• 한국공간정보시스템학회:학술대회논문집
• /
• 2005.11a
• /
• pp.55-60
• /
• 2005

지리 공간 정보에 대한 관심 증가와 더불어 활용 분야도 다양해지고 있다. OGC(Open GIS Consortium)에서는 XML(extensible Markup Language)을 GIS 분야에 도입한 GML(Geography Markup Language)을 개발하였으며 여러 활용 분야에서 GML을 사용하고 계속적으로 연구되고 있다. 본 연구에서는 기존의 XML 문서를 기반으로 연구되었던 데이터 마이닝 방법 중 하나인 연관규칙을 GML 데이터에 사용하여 의미 있는 규칙을 찾아내려 한다. 규칙을 찾는 방법에는 2가지가 있을 수 있는데 하나는 GML 데이터의 내용만을 뽑아내어 그에 따른 규칙을 찾아내는 방법이고, 다른 하나는 사용된 태그와 속성을 기반으로 규칙을 찾아내는 방법이다. 본 연구에서는 2가지 방법을 통해 규칙을 찾는 것에 대하여 기술할 것이다. 본 연구를 바탕으로 GML문서를 사용하는 여러 분야에서 기본 정보뿐만 아니라 함축적이고 의미 있는 정보도 얻어 낼 수 있을 것으로 기대한다.

• Annual Conference on Human and Language Technology
• /
• 2014.10a
• /
• pp.228-232
• /
• 2014

지식 베이스(Knowledge Base)는 주어진 질의 문에 대한 잠재적인 답과 답에 대한 단서가 될 수 있는 구조화된 형태의 정보를 포함하고 있기 때문에 질의응답 시스템에서 매우 중요하다. 하지만 비록 DBpedia, Freebase, YAGO 등과 같이 이용 가능한 여러 개의 지식 베이스가 존재함에도 불구하고 이러한 지식 베이스에 포함되어 있는 정보는 웹(Web)상에 존재하는 정보에 비하면 매우 제한적이다. 본 논문에서는 무제한 정보 추출 기술을 이용하여 정형화되지 않은 텍스트로부터 트리플(Triple)을 추출하고, 추출된 트리플의 각 개체 및 관계 어휘를 대상 온톨로지(Ontology) 상의 어휘에 사상시킴으로써 지식 베이스를 확장 시키는 방법을 제안한다. 이를 통하여 무제한 정보 추출 방법과 명확화(Disambiguation) 기술이 지식 베이스를 확장시키는데 어떻게 사용될 수 있고, 어떠한 요소가 전체 시스템의 주된 성능 저하를 일으키며 개선되어야 하는지 알아보도록 한다.

• Proceedings of the CALSEC Conference
• /
• 2004.02a
• /
• pp.107-111
• /
• 2004

The purpose of the study is to develop an integrated knowledge management system for the domains of genome and nano-technology, in which terminology-based literature mining, knowledge acquisition, knowledge structuring, and knowledge retrieval are combined. The system supports integrating different types of databases (papers and patents, technologies and innovations) and retrieving different types of knowledge simultaneously. The main objective of the system is to facilitate knowledge acquisition from documents and new knowledge discovery through a terminology-based similarity calculation and a visualization of automatically structured knowledge. Implementation issue of the system is also mentioned.

• Annual Conference on Human and Language Technology
• /
• 2015.10a
• /
• pp.41-45
• /
• 2015

무제한 정보추출은 주로 영어를 대상으로 연구가 진행 되었지만, 최근에는 영어가 아닌 다른 언어에 대한 적용이 시도되고 있다. 본 논문에서는 관계 어휘의 유형을 동사형과 명사형 2가지로 정의하고, 각 유형별로 구문 분석 결과 기반의 서로 다른 방법론을 적용하는 한국어 대상 무제한 정보추출 시스템을 소개한다. 동사형 관계 어휘에 대해서는 의존 관계 기반의 추출 규칙을 적용하고, 명사형 관계 어휘에 대해서는 대량의 말뭉치로부터 자동으로 학습한 의존 관계 구조 기반의 추출 패턴을 적용한다. 임의의 100개 문장에 대해서 수행한 결과는 산출된 전체 트리플에 대해 0.8이상의 정밀도를 보임으로써 본 논문에서 제안하는 방법의 효용성을 증명하였다.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.23 no.3
• /
• pp.120-131
• /
• 2020

Water body detection using remote sensing based on machine interpretation of satellite image is efficient for managing water resource, drought and flood monitoring. In this study, water body detection with SAR satellite image based on machine learning was performed. However, non water body area can be misclassified to water body because of shadow effect or objects that have similar scattering characteristic comparing to water body, such as roads. To decrease misclassifying, 8 combination of morphology open filtered band, DEM band, curvature band and Cosmo-SkyMed SAR satellite image band about Mokpo region were trained to semantic segmentation machine learning models, respectively. For 8 case of machine learning models, global accuracy that is final test result was computed. Furthermore, concordance rate between landcover data of Mokpo region was calculated. In conclusion, combination of SAR satellite image, morphology open filtered band, DEM band and curvature band showed best result in global accuracy and concordance rate with landcover data. In that case, global accuracy was 95.07% and concordance rate with landcover data was 89.93%.

