• Annual Conference of KIPS
• /
• 2002.04b
• /
• pp.1049-1052
• /
• 2002

기존의 키워드 추출 방법은 출현회수(frequency)에 기반한 가중치(weight) 부여 방식이 많이 쓰였다. 본 논문에서는 HTML 문서와 같이 스타일이 적용된 문서의 경우 출현회수와 함께 단어에 적용된 스타일을 고려하여 가중치를 부여해 키워드를 추출하는 방법을 제안한다. 가중치를 부여할 스타일 항목과 항목별 가중치 부여방법을 정의하고 이를 단어별로 합산하고 정규화(normalization)하는 방법을 정의하여 스타일에 기반 해 키워드를 추출하였다. 내용이 특정된 도메인으로부터 순위(ranking)가 매겨진 도메인 키워드 리스트를 뽑아서 이를 기준으로 삼아 기존의 출현회수 기반의 키워드 추출 방식과 양적, 질적인 비교를 수행하여 우월함을 보였다.

• Journal of Korean Library and Information Science Society
• /
• v.22
• /
• pp.373-401
• /
• 1995

This study aims to improve subject retrieval by constructing the hypertext-based thesaurus to provide a browsing interface to a thesaurus. The experimental system used IBM 486 DXII as a hardware, C++ language as a programming language and Hangul Window 3.1 version as a user interface. The results of this study are summarized as follows : (1) The experimental hypertext-based thesaurus can be used as an efficient search aid for query formulation for the retrieval of bibliographic information. (2) The initial access to the hypertext-based thesaurus is via a keyword index. This index is consist of all the words used to form thesaurus terms, whether descriptors or nondescriptors. (3) Hypertext-based thesaurus allow bookmark button and history button to alleviating the problem of disorientation. (4) This system allow an end-user to view a rich variety of inter-term relationships and a complete conceptus of associations through the information space in a nonsequential manner.

• 제어로봇시스템학회:학술대회논문집
• /
• 2005.06a
• /
• pp.476-479
• /
• 2005

The information available on the Internet has become widely used, primarily due to the ability of Web based E-Commerce and M-Commerce Retrieval Engines to find useful information for users. However, present day Commerce Retrieval Engines are far from perfect because they return results based on simple user keyword matches without any regard for the concepts in which the user is interested. In this thesis, we design and evaluate a Recommender system for web context aware based information retrieval using user profiles. Also, we designed personalization framework in ubiquitous environment based both e-commerce and m-commerce and presented the interaction of user profile including User XQuery pattern in semantic web.

• International Journal of Contents
• /
• v.2 no.1
• /
• pp.17-21
• /
• 2006

In this paper, we describe a concept-based question-answering system in which concept rather than keyword itself makes an important role on both question analysis and answer extraction. Our idea is that concepts occurred in same type of questions are similar, and if a question is analyzed according to those concepts then we can extract more accurate answer because we know the semantic role of each word or phrase in question. Concept frame is defined for each type of question, and it is composed of important concepts in that question type. Currently the number of question type is 79 including 34 types for person, 14 types for location, and so on. We experiment this concept-based approach about questions which require person s name as their answer. Experimental results show that our system has high accuracy in answer extraction. Also, this concept-based approach can be used in combination with conventional approaches.

• Journal of the Korean Society for Precision Engineering
• /
• v.23 no.5 s.182
• /
• pp.30-36
• /
• 2006

The participants in collaborative environment want to get the right information or documents which are intended to find. In general search systems, documents which contain only the keywords are retrieved. For searching different word-expressions for the same meaning, we perform mapping before searching. Our mapping-based search approach has two parts, ontology-based mapping logic and ontology libraries. The ontology-based mapping consists of three steps such as character matching (CM), definition comparing (DC) and similarity checking (SC). First, the character matching is the mapping of two terminologies that have identical character strings. Second, the definition comparing is the method that compares two terminologies' ontological definitions. Third, the similarity checking pairs two terminologies which were not mapped by two prior steps through evaluating the similarity of the ontological definitions. For the ontology libraries, document ontology library (DOL), keyword ontology library (KOL), and mapping result library (MRL) are defined. With these three libraries and three mapping steps, an ontology-based search engine (OntSE) is built, and a use case scenario is discussed to show the applicability.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.16 no.6
• /
• pp.766-771
• /
• 2006

