• Journal of KIISE:Software and Applications
• /
• v.35 no.9
• /
• pp.562-571
• /
• 2008

For the purpose of building domain ontology, this paper proposes a methodology for building core ontology first, and then enriching the core ontology with the concepts and relations in the domain thesaurus. First, the top-level concept taxonomy of the core ontology is built using domain dictionary and general domain thesaurus. Then, the concepts of the domain thesaurus are classified into top-level concepts in the core ontology, and relations between broader terms (BT) - narrower terms (NT) and related terms (RT) are classified into semantic relations defined for the core ontology. To classify concepts, a two-step approach is adopted, in which a frequency-based approach is complemented with a similarity-based approach. To classify relations, two techniques are applied: (i) for the case of insufficient training data, a rule-based module is for identifying isa relation out of non-isa ones; a pattern-based approach is for classifying non-taxonomic semantic relations from non-isa. (ii) For the case of sufficient training data, a maximum-entropy model is adopted in the feature-based classification, where k-NN approach is for noisy filtering of training data. A series of experiments show that performances of the proposed systems are quite promising and comparable to judgments by human experts.

• Journal of KIISE
• /
• v.44 no.7
• /
• pp.742-747
• /
• 2017

In this paper, we propose a novel approach to improve the performance of the Convolutional Neural Network(CNN) word embedding model on top of word2vec with the result of performing like doc2vec in conducting a document classification task. The Word Piece Model(WPM) is empirically proven to outperform other tokenization methods such as the phrase unit, a part-of-speech tagger with substantial experimental evidence (classification rate: 79.5%). Further, we conducted an experiment to classify ten categories of news articles written in Korean by feeding words and document vectors generated by an application of WPM to the baseline and the proposed model. From the results of the experiment, we report the model we proposed showed a higher classification rate (89.88%) than its counterpart model (86.89%), achieving a 22.80% improvement. Throughout this research, it is demonstrated that applying doc2vec in the document classification task yields more effective results because doc2vec generates similar document vector representation for documents belonging to the same category.

• The Journal of Korean Medicine
• /
• v.41 no.3
• /
• pp.125-137
• /
• 2020

Objectives: This study was aimed to present the experts' opinions for the successful application of Korean traditional medical practices (KTMPs) to the International Classification of Health Intervention (ICHI). Methods: Two doctors of Korean Medicine and two health information managers who had tried coding 131 KTMPs using ICHI participated in the focus group discussion. The remarks from the discussion were summarized according to the thematic analysis method. Results: The participants expected ICHI to be mainly used for statistics when applied to TKMPs. It can be used for payment systems as well, but it was expected that additional work would be required. They thought the current version of the ICHI did not sufficiently reflect the KMTPs of the real world, and even the interventions already included in the ICHI were not explained enough in the system. They thought it would not be easy to explain more KTMPs within the current structure of the ICHI, but they also said it seemed possible. In the process, rather than adding entirely new stem codes, it would be better to generate new combinations of the existing codes, to suppose subdivided codes, and to utilize the include terms or extension codes. Conclusions: For the successful introduction of ICHI, clarifying the definition of each intervention of KTMPs is a top priority. In addition, it is necessary to continue the matching work of ICHI - KMPTs and also required to make this effort together with the field of traditional medicine and complementary medicine worldwide.

• Journal of IKEEE
• /
• v.24 no.3
• /
• pp.783-790
• /
• 2020

In this paper, the human detecting radar system for indoor security applications is proposed, and its FPGA-based implementation results are presented. In order to minimize the complexity and memory requirements of the computation, the top half of the spectrogram was used to extract features, excluding the feature extraction techniques that require complex computation, feature extraction techniques were proposed considering classification performance and complexity. In addition, memory requirements were minimized by designing a pipeline structure without storing the entire spectrogram. Experiments on human, dog and robot cleaners were conducted for classification, and 96.2% accuracy performance was confirmed. The proposed system was implemented using Verilog-HDL, and we confirmed that a low-area design using 1140 logics and 6.5 Kb of memory was possible.

• Proceedings of the Korean Geotechical Society Conference
• /
• 2008.10a
• /
• pp.974-979
• /
• 2008

The purpose of this study was to evaluate the effect of vegetation on the cutting slope applied by vegetation system in the whole land. The engineering characteristics of slopes were investigated using the face mapping and physical tests. From the statistical methods, a relationship between a geologic stratum and degree of covering was independent. Therefore, the afforestation of slope was affected more by condition of vegetation as direction and opening of joints, and a topsoil state than by conventional classification of layer. It was concluded that the adjustable vegetation on the slope considering condition of geometric shape of slope, joint data and spontaneous type could make useful early afforestation.

