• Journal of the Korea Computer Industry Society
• /
• v.4 no.12
• /
• pp.919-936
• /
• 2003

Nowadays Electronic Commerce shopping mall is welcomed more and more on the Internet. It is expected that Shopping mall systems come to be various and adaptable to complex requirements according to customers who have these various needs, but just show products list, instead. This thesis suggests various structures of shopping malls showing interface agent model using Case-Based Reasoning one of reasoning method of Artificial Intelligence instead of the method of prior EC shopping mall. 1 constructed case base by making index with shopping mall members and customers' private informations, and pursued difference from prior EC shopping malls by proposing to customers cases of other users' selection of products who have similar private informations with them.

• The Journal of Society for e-Business Studies
• /
• v.13 no.4
• /
• pp.173-191
• /
• 2008

As volumes of electronic commerce increase rapidly, customers are faced with information overload, and it becomes difficult for them to find necessary information and select what they need. In this situation, recommender systems can help the customers search and select the products and services they need more conveniently. These days, the recommender systems play important roles in customer relationship management. In this research, we develop a recommender system that recommends the books to the customers of Internet bookstore. In previous researches on recommender systems, collaborative filtering technique has been often employed. For the collaborative filtering technique to be used, the rating scores on books given by previous purchasers have to be collected. However, the collection of rating scores is not an easy task in reality. Therefore, in this research, we employed case-based reasoning technique that can work only with the book purchase history of customers. The accuracy of recommendation of the resulting book recommender system was about 40% on the level 3 classification code.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.35 no.12B
• /
• pp.1219-1226
• /
• 2010

It is necessary to implementation of system contain intelligent decision making algorithm because discriminant and prediction system for Red Tide is insufficient development and the study of red tide are focused for the investigation of chemical and biological causing. In this paper, we designed inference system using case based reasoning method and implemented knowledge base that case for Red Tide. We used K-Nearest Neighbor algorithm for recommend best similar case and input 375 EA by case for Red Tide case base. As a result, conducted 10-fold cross verification for minimal impact from learning data and acquired confidence, we obtained about 84.2% average accuracy for Red Tide case and the best performance results in case by number of similarity classification k is 5. And, we implemented Red Tide monitoring system using inference result.

• Korean Journal of Construction Engineering and Management
• /
• v.12 no.1
• /
• pp.53-61
• /
• 2011

For construction projects, the importance of early cost estimates is highly recognized by the project team and sponsoring organization because early cost estimates are frequently a foundation of business decisions as well as a basis for identifying any changes as the project progresses from design to construction. However, it is difficult to accurately estimate construction cost in the early stage of a project due to various uncertainties in construction. To deal with these uncertainties, cost estimates should be made several times over the course of the project. In particular, early cost estimates are essential process for successful project management. For accurate construction cost estimates, it is necessary to compare cost estimates with actual costs based on historical project data. In this context, case-based reasoning (CBR), which is the process of solving new problems based on the solutions of similar past problems, can be considered as an effective method for cost estimating. To obtain this, it is also required to define the attribute similarities and the attribute weights. However, no existing method is capable of determining attribute weights of qualitative variables. Consequently, it has been a well-known barrier of accurate early cost estimates. Using Genetic Algorithms (GA), this research suggests the method of determining the attribute weight of qualitative variables. Based on building project case studies, the proposed methodology was validated.

• Proceedings of the Korean Information Science Society Conference
• /
• 2004.04b
• /
• pp.610-612
• /
• 2004

사례기반 추론 기법 등을 이용한 여행정보 제공 시스템은, 도메인 용어를 이용하여 사례 표현과 유사도 검색을 하기 때문에, 사례 기술의 제약을 받고, 사례 검색에서도 사용자가 요구하는 결과를 의미에 맞게 검색을 하지 못하며, 다른 시스템간의 상호운용성(interoperability)을 제공하지 못한다는 단점이 있다. 이러한 단점을 극복하기 위해, 여행정보 제공 시스템에 지역 온톨로지 정보를 이용하게 되면, 용어의 타입, 계층, 관계 등을 기술 할 수 있게 되어 사례기반 추론의 한계점을 극복하여 보다 의미적으로 정확한 사례표현과, 검색 결과를 생성할 수 있으며, 더 나아가 차세대 지능형 웹으로 급부상하는 시맨틱 웹에서도 활용이 가능하게 된다. 본 논문에서는, 지역 온톨로지 정보를 이용한 여행 정보 제공시스템의 장점에 대해 고찰하였으며, 그 증명용 프로그램을 설계 및 개발하였다. 본 논문에서 개발한 시스템은 사용자의 요구를 의미적으로 매핑 할 수 있으며, 용어 사이의 관계를 기술하여 여러 시스템 사이의 상호운용성(interoperability)을 제공하며, 분산 환경에서 데이터의 공유를 가능하게 한다.

