• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2004.10a
• /
• pp.1061-1065
• /
• 2004

The knowledge-based society of the 21st century requires effective education and learning methods in each professional field because the development of human resource determines its competence more than any other factors. It is highly desirable to develop an intelligent tutoring system, which meets ever increasing demands of education and learning. Such a system should be adaptive to each individual learner's demands as well as the continuously changing state of the learning process, thus enabling the effective education. The development of a learning environment based on learner modeling is necessary in order to be adaptive to individual learning variants. An intelligent learning environment is being developed targeting the heritage education, which is able to provide a customized and refined learning guide by storing the content of interactions between the system and the learner, analyzing the correlations in learning situations, and inferring the learning preference from the learner's learning history. This paper proposes a heritage learning system of Bulguksa temple, integrating the ontology-based learner modeling and the learning preference which considers perception styles, input and processing methods, and understanding process of information.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.10 no.12
• /
• pp.2212-2220
• /
• 2006

Recently enterprises introduce EAI systems and legacy business which already obtained for data integration among legacy systems. EAI systems in cooperative transaction environment can be expected efficient retrieval as sharing and integrating. However existing legacy systems have to introduce particular EAI solution because it is difficult to adjust standard technology to EAI due to be managed independently without considering interoperability. For solving these problems we use metadata registry using data integration. Various types, semantic specification data heterogeneity and heterogeneity of systems, however, are occurred. Therefore retrieval system based on XMDR(extended Meta-Data Registry) for data interoperability in the web environment are proposed in this paper.

• Proceedings of the Korean Information Science Society Conference
• /
• 2003.10c
• /
• pp.187-189
• /
• 2003

CPXe(The Common Picture eXchange environment) 서비스는 13A(International Imaging Industry Association)에서 제정한 디지털 이미지 교환 환경에 대한 표준으로써, 디지털 이미징 서비스를 이용하는 사용자들이 이미지 데이터를 보다 쉽고 편리하게 다양한 디지털 이미지 관련 웹 서비스(Web Services)를 이용할 수 있도록 지원하고 있다. 현재 CPXe 서비스는 CPXe UDDI 디렉토리 서비스의 정보를 사용자의 요구에 맞도록 필터링하여 HTML 정보로 변환한 후, 사용자가 인식하기 쉬운 방법으로 제공하는 Locator 서비스, 이미지 인화에 관한 Fulfillment 서비스, 웹 서비스와 사용자간 보다 편리한 인터페이스를 제공하는 WBIS(Web Browser Interaction Service) 등에 대한 API 스펙을 제공하고 있다. 본 논문에서는 사용자가 BPEL4WS(Business Process Execution Language for Web Services) 언어 를 사용하여, CPXe 표준을 따르는 온톨로지(Ontology)간 다양한 웹 서비스를 컴포넌트 형태로 구성(Composition)하고 궁극적으로 자신이 원하는 하나의 독특한 서비스를 구현할 수 있는 웹 서비스간 반자동(Semi­automatic) 구성 서비스 원형 (Prototype) 모델을 소개 할 것이다.

• Proceedings of the Korea Contents Association Conference
• /
• 2004.11a
• /
• pp.265-268
• /
• 2004

Keyword matching technique which is used in most information retrieval systems is unfit for efficient processing of geometrically increasing information. The problem can be solved by using semantic information and an efficient method of semantic processing is introduced in this paper. The technique uses conceptual graph to represent the semantic information and apply it for information retrieval. The implemented system can perform exact matching and partial matching. Partial matching has two different types. One is syntactic partial matching and the other is semantic partial matching. The semantic semilaries are measured by the subclass relations in the ontology. The introduced technique can be used not only information retrieval but also in various applications such as an implementation of dynamic hyperlinks.

• Proceedings of the Korean Information Science Society Conference
• /
• 2007.10c
• /
• pp.17-22
• /
• 2007

이 논문에서는 관계형 데이터베이스 모델 기반의 OWL 웹 온톨로지 모델을 보이고 이에 대한 실험 및 비교 평가 결과에 대하여 기술한다. OWL은 W3C에 의해 2004년 12월에 권고안으로 채택된 이후에 많은 연구가 진행되고 있다. 편집 도구 개발, 저장소 개발로 OWL 기반의 추론 엔진까지 이와 관련된 다양한 연구가 진행 중이다. 특히 OWL 온톨로지의 영구적인 저장 및 관리를 위해 관계형 데이터베이스 모델을 이용한 많은 연구 결과들이 발표되고 있다. 이 논문에서는 널리 알려진 관계형 모델 기반의 저장소 보다 나은 성능을 제공하기 위해 제안한 모델에 대한 평가 결과에 대하여 기술한다. 기존 유사 연구의 경우, 비교 평가를 위한 평가 항목으로 온톨로지 로드 시간을 고려하기도 하지만 이 논문에서는 질의응답 시간에만 초점을 둔다. 이는 매우 특수한 상황을 제외한 대부분의 상황에서 질의 처리 시간이 가장 중요한 요소이며 실질적인 활용성 측면에서 핵심적으로 다루어야 하는 평가 항목이기 때문이다. 실험을 위한 데이터로서는 많은 연구에서 활용하고 있는 LUBM 데이터 셋을 이용하며 실험 대상으로는 오픈 소스이며 널리 알려진 시스템인 Jena의 저장소와 Sesame를 이용한다. 실험 및 비교 평가 결과, 제안 시스템이 비교 대상 시스템들에 비해 나은 성능을 보임을 알 수 있다.

