• Journal of Information Science Theory and Practice
• /
• v.2 no.1
• /
• pp.6-21
• /
• 2014

This paper proposes a novel knowledge extraction system, TAKES (Two-step Approach for Knowledge Extraction System), which integrates advanced techniques from Information Retrieval (IR), Information Extraction (IE), and Natural Language Processing (NLP). In particular, TAKES adopts a novel keyphrase extraction-based query expansion technique to collect promising documents. It also uses a Conditional Random Field-based machine learning technique to extract important biological entities and relations. TAKES is applied to biological knowledge extraction, particularly retrieving promising documents that contain Protein-Protein Interaction (PPI) and extracting PPI pairs. TAKES consists of two major components: DocSpotter, which is used to query and retrieve promising documents for extraction, and a Conditional Random Field (CRF)-based entity extraction component known as FCRF. The present paper investigated research problems addressing the issues with a knowledge extraction system and conducted a series of experiments to test our hypotheses. The findings from the experiments are as follows: First, the author verified, using three different test collections to measure the performance of our query expansion technique, that DocSpotter is robust and highly accurate when compared to Okapi BM25 and SLIPPER. Second, the author verified that our relation extraction algorithm, FCRF, is highly accurate in terms of F-Measure compared to four other competitive extraction algorithms: Support Vector Machine, Maximum Entropy, Single POS HMM, and Rapier.

• The Transactions of the Korea Information Processing Society
• /
• v.5 no.8
• /
• pp.2075-2082
• /
• 1998

Rule-based knowledge representHtion is, the most popular technique for ,storage and manipulation of domain knowledge in expert system. By the way, the amount of knowledge increases more and more in this representatiun technique, it, relationship becomes complex, and even its contents can be modified. This is the reason why rule-based knowledge representation technique requires a verification ,system which can maintain consistency and completeness of knowledge base. This paper is to propose a verification system for consistency and completeness of knowledge base to promote the efficiency and reliability of expert system. After verifying the potential errors both in structure and in semantics whenever a new rule is added, this system renders knowledge base consistent and complete by correcting them automatically or by making expert correct them if it fails.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.10a
• /
• pp.267-268
• /
• 2022

Recently, big data analysis can use various techniques according to the development of machine learning. Big data collected in reality lacks an automated refining technique for the same or similar terms based on semantic analysis of the relationship between words. Big data is usually in the form of sentences, and morphological analysis or understanding of the sentences is required. Accordingly, NLP, a technique for analyzing natural language, can understand the relationship of words and sentences. In this paper, we study the advantages and disadvantages of Transformers and Reformers, which are techniques that complement the disadvantages of RNN, which is a time series approach to big data.

• The Journal of Society for e-Business Studies
• /
• v.15 no.3
• /
• pp.131-145
• /
• 2010

Until now, popular paradigms to provide e-catalog documents that are adapted to users' needs are keyword search or collaborative filtering based recommendation. Since users' queries are too short to represent what users want, it is hard to provide the users with e-catalog documents that are adapted to their needs(i.e., queries and preferences). Although various techniques have beenproposed to overcome this problem, they are based on index term matching. A conventional Bayesian belief network-based approach represents the users' needs and e-catalog documents with their corresponding concepts. However, since the concepts are the index terms that are extracted from the e-catalog documents, it is hard to represent relationships between concepts. In our work, we extend the conventional Bayesian belief network based approach to represent users' needs and e-catalog documents with a concept network which is derived from the Web directory. By exploiting the concept network, it is possible to search conceptually relevant e-catalog documents although they do not contain the index terms of queries. Furthermore, by computing the conceptual similarity between users, we can exploit a semantic collaborative filtering technique for recommending e-catalog documents.

• Journal of Internet Computing and Services
• /
• v.24 no.1
• /
• pp.71-86
• /
• 2023

The purpose of this exploratory study is to compare the differences in public perceptual characteristics of Korean and Chinese societies regarding the metaverse using big data analysis. Due to the environmental impact of the COVID-19 pandemic, technological progress, and the expansion of new consumer bases such as generation Z and Alpha, the world's interest in the metaverse is drawing attention, and related academic studies have been also in full swing from 2021. In particular, Korea and China have emerged as major leading countries in the metaverse industry. It is a timely research question to discover the difference in social awareness using big data accumulated in both countries at a time when the amount of mentions on the metaverse has skyrocketed. The analysis technique identifies the importance of key words by analyzing word frequency, N-gram, and TF-IDF of clean data through text mining analysis, and analyzes the density and centrality of semantic networks to determine the strength of connection between words and their semantic relevance. Python 3.9 Anaconda data science platform 3 and Textom 6 versions were used, and UCINET 6.759 analysis and visualization were performed for semantic network analysis and structural CONCOR analysis. As a result, four blocks, each of which are similar word groups, were driven. These blocks represent different perspectives that reflect the types of social perceptions of the metaverse in both countries. Studies on the metaverse are increasing, but studies on comparative research approaches between countries from a cross-cultural aspect have not yet been conducted. At this point, as a preceding study, this study will be able to provide theoretical grounds and meaningful insights to future studies.