In this paper, we focus on the building domain ontology from corpus by extracting concepts and properties relationships based on linguistic patterns. The pharmacy field is selected as an experiment domain and we present an algorithm to extract hierarchical structure for terminology based on the noun/suffix patterns of terminology in domain texts. In order to show usefulness of our domain ontology, we compare a typical keyword based retrieval method with an ontology based retrieval mettled which uses related information in an ontology for a related feedback. As a result, our method shows the improvement of precision by 4.97% without losing recall.

• Journal of information and communication convergence engineering
• /
• v.22 no.1
• /
• pp.56-63
• /
• 2024

Despite the rapid strides in content-based image retrieval, a notable disparity persists between the visual features of images and the semantic features discerned by humans. Hence, image retrieval based on the association of semantic similarities recognized by humans with visual similarities is a difficult task for most image-retrieval systems. Our study endeavors to bridge this gap by refining image semantics, aligning them more closely with human perception. Deep learning techniques are used to semantically classify images and retrieve those that are semantically similar to personalized images. Moreover, we introduce a keyword-based image retrieval, enabling automatic labeling of images in mobile environments. The proposed approach can improve the performance of a mobile device with limited resources and bandwidth by performing retrieval based on the visual features and keywords of the image on the mobile device.

• The Journal of Pediatrics of Korean Medicine
• /
• v.27 no.4
• /
• pp.77-86
• /
• 2013

Objectives Allergic purpura is frequent disease in children. The purpose of this study is to analyze traditional Chinese medicine treatments of Allergic purpura in children through traditional Chinese medical journal research. Methods 22 studies were selected based on title keyword "Allergic purpura" "Child" published in CAJ (China Academic Journal). The studies were about clinical effect, herbs, injections, treatments, and nursing in Allergic purpura in children. Results & Conclusions There are so many treatments studied on purpura in children based on CAJ. A Single or combination traditional Chinese medicine treatment is effective in Allergic purpura in children. Therefore, we need to study more about Allergic purpura in children and should make more clinical cases about it.

• International Journal of Advanced Culture Technology
• /
• v.8 no.3
• /
• pp.325-333
• /
• 2020

In the past, eating outside was usually the purpose of eating. However, it has recently expanded into a restaurant culture market. In particular, a dessert culture is being established where people can talk and enjoy. Each consumer has a different tendency to buy chocolate such as health, taste, and atmosphere. Therefore, it is time to recommend chocolate according to consumers' tendency to eat out. In this paper, we propose a chocolate recommendation application based on the tendency to eat out using data on social networks. To collect keyword-based chocolate information, Textom is used as a text mining big data analysis solution.Text mining analysis and related topics are extracted and modeled. Because to shorten the time to recommend chocolate to users. In addition, research on the propensity of eating out is based on prior research. Finally, it implements hybrid app base.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.10 no.3
• /
• pp.1311-1320
• /
• 2016

The fourth industrial revolution is currently proceeding and is expected to significantly affect the way individuals live and in result change the society in various aspects. The ICT-based convergence industries of the fourth industrial revolution contain various fields such as driverless cars, lighter and tougher materials, robotics, 3D printing and even biotechnology. This paper examines the researches done in fourth industrial revolution field based on the articles submitted to APIC-IST 2015. The topics from articles related to the fourth industrial revolution were categorized based on the keyword frequency of main issues. Results suggested that IoT and Wireless sensor network related researches were among the fields that the most researches were done in it and topics like nanotechnology, biotechnology, driverless cars, sharing economy and 3D printing were not mentioned at all. This paper also suggests necessary contents in the fourth industrial revolution to be focused on for further research in this field.