• Proceedings of the Korean Information Science Society Conference
• /
• 2001.10b
• /
• pp.22-24
• /
• 2001

정보검색 시스템에서 사용자의 질의어가 불완전함에 따라 생기는 검색 효율의 저하를 줄이기 위하여 용어의 상호관련성을 반영함과 동시에 벡터의 공간을 축소하는 LSI 모델을 사용하여 문서 집합으로부터 잠재적 의미 공간을 구축하였다. 또한 의미 공간상에 있는 문서의 분포에 따라 \"개념\"을 추출하기 하기 위해 k-means algorithm을 사용하여 군집화 시켰다. 이로부터 불완전한 초기 사용자 질의어를 의미 공간에 구축된 클러스터링 정보로 수정하여 새로운 질의어를 생성함으로 검색의 효율을 높이고자 하였다. 검색 효율을 측정하기 위해 TREC 데이터를 이용하여 분석하였으며 결과는 질의어의 성격에 따라 달라졌으나 대체적으로 우수한 성능을 보였다.한 성능을 보였다.

• Proceedings of the Korea Society for Simulation Conference
• /
• 2005.11a
• /
• pp.56-62
• /
• 2005

추천자 시스템은 E-commerce 사이트에서 소비자가 관심을 가지는 상품에 대한 정보를 수집하여 소비자가 구매할 것으로 예상되는 상품을 추천하는 목적으로 개발되었다. 추천자 시스템을 구축하여 성공적으로 활용하기 위해서 해결해야 할 과제로 취급 상품이 대량인 경우에 알고리즘의 효율성 문제라고 볼 수 있는데 본 연구는 문서 검색에서 사용되는 LSI(latent semantic indexing) 분석법을 이용하여 추천자 시스템을 개선하는 방안을 연구하고자 한다. LSI 분석법을 이용하여 고객-상품 구매행렬에서 고객이 상품을 구매하는 경향을 효과적으로 파악할 수 있다면 목표고객에 대한 인접고객군을 생성하는 계산 노력은 현저히 감소되어 추천자 알고리즘이 실시간으로 고객 데이터베이스로부터 많은 인접 고객을 효율적으로 검색할 수 있을 것으로 기대된다. 본 연구는 E-commerce 사이트로부터 얻는 실제적인 고객 자료와 유사한 자료를 시뮬레이션을 통하여 재생하고 이를 바탕으로 LSI에 의한 추천자 시스템의 효율성을 분석하고자 한다.

• The Journal of the Acoustical Society of Korea
• /
• v.28 no.5
• /
• pp.441-446
• /
• 2009

This paper proposes an automatic indexing algorithm of golf video using audio information. In the proposed algorithm, the input audio stream is demultiplexed into the stream of video and audio. By means of Adaboost-cascade classifier, the continuous audio stream is classified into announcer's speech segment recorded in studio, music segment accompanied with players' names on TV screen, reaction segment of audience according to the play, reporter's speech segment with field background, filed noise segment like wind or waves. And golf swing sound including drive shot, iron shot, and putting shot is detected by the method of impulse onset detection and modulation spectrum verification. The detected swing and applause are used effectively to index action or highlight unit. Compared with video based semantic analysis, main advantage of the proposed system is its small computation requirement so that it facilitates to apply the technology to embedded consumer electronic devices for fast browsing.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.41 no.4
• /
• pp.95-102
• /
• 2004

In order to process video data effectively, it is required that the content information of video data is loaded in database and semantic-based retrieval method can be available for various query of users. Currently existent contents-based video retrieval systems search by single method such as annotation-based or feature-based retrieval, and show low search efficiency md requires many efforts of system administrator or annotator because of imperfect automatic processing. In this paper, we propose semantics-based video retrieval system which support semantic retrieval of various users by feature-based retrieval and annotation-based retrieval of massive video data. By user's fundamental query and selection of image for key frame that extracted from query, the agent gives the detail shape for annotation of extracted key frame. Also, key frame selected by user become query image and searches the most similar key frame through feature based retrieval method and optimized comparison area extracting that propose. Therefore, we propose the system that can heighten retrieval efficiency of video data through semantics-based retrieval.

