• The KIPS Transactions:PartB
• /
• v.16B no.3
• /
• pp.225-232
• /
• 2009

Author name disambiguation is essential for improving performance of document indexing, retrieval, and web search. Author name disambiguation resolves the conflict when multiple authors share the same name label. This paper introduces a novel approach which exploits ontologies and WordNet-based category utility for author name disambiguation. Our method utilizes author knowledge in the form of populated ontology that uses various types of properties: titles, abstracts and co-authors of papers and authors' affiliation. Author ontology has been constructed in the artificial intelligence and semantic web areas semi-automatically using OWL API and heuristics. Author name disambiguation determines the correct author from various candidate authors in the populated author ontology. Candidate authors are evaluated using proposed WordNet-based category utility to resolve disambiguation. Category utility is a tradeoff between intra-class similarity and inter-class dissimilarity of author instances, where author instances are described in terms of attribute-value pairs. WordNet-based category utility has been proposed to exploit concept information in WordNet for semantic analysis for disambiguation. Experiments using the WordNet-based category utility increase the number of disambiguation by about 10% compared with that of category utility, and increase the overall amount of accuracy by around 98%.

• Journal of the Korean Society for information Management
• /
• v.29 no.4
• /
• pp.273-294
• /
• 2012

Images have been substantially searched and used due to not only the advanced internet and digital technologies but the characteristics of a younger generation. The purpose of this study aims to discuss the ways on expanding the access points to images by analyzing the needs of users in context of everyday life. In order to achieve the purpose of this study, 105 questions of image seeking in NAVER, which is one of social Q&A services in Korea, were analyzed. For the analysis, a two-dimensional framework with image uses and image attributes were utilized. The findings of this study demonstrate that considerable use purposes on data oriented pole, such as information processing, information dissemination and learning are identified. On the other hand, image attributes from the needs of image show that non-visual aspects including contextual attributes are recognized substantially in addition to the traditional semantic attributes.

• Journal of Broadcast Engineering
• /
• v.7 no.2
• /
• pp.96-106
• /
• 2002

We introduce a novel scheme to characterize and index events in TV golf programs using MPEG-7 descriptors. Our goal is to identify and localize the golf events of interest to facilitate highlight-based video indexing and summarization. In particular, we analyze multiple (low-level) visual features using domain-specific model to create a perceptual relation for semantically meaningful(high-level) event identification. Furthermore, we summarize a TV golf program with TV-Anytime segmentation metadata, a standard form of an XML-based metadata description, in which the golf events are represented by temporally localized segments and segment groups of highlights. Experimental results show that our proposed technique provides reasonable performance for identifying a variety of golf events.

• Journal of Korea Multimedia Society
• /
• v.7 no.10
• /
• pp.1452-1463
• /
• 2004

The requirement of automatic video summary is increasing as bi-directional broadcasting contents and various user requests and preferences for the bi -directional broadcast environment are increasing. Automatic video summary is needed for an efficient management and usage of many contents in service provider as well. In this paper, we propose a method to generate a content-based summary of linguistic educational videos automatically. First, shot-boundaries and keyframes are generated from linguistic educational video and then multiple(low-level) visual features are extracted. Next, the semantic parts (Explanation part, Dialog part, Text-based part) of the linguistic educational video are generated using extracted visual features. Lastly the XMI- document describing summary information is made based on HieraTchical Summary architecture oi MPEG-7 MDS (Multimedia I)escription Scheme). Experimental results show that our proposed algorithm provides reasonable performance for automatic summary of linguistic educational videos. We verified that the proposed method is useful ior video summary system to provide various services as well as management of educational contents.

• The Journal of the Korea Contents Association
• /
• v.16 no.6
• /
• pp.205-214
• /
• 2016

As a large amount of graph-structured data is widely used in various applications such as social networks, semantic web, and bio-informatics, keyword-based search over graph data has been getting a lot of attention. In this paper, we propose an efficient method for keyword search over graph data to find a set of top-k answers that are relevant as well as non-redundant in structure. We define a non-redundant answer structure for a keyword query and a relevance measure for the answer. We suggest a new indexing scheme on the relevant paths between nodes and keyword terms in the graph, and also propose a query processing algorithm to find top-k non-redundant answers efficiently by exploiting the pre-calculated indexes. We present effectiveness and efficiency of the proposed approach compared to the previous method by conducting an experiment using a real dataset.

• Journal of KIISE:Information Networking
• /
• v.30 no.4
• /
• pp.504-512
• /
• 2003

In this paper, we propose a new adaptive dissolve detection method based on the analysis of a dissolve modeling error which is the difference between an ideally modeled dissolve curve with no correlation and an actual dissolve curve including a correlation. The proposed dissolve detection method consists of two steps. First, candidate dissolve regions are extracted using the characteristics of a downward convex parabola, then each candidate region is verified based oil the dissolve modeling error. If the dissolve modeling error for a candidate region is less than a threshold defined by the target modeling error with a target correlation, the candidate region is determined as a resolve region with a lower correlation than the target correlation. The threshold is adaptively determined based on the variances between the candidate regions and the target correlation. By considering the correlation between neighbor scenes, the proposed method is able to be a semantic scene-change detector. The proposed method was tested on various types of data and its performance proved to be more accurate and reliable regardless of variation of variance of test sequences when compared with other commonly use methods.