• Journal of the Korea Society of Computer and Information
• /
• v.24 no.1
• /
• pp.93-100
• /
• 2019

One of critical issues in dealing with 360-degree realistic contents is the performance degradation in searching and recognition process since they support up to 4K UHD quality and have all image angles including the front, back, left, right, top, and bottom parts of a screen. To solve this problem, in this paper, we propose an efficient search and comparison method for 360-degree realistic contents. The proposed method first corrects the distortion at the less distorted regions such as front, left and right parts of the image excluding severely distorted regions such as upper and lower parts, and then it extracts feature points at the corrected region and selects the representative images through sequence classification. When the query image is inputted, the search results are provided through feature points comparison. The experimental results of the proposed method shows that it can solve the problem of performance deterioration when 360-degree realistic contents are recognized comparing with traditional 2D contents.

• Smart Media Journal
• /
• v.2 no.2
• /
• pp.20-27
• /
• 2013

The concept of social media is top of the agenda for many business executives and decision makers, as well as consultants try to identify ways where companies can make profitable use of applications such as Netflix, Flixster. The social media is playing an increasingly important role as the information sources for customers making product choices etc. With the flourish of Web 2.0 technology, customer reviews are becoming more and more useful and important information resources for people to save their time and energy on purchasing products that they want. This paper proposes the Bayesian Probabilistic Classification algorithm to mine the social media review, and evaluates it by different splits and cross validation mechanism from the real data set. The explored study experimental results show the robustness and effectiveness of proposed approach for mining the social media review.

• Food Science and Biotechnology
• /
• v.16 no.5
• /
• pp.675-690
• /
• 2007

Bacteriocins in Gram-positive bacteria have attracted much attention because many have a strong antimicrobial activity also against bacteria outside the genera of the producers. Lantibiotics and the pediocin-like bactericins have attracted most attention since they kill a broad spectrum of Gram-positive bacteria including important pathogens. But many other promising Gram-positive bacteriocins have been thoroughly characterized. Recent studies have shown that bacteriocins may playa role in the intestinal flora to protect us against the food-borne pathogens. Bacterial genome sequencing has demonstrated that there may be an arsenal of such compounds and we are only seeing the top of the iceberg. The present review gives a short outlook of the field of bacteriocins with focus on lactic acid bacteria and includes recent findings.

• Proceedings of the Korean Information Science Society Conference
• /
• 2012.06b
• /
• pp.226-228
• /
• 2012

최근 HTML5, AJAX(Asynchronous JavaScript XML) 등으로 구현된 웹 애플리케이션이 널리 이용됨에 따라 웹 애플리케이션에 존재하는 취약점을 악용하는 공격 사례가 증가하고 있다. 웹 애플리케이션의 안전한 개발과 유지보수를 위해, 설계/구현 단계에서의 취약점 완화를 통한 예방, 그리고 운영 단계에서의 공격 탐지 및 대응이 필요하다. 더불어, 위험한 취약점들 및 공격 패턴들을 분석하고 우선순위를 부여하여, 웹 애플리케이션 개발 단계 및 운영 단계에서 심각한 취약점과 공격들을 우선 고려해야 한다. 본 논문에서는 OWASP Top 10과 CWE(Common Weakness Enumeration)를 연동시켜 CAPEC(Common Attack Pattern Enumeration and Classification)에서 웹 관련 주요 공격 패턴을 선별하고 순위화하였다. CWE는 취약점 예방에 도움을 주며, 순위화된 공격 패턴은 웹 애플리케이션에서 주요 공격들을 효율적으로 방어할 수 있게 하여 준다.

• Korean Journal of Environment and Ecology
• /
• v.29 no.2
• /
• pp.221-227
• /
• 2015

This study was carried out to measure seasonal changes in the community structure and species composition of marobenthos in the intertidal area of Dokdo. The macrobenthos identified during this study was comprised of 36 species: predominately 25 species of mollusks(69.4 %), 6 species of arthropods(16.7 %), 3 species of echinodermata(8.3 %) and 1 species of cnidaria (5.6 %). The number of marobenthos species ranged from 27 in Spring to 33 in Autumn. In terms of the top 10 dominant species, there were 7 species of mollusks and 3 species of arthropods in the this study. After analyzing the bray-curtis similarity, it was divided into two large groups(A, B). Such group classification matched the SIMPROF(Similarity Profile Analysis) and the one-way ANOSIM(Analysis of similarities) analysis.