• KIEAE Journal
• /
• v.10 no.3
• /
• pp.57-62
• /
• 2010

To effectively use Building Information Modelling (BIM) dealing with semantic information including the entities of building components, the information about building components should be standardized. Like standardized modern buildings. in the past, Korean traditional houses were built according to strict procedures and formats. Therefore, if the Korean traditional house are modelled by using BIM,. not only the Korean traditional house of good quality will be built quickly and cheaply, but also spaces in the existing Korean traditional house will be easily analyzed. However, when analyzing spaces of the Korean traditional house using Space Syntax, some problems are caused in dividing outdoor space such as yard with unclear boundaries, unlike indoor space with clear boundaries surrounded by walls. These comes from the fact that researchers have subjectively divided a space in the house into convex spaces as units for Space Syntax analysis. Therefore, this study aims to develop an objective and rational spatial subdivision technique for Space Syntax analysis of a Korean traditional house modelled by using BIM. We could objectively and reasonably divide a Korean traditional house space into convex spaces by recognizing the building components in the house modelled in the form of Industry Foundation Classes(IFC). Depending on the connection of convex spaces allocated in the spatial subdivision technique, j-graph in Space Syntax could be drawn and the measurements of spatial configurations could be determinded. Through the developed technique, the social properties including the cultural and philosophical aspects of Korean people was identified by measuring the spatial configurations of Korean traditional house. The developed technique will serve as useful means to help architects to find an appropriate purpose of each space for sustainable architecture on the basis of the spatial and social relationships in buildings or urban systems.

• Journal of KIISE:Databases
• /
• v.36 no.6
• /
• pp.434-445
• /
• 2009

Content-based image retrieval(CBIR) is the retrieval technique which uses the contents of images. However, in contrast to text data, multimedia data are ambiguous and there is a big difference between system's low-level representation and human's high-level concept. So it doesn't always mean that near points in the vector space are similar to user. We call this the semantic-gap problem. Due to this problem, performance of image retrieval is not good. To solve this problem, the relevance feedback(RF) which uses user's feedback information is used. But existing RF doesn't consider user's region-of-interest(ROI), and therefore, irrelevant regions are used in computing new query points. Because the system doesn't know user's ROI, RF is proceeded in the image-level. We propose a new ROI RF method which guides a user to select ROI from relevant images for the retrieval of complex satellite image, and this improves the accuracy of the image retrieval by computing more accurate query points in this paper. Also we propose a pruning technique which improves the accuracy of the image retrieval by using images not selected by the user in this paper. Experiments show the efficiency of the proposed ROI RF and the pruning technique.

• The Journal of the Korea Contents Association
• /
• v.14 no.3
• /
• pp.40-51
• /
• 2014

Owing to importance of document copyright the need to detect document duplication and plagiarism is increasing. Many studies have sought to meet such need, but there are difficulties in document duplication detection due to technological limitations with the processing of natural language. This thesis designs and implements a discriminator of similar documents with natural language processing technique. This system discriminates similar documents using morphological analysis, syntactic analysis, and weight on low frequency and idiom. To evaluate the system, we analyze the correlation between human discrimination and term-based discrimination, and between human discrimination and proposed discrimination. This analysis shows that the proposed discrimination needs improving. Future research should work to define the document type and improve the processing technique appropriate for each type.

• Journal of the Korean Society of Costume
• /
• v.54 no.7
• /
• pp.91-106
• /
• 2004

The purpose of this study was to review the previous researches, analyze the clothing image, the make-up image and compare the analyses of clothing image and make-up image. The previous researches of clothing image and make-up image were reviewed in 6 kinds of Journal. The results of previous research review and analysis were followed as : Measuring mean of image are used to similarly that semantic differential technique and summated rating technique. Attention to proposed researcher abstraction image in make-up image, but there is problem that this hard to explain objectivity of image abstraction. There are a lot of occasions that 4 or 5 image factors were extracted by factor analysis. The make-up image researches that presented image stimulus were more than study that do not present. Image words were classified which were compiled words have similar sub image. Grace, activeness, lively. unique, modernity attractive, feminine. sexy and ripeness clothing images were classified factors. which were representative clothing image. Elegance, Sophisticate. romantic, natural, modern and youthfulness make-up image for factor were representative make-up image factors. However the problems were found that some representative image factor included the sub images which were different from some factor image. Compared with representation image words, same image words were used to not agree what clothing image and make-up image. Standardization of word should be made that show that clothing image and make-up image.

• Journal of the Korean association of regional geographers
• /
• v.3 no.2
• /
• pp.105-120
• /
• 1997

One of the most important issues of object-oriented geographical database system is to develop an indexing technique which enables more efficient I/O processing within aggregation hierarchy or inheritance hierarchy. Up to present, several indexing schemes have been developed for this purpose. However, they have separately focused on aggregation hierarchy or inheritance hierarchy of object-oriented data model. A recent research is proposing a nested-inherited index which combines these two hierarchies simultaneously. However, this new index has some weak points. It has high storage costs related to its use of auxiliary index. Also, it cannot clearly represent the inheritance relationship among classes within its index structure. To solve these problems, this thesis proposes a pointer-chain index. Using pointer chain directory, this index composes a hierarchy-typed chain to show the hierarchical relationship among classes within inheritance hierarchy. By doing these, it could fetch the OID list of objects to be retrieved more easily than before. In addition, the pointer chain directory structure could accurately recognize target cases and subclasses and deal with "select-all" typed query without collection of schema semantic information. Also, it could avoid the redundant data storing, which usually happens in the process of using auxiliary index. This study evaluates the performance of pointer chain indexing technique by way of simulation method to compare nested-inherited index. According to this simulation, the pointer chain index is proved to be more efficient with regard to storage cost than nested-inherited index. Especially in terms of retrieval operation, it shows efficient performance to that of nested-inherited index.