• Journal of Korea Multimedia Society
• /
• v.12 no.8
• /
• pp.1172-1181
• /
• 2009

An electronic medical record (EMR) is the medical system that all the test are recorded as text data. However, domestic EMR systems have various forms of medical records. There are a lot of related works to standardize the laboratory codes as a LOINC (Logical Observation Identifiers Names and Code). However the existing researches resolve the problem manually. The manual process does not work when the size of data is enormous. The paper proposes a novel automatic LOINC mapping algorithm which uses indexing techniques and semantic similarity analysis of medical information. They use file system which is not proper to enormous medical data. We designed and implemented mapping algorithm for standardization laboratory codes in medical informatics compared with the existing researches that are only proposed algorithms. The automatic creation of searching words is being possible. Moreover, the paper implemented medical searching framework based on database system that is considered large size of medical data.

• The Journal of the Korea Contents Association
• /
• v.15 no.1
• /
• pp.9-23
• /
• 2015

In this paper, we propose a new RDF index scheme considering the characteristics of large scale RDF data to improve the query processing performance. The proposed index scheme creates a S-O index for subjects and objects since the subjects and objects of RDF triples are used redundantly. In order to reduce the total size of the index, it constructs a P index for the relatively small number of predicates in RDF triples separately. If a query contains the predicate, we first searches the P index since its size is relatively smaller compared to the S-O index. Otherwise, we first searches the S-O index. It is shown through performance evaluation that the proposed scheme outperforms the existing scheme in terms of the query processing time.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2013.11a
• /
• pp.1294-1297
• /
• 2013

본 논문은 기계학습을 통하여 특허문서를 국제 특허 분류(IPC) 기준에 따라 자동으로 분류하는 시스템에 관한 연구로 잠재 의미 색인 기법을 이용하여 분류의 성능을 높일 수 있는 방법을 제안하기 위한 연구이다. 종래 특허문서에 관한 IPC 자동 분류에 관한 연구가 단어 매칭 방식의 색인 기법에 의존해서 이루어진바가 있으나, 현대 기술용어의 발생 속도와 다양성 등을 고려할 때 특허문서들 간의 관련성을 분석하는데 있어서는 단어 자체의 빈도 보다는 용어의 개념에 의한 접근이 보다 효과적일 것이라 판단하여 잠재 의미 색인(LSI) 기법에 의한 분류에 관한 연구를 하게 된 것이다. 실험은 단어 매칭 방식의 색인 기법의 대표적인 자질선택 방법인 정보획득량(IG)과 카이제곱 통계량(CHI)을 이용했을 때의 성능과 잠재 의미 색인 방법을 이용했을 때의 성능을 SVM, kNN 및 Naive Bayes 분류기를 사용하여 분석하고, 그중 가장 성능이 우수하게 나오는 SVM을 사용하여 잠재 의미 색인에서 명사가 해당 용어의 개념적 의미 구조를 구축하는데 기여하는 정도가 어느 정도인지 평가함과 아울러, LSI 기법 이용시 최적의 성능을 나타내는 특이값의 범위를 실험을 통해 비교 분석 하였다. 분석결과 LSI 기법이 단어 매칭 기법(IG, CHI)에 비해 우수한 성능을 보였으며, SVM, Naive Bayes 분류기는 단어 매칭 기법에서는 비슷한 수준을 보였으나, LSI 기법에서는 SVM의 성능이 월등이 우수한 것으로 나왔다. 또한, SVM은 LSI 기법에서 약 3%의 성능 향상을 보였지만 Naive Bayes는 오히려 20%의 성능 저하를 보였다. LSI 기법에서 명사가 잠재적 의미 구조에 미치는 영향은 모든 단어들을 내용어로 한 경우 보다 약 10% 더 향상된 결과를 보여주었고, 특이값의 범위에 따른 성능 분석에 있어서는 30% 수준에 Rank 되는 범위에서 가장 높은 성능의 결과가 나왔다.

• Journal of the Korea Society for Simulation
• /
• v.15 no.3
• /
• pp.23-30
• /
• 2006

A recommender system for E-commerce site receives information from customers about which products they are interested in, and recommends products that are likely to fit their needs. In this paper, we investigate several methods for large-scale product purchase data for the purpose of producing useful recommendations to customers. We apply the traditional data mining techniques of cluster analysis and collaborative filtering(CF), and CF with reduction of product-dimensionality by use of latent semantic indexing(LSI). If reduced product-dimensionality obtained from LSI shows a similar latent trend of customers for buying products to that based on original customer-product purchase data, we expect less computational effort for obtaining the nearest-neighbor for target customer may improve the efficiency of recommendation performance. From simulation experiments on synthetic customer-product purchase data, CF-based method with reduction of product-dimensionality presents a better performance than the traditional CF methods with respect to the recall, precision and F1 measure. In general, the recommendation quality increases as the size of the neighborhood increases. However, our simulation results shows that, after a certain point, the improvement gain diminish. Also we find, as a number of products of recommendation increases, the precision becomes worse, but the improvement gain of recall is relatively small after a certain point. We consider these informations may be useful in applying recommender system.