 이용해 생성한 대안이 유의미함을 검증하였다.

• 한국정보통신학회논문지
• /
• 제14권4호
• /
• pp.875-885
• /
• 2010

사례기반추론(CBR:Case-Based Reasoning)은 기존 데이터와 사례 데이터들의 관계성을 추론하는 기법으로 유사도(Similarity)와 유클리디안(Euclidean) 거리 계산 방법이 가장 많이 사용되고 있다. 그러나 이 방법들은 기존 데이터와 사례 데이터를 모두 비교하기 때문에 데이터 검색과 필터링에 많은 시간이 소요되는 단점이 있다. 따라서 이를 해결하기 위한 다양한 연구들이 진행되고 있다. 본 논문에서는 기존의 유사도와 유클리디안 계산과정에서 발견된 패턴을 활용한 SE(Speed Euclidean-distance) 계산방법을 제안한다. SE 계산방법은 새로운 사례입력에 발견된 패턴과 가중치를 적용하여 빠른 데이터 추출과 수행시간 단축으로 시간적 공간적 제약사항에 대한 연산 속도를 향상시키고 불필요한 연산 수행을 배제하는 것이다. 실험을 통해 유사도나 유클리디안 방법으로 데이터를 추출하는 기존의 방법보다 제안하는 방법이 다양한 컴퓨터 환경과 처리 속도에서 성능이 향상됨을 확인할 수 있었다.

• 산업공학
• /
• 제21권4호
• /
• pp.411-417
• /
• 2008

An impeller is a type of high-speed rotor that is used to compress or transfer fluid under high-speed and pressure at high temperatures. The impeller is composed of an axial hub and several blades attached along the hub. The weight and shape of an impeller must be balanced, because their imbalances can cause noise and vibration, which can lead to the breakage of the impeller blades during operation. Thus, the hub and blades of an impeller are commonly machined in a 5-axis NC machine to obtain qualified surfaces. The impeller machining strategy or process plan can not be easily obtained due to the complex, overlapped and twisted shapes of impeller blades. Skillful machining process planners may generate appropriate machining strategies based on their experiences and floor data. However, in practice most shop floor data for the impeller machining is not well-structured such that it does not effectively provide a process planner with information for machining strategies and/or process plans. This paper reports the development of a case-based machining strategy support system (CBMS) that employs case-based reasoning to obtain the machining strategy of an impeller by using the existing machining strategies of the shop floor. The CBMS generates impeller machining strategies through a stepwise reasoning process considering the similarity features between the blade shapes and machining regions. A case study is provided to demonstrate that CBMS can generate useful machining strategies facilitating process planners. The developed system can simulate the tool paths of impeller machining and runs on the web.

• 한국경영과학회지
• /
• 제28권3호
• /
• pp.81-101
• /
• 2003

The financial statements purpose to provide useful information to decision-making process of business managers. The value-relevant information, however, embedded in the financial statement has been often overlooked in Korea. In fact, the financial statements in Korea have been utilized for nothing but account reports to Security Supervision Boards (SSB). The objective of this study is to develop earnings forecasting models through financial statement analysis using artificial intelligence (AI). AI methods are employed in forecasting earnings: artificial neural networks (ANN) for manufacturing industry and case~based reasoning (CBR) for banking industry. The experimental results using such AI methods are as follows. Using ANN for manufacturing industry records 63.2% of hit ratio for out-of-sample, which outperforms the logistic regression by around 4%. The experiment through CBR for banking industry shows 65.0% of hit ratio that beats the statistical method by 13.2% in holdout sample. Finally, the prediction results for manufacturing industry are validated through monitoring the shift in cumulative returns of portfolios based on the earning prediction. The portfolio with the firms whose earnings are predicted to increase is designated as best portfolio and the portfolio with the earnings-decreasing firms as worst portfolio. The difference between two portfolios is about 3% of cumulative abnormal return on average. Consequently, this result showed that the financial statements in Korea contain the value-relevant information that is not reflected in stock prices.