• Journal of the Korea Society of Computer and Information
• /
• v.18 no.5
• /
• pp.133-145
• /
• 2013

The objective of this study is to contribute effective operation of traffic information center by traffic information data measure process which are now being serviced by frame work of traffic information and by providing traffic information assessment criteria which reliable traffic information throughout traffic information quality characteristics in intelligent transport system. For the objectives, we analyzed the information attribute of ontology technique for quality management of traffic information in system engineering database research area. Throughout the result of this study, SE database utilized the development of subsystems, the component and interface design for convenient and rapid information services, and diverse related reliable systems design and expected to be indicated in systematic database.

• Journal of Information Processing Systems
• /
• v.16 no.1
• /
• pp.171-183
• /
• 2020

Capsule endoscopy is one of the increasingly demanded diagnostic methods among patients in recent years because of its ability to observe small intestine difficulties. It is often conducted for 12 to 14 hours, but significant frames constitute only 10% of whole frames. Thus, it has been designed to automatically acquire significant frames through deep learning. For example, studies to track the position of the capsule (stomach, small intestine, etc.) or to extract lesion-related information (polyps, etc.) have been conducted. However, although grouping or labeling the training images according to similar features can improve the performance of a learning model, various attributes (such as degree of wrinkles, presence of valves, etc.) are not considered in conventional approaches. Therefore, we propose a class-labeling method that can be used to design a learning model by constructing a knowledge model focused on main lesions defined in standard terminologies for capsule endoscopy (minimal standard terminology, capsule endoscopy structured terminology). This method enables the designing of a systematic learning model by labeling detailed classes through differentiation of similar characteristics.

• Korea Information Processing Society Review
• /
• v.11 no.6
• /
• pp.56-75
• /
• 2004

In this article we address some system characteristics and challenging issues in developing Context-aware Middleware for Ubiquitous Computing. The functionalities of a Context-aware Middleware includes gathering context data from hardware/software sensors, reasoning and inferring high-level context data, and disseminating/delivering appropriate context data to interested applications/services. The Middleware should facilitate the query, aggregation, and discovery for the contexts, as well as facilities to specify their privacy policy. Following a formal context model using ontology would enable syntactic and semantic interoperability, and knowledge sharing between different domains. Moddleware should also provide different kinds of context classification mechanical as pluggable modules, including rules written in different types of logic (first order logic, description logic, temporal/spatial logic, fuzzy logic, etc.) as well as machine-learning mechanical (supervised and unsupervised classifiers). Different mechanisms have different power, expressiveness and decidability properties, and system developers can choose the appropriate mechanism that best meets the reasoning requirements of each context. And finally, to promote the context-trigger actions in application level, it is important to provide a uniform and platform-independent interface for applications to express their need for different context data without knowing how that data is acquired. The action could involve adapting to the new environment, notifying the user, communicating with another device to exchange information, or performing any other task.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2005.10a
• /
• pp.440-443
• /
• 2005

The wide spread of internet business recently necessitates recommendation systems which can recommend the most suitable product fur customer demands. Currently the recommendation systems use content-based filtering and/or collaborative filtering methods, which are unable both to explain the reason for the recommendation and to reflect constantly changing requirements of the users. These methods guarantee good efficiency only if there is a lot of information about users. This paper proposes an algorithm called 'demand articulate & integration' which can perceive user's continuously varying intents and recommend proper contents. A method of knowledge classification which can be applicable to this algorithm is also developed in order to disassemble knowledge into basic units and articulate indices. The algorithm provides recommendation outputs that are close to expert's opinion through the tracing of articulate index. As a case study, a knowledge base for heritage information is constructed with the expert guide's knowledge. An intelligent recommendation system that can guide heritage tour as good as the expert guider is developed.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2013.11a
• /
• pp.1165-1168
• /
• 2013

웹의 비약적인 발전으로 정보가 폭발적으로 증가하였고, 이로 인하여 정보검색 기술에서 해당 정보를 빠르게 찾는 것에 목표를 두었던 기술이 원하는 정보를 정확하게 찾는 기술로 발전을 이루게 된다. 시맨틱 웹 기술은 이와 같은 요구에 부응하기 위하여 등장했으며 의미 기반의 검색 및 추론과 같은 지식 발견 등의 기술을 가능하게 한다. 일반적인 정보가 아닌 법률과 같은 전문지식 영역의 정보는 현재 일반 사용자들이 쉽게 접근하여 법률 정보를 확인할 수 있는 환경이 되지 못한다. 따라서 시맨틱 웹 기술을 이용한 온톨로지 기반의 법률 검색 서비스가 필요하며 이를 위한 기반 시스템을 구축하는 것이 중요하다. 따라서 본 논문에서는 온톨로지 기반의 법률 검색 서비스를 위해 법률이 가지는 구조적 특징을 분석하고, RDF 기반의 온토롤지 구축 방법 및 RDF 언어 레벨에서 하지 못했던 명시적인 트리플 외에 추론된 트리플을 찾아 낼 수 있는 질의 방법의 고안 및 추론 방법을 제안한다. 이를 통해 법률 용어를 정확하게 모르는 일반 사용자들이 법과 관련된 검색을 수행할 시 효과적으로 법명 및 조문 내용을 확인할 수 있으며 RDF 언어 레벨의 추론 기능의 제안으로 RDF 레벨로 구축된 다양한 분야의 시스템에서 다른 추가적인 레이어 없이 추론을 위한 기반 기술을 갖출 수 있다.