• Journal of Computing Science and Engineering
• /
• v.6 no.3
• /
• pp.207-218
• /
• 2012

In recent years, the skyline query paradigm has been established as a reliable method for database query personalization. While early efficiency problems have been solved by sophisticated algorithms and advanced indexing, new challenges in skyline retrieval effectiveness continuously arise. In particular, the rise of the Semantic Web and linked open data leads to personalization issues where skyline queries cannot be applied easily. We addressed the special challenges presented by linked open data in previous work; and now further extend this work, with a heuristic workflow to boost efficiency. This is necessary; because the new view on linked open data dominance has serious implications for the efficiency of the actual skyline computation, since transitivity of the dominance relationships is no longer granted. Therefore, our contributions in this paper can be summarized as: we present an intuitive skyline query paradigm to deal with linked open data; we provide an effective dominance definition, and establish its theoretical properties; we develop innovative skyline algorithms to deal with the resulting challenges; and we design efficient heuristics for the case of predicate equivalences that may often happen in linked open data. We extensively evaluate our new algorithms with respect to performance, and the enriched skyline semantics.

• Journal of the Korea Computer Industry Society
• /
• v.2 no.11
• /
• pp.1421-1426
• /
• 2001

Nowadays, as the quantity of multimedia information increases rapidly, an efficient management for multimedia has become more important. In this paper, to index and search multimedia contents efficiently, we designed the algorithm searching specific image and saving the extracted image using the semantic information extraction scheme based on contents and it is one of the schemes to indexing and searching of video data. After extracting the RGB information from input image, while all frames of video is inspected sequentially, the specific image is saved through referring to the position and distribution of contents from the collection scheme of RGB range. In case of using the proposed image extraction algorithm, because only saved video is searched instead of the whole the searching time can be reduced.

• Journal of Korea Society of Industrial Information Systems
• /
• v.9 no.1
• /
• pp.36-42
• /
• 2004

In this paper, we compare the vector model performance with the probabilistic model of information system. We use LSI(Latent Semantic Indexing) model for vector model, while Condor information search system that is ready to sell on business is used as a probabilistic model. Each model produces the search results from the original queries and the queries extended by a dictionary definition. We compare those results between two models and find out the vector model is much better than the probabilistic model for the most queries.

• The KIPS Transactions:PartB
• /
• v.12B no.7 s.103
• /
• pp.761-766
• /
• 2005

This paper proposes a video model for the implementation of the cultural video database system. We have utilized an efficient scene change detection method that segments cultural video into semantic units for efficient indexing and retrieval of video. Since video has a large volume and needs to be played for a longer time, it implies difficulty of viewing the entire video. To solve this Problem. the cultural video abstraction was made to save the time and widen the choices of video the video abstract is the summarization of scenes, which includes important events produced by setting up the abstraction rule.

• ETRI Journal
• /
• v.44 no.3
• /
• pp.413-425
• /
• 2022

The study of literary texts is one of the earliest disciplines practiced around the globe. Poetry is artistic writing in which words are carefully chosen and arranged for their meaning, sound, and rhythm. Poetry usually has a broad and profound sense that makes it difficult to be interpreted even by humans. The essence of poetry is Rasa, which signifies mood or emotion. In this paper, we propose a poetry classification-based approach to automatically extract similar poems from a repository. Specifically, we perform a novel Rasa-based classification of Hindi poetry. For the task, we primarily used lexical features in a bag-of-words model trained using the support vector machine classifier. In the model, we employed Hindi WordNet, Latent Semantic Indexing, and Word2Vec-based neural word embedding. To extract the rich feature vectors, we prepared a repository containing 37 717 poems collected from various sources. We evaluated the performance of the system on a manually constructed dataset containing 945 Hindi poems. Experimental results demonstrated that the proposed model attained satisfactory performance.

• The Journal of Society for e-Business Studies
• /
• v.19 no.3
• /
• pp.107-123
• /
• 2014

Current text mining techniques suffer from the problem that the conventional text representation models cannot express the semantic or conceptual information for the textual documents written with natural languages. The conventional text models represent the textual documents as bag of words, which include vector space model, Boolean model, statistical model, and tensor space model. These models express documents only with the term literals for indexing and the frequency-based weights for their corresponding terms; that is, they ignore semantical information, sequential order information, and structural information of terms. Most of the text mining techniques have been developed assuming that the given documents are represented as 'bag-of-words' based text models. However, currently, confronting the big data era, a new paradigm of text representation model is required which can analyse huge amounts of textual documents more precisely. Our text model regards the 'concept' as an independent space equated with the 'term' and 'document' spaces used in the vector space model, and it expresses the relatedness among the three spaces. To develop the concept space, we use Wikipedia data, each of which defines a single concept. Consequently, a document collection is represented as a 3-order tensor with semantic information, and then the proposed model is called text cuboid model in our paper. Through experiments using the popular 20NewsGroup document corpus, we prove the superiority of the proposed text model in terms of document clustering and concept clustering.