• Journal of Intelligence and Information Systems
• /
• v.5 no.1
• /
• pp.65-80
• /
• 1999

선박설계는 그 과정이 매우 복잡하고 많은 양의 데이터를 다루고 있는 작업으로서 그 환경이 분산화, 이질화 됨에따라 최근들어 CSCW(Computer Supported Collaborative Work)의 요구가 증대되고 있다. 본 논문에서는 분산된 선박설계 환경에서의 협동작업을 지원하기 위한 에이전트 기반 선박설계 시스템을 개발하였다. 특히 여기서는 설계 에이전트간의 정보교환 및 지식공유를 통한 선박설계의 의사결정 과정에서 발생하는 의사충돌 문제를 해결하기 위하여 사례기반 추론 기법을 이용하여 이의 해결을 시도하였다. 설계 에이전트, 이들을 중재하는 퍼실리테이터, 충돌 처리기, 그리고 사례기반 시스템의 유기적인 도움을 받아 설계자는 설계과정에서 발생하는 설계 시스템간의 의사충돌 문제에 대한 의사결정을 과거의 유사한 문제해결 사례로부터 효과적으로 처리할 수 있다.

• 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.

• Proceedings of the Korea Inteligent Information System Society Conference
• /
• 2000.04a
• /
• pp.293-303
• /
• 2000

데이터 마이닝의 수행 예측 오차를 줄이기 위한 방법으로 하나의 문제를 여러 기법들을 결합하여 해결하고 있다. 본 연구에서는 새로운 결합 모델을 제시하고 이를 통해 예측 오차를 감소시킬 수 있는 가능성을 제시한다. 제시된 결합모델의 성능을 검증하기 위해서 국내 자동차보험 회사의 고객데이터를 바탕으로 고객이탈 예측문제를 다루었다. 결합모델의 예측결과를 의사결정나무, 사례기반추론 그리고 인공신경망 중 하나의 기법만을 사용하여 예측한 결과와 비교 평가하였다. 평가 결과, 결합 모델의 예측 적중률이 개별 기법의 예측 적중률보다 우수했다.

• Proceedings of the KAIS Fall Conference
• /
• 2010.05a
• /
• pp.428-431
• /
• 2010

오늘날 인터넷을 이용한 전자상거래 시장의 꾸준한 성장으로 수많은 쇼핑몰 회사들이 생겨났다. 이러한 쇼핑몰을 통해 고객들은 다양한 상품들을 손쉽게 구매할 수 있게 되었지만, 원하는 상품을 찾기 위해 수많은 쇼핑몰들을 검색해야 하는 문제점이 있다. 또한 고객이 상품을 검색하는데 있어서 고객이 원하지 않는 상품 정보를 제공함으로써 불편함을 초래하였다. 따라서 본 연구에서는 통합 쇼핑몰 검색시스템을 설계하였다. 통합 쇼핑몰 검색시스템은 온톨로지 매핑 기법을 통해 쇼핑몰 간의 온톨로지를 통합하고, 추천시스템 기법 중의 하나인 사례기반추론 기법을 활용하여 고객이 원하는 정확한 검색 결과를 제공하도록 설계하였다.

• The KIPS Transactions:PartD
• /
• v.9D no.6
• /
• pp.1009-1016
• /
• 2002

We design and implement a new case-based recommender system using implicit rating information for a digital content site. Our system consists of the User Profile Generation module, the Similarity Evaluation and Recommendation module, and the Personalized Mailing module. In the User Profile Generation Module, we define intra-attribute and inter-attribute weight deriver from own's past interests of a user stored in the access logs to extract individual preferences for a content. A new similarity function is presented in the Similarity Evaluation and Recommendation Module to estimate similarities between new items set and the user profile. The Personalized Mailing Module sends individual recommended mails that are transformed into platform-independent XML document format to users. To verify the efficiency of our system, we have performed experimental comparisons between the proposed model and the collaborative filtering technique by mean absolute error (MAE) and receiver operating characteristic (ROC) values. The results show that the proposed model is more efficient than the traditional collaborative filtering technique.