• KIPS Transactions on Computer and Communication Systems
• /
• v.8 no.5
• /
• pp.119-126
• /
• 2019

Typical software developed and used by North Korea is Red Star and internal application software. However, most of the existing research on the North Korean software is the software installation method and general execution screen analysis. One of the ways to identify software vulnerabilities is file fuzzing, which is a typical method for identifying security vulnerabilities. In this paper, we use file fuzzing to analyze the security vulnerability of the software used in North Korea's Seogwang Document Processing System. At this time, we propose the analysis of open document text (ODT) file produced by Seogwang Document Processing System, extraction of node based on Document Object Mode (DOM) to determine test target, and generation of mutation file through insertion and substitution, this increases the number of crash detections at the same testing time.

• Journal of KIBIM
• /
• v.8 no.1
• /
• pp.56-62
• /
• 2018

There exists no precedented case of quantity take-off, using parametric modeling, from BIM-based irregular structures. Civil 3D provides earthwork quantity take-off based on surface modeling. Generally, designers should enter data into the specification additionally after extracting quantity estimation from earthwork modeling design. The objective of this report is to suggest the method from quantity take-off to specification of BIM-based earthwork quantities. We intend to investigate earthwork take-off method by Civil3D and explain why parametric information extraction is required for quantity estimation and specification and how information of earthwork quantity based on solid and surface modeling is connected to open quantity take-off module. It is highly expected that this suggestion would be the practical methodology of earthwork quantity take-off and specification in the field of civil engineering.

• Journal of the Korea Society of Computer and Information
• /
• v.18 no.9
• /
• pp.1-10
• /
• 2013

In this paper, we implement the SIFT(Scale-Invariant Feature Transform) algorithm for feature point extraction using a many-core processor, and analyze the performance, area efficiency, and system area efficiency of the many-core processor. In addition, we demonstrate the potential of the proposed many-core processor by comparing the performance of the many-core processor with that of high-performance CPU and GPU(Graphics Processing Unit). Experimental results indicate that the accuracy result of the SIFT algorithm using the many-core processor was same as that of OpenCV. In addition, the many-core processor outperforms CPU and GPU in terms of execution time. Moreover, this paper proposed an optimal model of the SIFT algorithm on the many-core processor by analyzing energy efficiency and area efficiency for different octave sizes.

• Journal of Korea Multimedia Society
• /
• v.15 no.4
• /
• pp.540-551
• /
• 2012

Recently, the W3C has developed the HTML5 standard which gives the basis for providing various web applications on the web environments. Because of the advent of the smart devices and the broadband wireless network, users can accesse the web applications on the smart devices at anytime and anywhere. In addition, the demand on the multiscreen services, which enables users to use the appropriate device to their situation, has increased, since users have various smart devices. In this paper, we propose the grouping mechanism of web objects on the HTML5 based web platform, the extraction mechanism of the web object information which is used to create the web object on other devices, and the web object creation mechanism based on the received web object information. In addition, we propose the web service migration architecture between devices on the open web platform and implement the grouping, extraction and creation mechanism of the web objects on the test web document and generic web document with Chrome extension. Finally, we implement the delivery mechanism of the web object information between devices using the node.js and the WebSocket technologies.

• Journal of the Korean BIBLIA Society for library and Information Science
• /
• v.26 no.4
• /
• pp.83-104
• /
• 2015

This study intends to provide guidance for library design and assessment by eliciting the emotional vocabulary related to academic library space. In order to accomplish the goal of this study, 12 major emotional vocabularies related to academic library space were derived through 5 stages of extraction and refinement processes. Literature search and analysis of preceding research, focus group interview and survey of academic librarians and users of the academic library, evaluation of similarity through KJ Method, etc., selected 12 adjectives of emotional vocabulary as follows: diverse, satisfactory, necessary, full, clean, stable, appropriate, harmonious, open, warm, natural, and excellent.