• 한국멀티미디어학회논문지
• /
• 제9권1호
• /
• pp.127-137
• /
• 2006

비디오 데이터를 효율적으로 처리하기 위해서는 비디오 데이터가 가지고 있는 내용에 대한 정보를 데이터 베이스에 저장하고 사용자들의 다양한 질의를 처리할 수 있는 의미기반 검색 기법이 요구된다. 기존의 내용기반 비디오 검색 시스템들은 주석기반 검색 또는 특징기반 검색과 같은 단일 방식으로만 검색을 하므로 검색 효율이 낮을 뿐 아니라 완전한 자동 처리가 되지 않아 시스템 관리자나 주석자의 많은 노력을 요구한다. 본 논문에서는 주석기반 검색과 특징기반 검색을 이용하여 대용량의 비디오 데이터에 대한 사용자의 다양한 의미검색을 지원하는 에이전트 기반에서의 자동화되고 통합된 비디오 의미기반 검색 시스템을 제안한다. 사용자의 기본적인 질의와 질의에 의해 추출된 키 프레임의 이미지를 선택함으로써 자동 인덱싱 에이전트는 추출된 키 프레임의 주석에 대한 의미를 더욱 구체화시킨다. 또한, 사용자에 의해 선택된 키 프레임은 질의 이미지가 되어 제안하는 특징기반 검색기법을 통해 가장 유사한 키 프레임을 검색한다. 따라서 의미기반 검색을 통해 비디오 데이터의 검색의 효율을 높일 수 있도록 시스템을 제안한다.

• 정보처리학회논문지C
• /
• 제13C권1호
• /
• pp.129-136
• /
• 2006

정보 검색 시스템은 사용자가 찾고자 하는 지식 정보를 보다 정확하고 빠르게 전달하는 데 그 목적이 있다. 그러나 현재의 검색 시스템은 단순 구문 분석 방식으로 사용자가 원하는 정확한 정보를 제공하지 못한다. 따라서 본 논문에서는 온톨로지 서버를 이용한 SW-IRS(Semantic Web based Information Retrieval System)를 제안한다. 제안한 시스템은 에이전트 기반의 자동 분류 기술과 시맨틱 점 기반의 정보 검색 기법들을 이용하여 반구조(semi-structured) 문서뿐만 아니라 비구조(unstructured) 문서의 처리를 극대화시키고자 한다. 또한 상호 운용성 및 데이터 통합을 위해 RDF(Resource Description Framework) 방식의 문서 저장 서버를 지원하며 웹 페이지들간에 검색 순위를 두어 보다 신속하고 정확한 정보 검색이 가능하도록 하고자 한다. 마지막으로 새로운 순위 측정 알고리즘을 제안하고 이를 이용한 성능 평가를 실시하여 그 효율성과 정확성을 검증해 보이고자 한다.

• 디지털산업정보학회논문지
• /
• 제14권4호
• /
• pp.35-45
• /
• 2018

Users are sharing many of contents such as text, image, video, and so on in SNS. There are various information as like as personal interesting, opinion, and relationship in social media contents. Therefore, many of recommendation systems or search systems are being developed through analysis of social media contents. In order to extract subject-related topics of social context being collected from social media channels in developing those system, it is necessary to develop ontologies for semantic analysis. However, it is difficult to develop formal ontology because social media contents have the characteristics of non-formal data. Therefore, we develop a social topic system based on semantic and subject correlation. First of all, an extracting system of social topic based on semantic relationship analyzes semantic correlation and then extracts topics expressing semantic information of corresponding social context. Because the possibility of developing formal ontology expressing fully semantic information of various areas is limited, we develop a self-extensible architecture of ontology for semantic correlation. And then, a classifier of social contents and feed back classifies equivalent subject's social contents and feedbacks for extracting social topics according semantic correlation. The result of analyzing social contents and feedbacks extracts subject keyword, and index by measuring the degree of association based on social topic's semantic correlation. Deep Learning is applied into the process of indexing for improving accuracy and performance of mapping analysis of subject's extracting and semantic correlation. We expect that proposed system provides customized contents for users as well as optimized searching results because of analyzing semantic and subject correlation.

• 선박안전
• /
• 통권33호
• /
• pp.63-73
• /
• 2012

The Ministry of Land, Transport and Maritime Affairs(MLTM) constructed the IMO Korea homepage to owned jointly IMO information when establishing a international standard in about marine transport and the shipbuilding, in order to speak for the profit of Korea in IMO and it was double renewal since 2004. But the newly re-opened the IMO Korea homepage is also operated to the level which simply keeps IMO documents because of limited H/W sizes. This study investigated and analyzed the domestic and similar foreign homepages to provide effectively about the IMO informations At the result, these homepages were serviced to the meeting resultants using the various contents such as Semantic search, Thesaurus search, establishment of web accessible etc. Therefore, the existing IMO Korea homepage must be re-constructed as IMO Information Portal Site to provide better information.

• Spatial Information Research
• /
• 제21권1호
• /
• pp.1-13
• /
• 2013

This paper describes a GIS framework for geo-semantic information retrieval in mobile computing environments. We built geographic ontologies of POI (point of interest) and weather information for use in the combination of semantic, spatial, and temporal functions in a fully integrated database. We also implemented a geo-semantic app for Android-based smartphones that can extract more appropriate POIs in terms of user contexts and geographic ontologies and can visualize the POIs using Google Maps API (application programming interface). The feasibility tests showed our geo-semantic app can provide pertinent POI information according to mobile user contexts such as location, time, schedule, and weather. We can discover a baking CVS (convenience store) in the test of bakery search and can find out a drive-in theater for a not rainy day, which are good examples of the geo-semantic query using semantic, spatial, and temporal functions. As future work, we should need ontology-based inference systems and the LOD (linked open data) of various ontologies for more advanced sharing of geographic knowledge.

• 한국한의학연구원논문집
• /
• 제16권2호
• /
• pp.91-99
• /
• 2010

In this paper, we designed and implemented a semantic social network system in Korea Institute of Oriental Medicine (abbreviated as KIOM). Our social network system provides the capabilities such as tracking search, ontology reasoning, ontology graph view, and personal information input, update and management. Tracking search provides the search results by the research information of relevant researchers using ontology, in addition to those by keywords. Ontology reasoning provides the reasoning for experts, mentors, and personal contacts. Users can easily browse the personal connections among researchers by traversing the ontology by graph viewer. These allows KIOM researchers to search other researchers who could aid the researches and to easily share their research information.

• 한국기록관리학회지
• /
• 제17권1호
• /
• pp.217-244
• /
• 2017

정보기술의 발달로 이용자들은 아키비스트의 개입 없이 자유롭게 기록을 검색할 수 있게 되었지만, 기존의 기록물 검색 시스템은 이용자의 의도를 파악하지 못하는 단편적인 결과를 제공하고 있다. 이런 문제를 극복하기 위해 시맨틱 웹 기술이 발전하고 있으며, ICA에서는 이를 반영하여 새로운 기록물 기술 표준인 RIC(Record In Context)을 개발하고 있다. RIC의 개념모델과 온톨로지는 시맨틱 검색을 구현하는 기반이 되기 때문에, 이것이 실제로 어떻게 이용자들에게 서비스될 수 있을지 고민해볼 필요가 있다. 따라서 본 연구에서는 온톨로지를 기반으로 하는 기록물 검색 시스템이 어떤 인터페이스를 통해 구현될 수 있을지 제안해보았다. 시맨틱웹 기술을 기반으로 한 검색 시스템의 사례 3가지를 선정해 이용자들의 인터뷰를 통한 사용경험 평가를 진행하였고, 여기에서 얻은 시사점을 기반으로 하여 기록물 검색 시스템의 인터페이스를 4가지 측면으로 구성하여 제안하였다.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2006년도 제37회 하계학술대회 논문집 D
• /
• pp.1951-1952
• /
• 2006

To effectively deal with video data, a semantic-based retrieval scheme that allows for processing diverse user queries and saving them on the database is required. In this regard, this paper proposes a semantic-based video retrieval system that allows the user to search diverse meanings of video data for electrical safetyrelated educational purposes by means of automatic annotation processing. If the user inputs a keyword to search video data for electrical safety-related educational purposes, the mobile agent of the proposed system extracts the features of the video data that are afterwards learned in a continuous manner, and detailed information on electrical safety education is saved on the database. The proposed system is designed to enhance video data retrieval efficiency for electrical safety-related educational purposes.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2005년도 제36회 하계학술대회 논문집 D
• /
• pp.2830-2832
• /
• 2005

Recently, retrieval or various video data has become an important issue as more and more multimedia content services are being provided. To effectively deal with video data, a semantic-based retrieval scheme that allows for processing diverse user queries and saving them on the database is required. In this regard, this paper proposes a semantic-based video retrieval system that allows the user to search diverse meanings of video data for electrical safetyrelated educational purposes by means of automatic annotation processing. If the user inputs a keyword to search video data for electrical safety-related educational purposes, the mobile agent of the proposed system extracts the features of the video data that are afterwards learned in a continuous manner, and detailed information on electrical safety education is saved on the database. The proposed system is designed to enhance video data retrieval efficiency for electrical safety-related educational purposes.

• 한국산학기술학회:학술대회논문집
• /
• 한국산학기술학회 2006년도 춘계학술발표논문집
• /
• pp.320-323
• /
• 2006

Recently, retrieval of various video data has become an important issue as more and more multimedia content services are being provided. To effectively deal with video data, a semantic-based retrieval scheme that allows for processing diverse user queries and saving them on the database is required. In this regard, this paper proposes a semantic-based video retrieval system that allows the user to search diverse meanings of video data for electrical safetyrelated educational purposes by means of automatic annotation processing. If the user inputs a keyword to search video data for electrical safety-related educational purposes, the mobile agent of the proposed system extracts the features of the video data that are afterwards learned in a continuous manner, and detailed information on electrical safety education is saved on the database. The proposed system is designed to enhance video data retrieval efficiency for electrical safety-related educational purposes.