• 한국안전학회지
• /
• 제33권6호
• /
• pp.77-84
• /
• 2018

Report documents of industrial and occupational accidents have continuously been accumulated in private and public institutes. Amongst others, information on narrative-texts of accidents such as accident processes and risk factors contained in disaster report documents is gaining the useful value for accident analysis. Despite this increasingly potential value of analysis of text information, scientific and algorithmic text analytics for safety management has not been carried out yet. Thus, this study aims to develop data processing and visualization techniques that provide a systematic and structural view of text information contained in a disaster report document so that safety managers can effectively analyze accident risk factors. To this end, the risk factor map using text mining and self-organizing map is developed. Text mining is firstly used to extract risk keywords from disaster report documents and then, the Self-Organizing Map (SOM) algorithm is conducted to visualize the risk factor map based on the similarity of disaster report documents. As a result, it is expected that fruitful text information buried in a myriad of disaster report documents is analyzed, providing risk factors to safety managers.

• 한국멀티미디어학회논문지
• /
• 제8권5호
• /
• pp.596-605
• /
• 2005

기존의 XML 질의 방법은 단순 키워드 정합이나 단순 구조적 확장 등에 국한되므로 문서에 내재된 정보를 검색하기에 불충분할 뿐만 아니라,모든 문서에 질의를 인가함으로써 정보검객의 효율을 저하시킨다. 본 연구는 온톨로지로부터 생성한 포괄적 BTD에 의해 검객대상 문서를 사전에 미리 선별하는 문서여과 방법과 온톨로지의 개념구조와 개념 간 연관관계를 추론하여 질의를 확장하는 방법을 제안함으로써 XML정보검색의 효과를 증대 하고자 한다. 제안한 문서여과 및 질의확장 방법은 다양한 XML 문서를 대상으로 검색 효과를 실험하였다.

• 스마트미디어저널
• /
• 제5권3호
• /
• pp.30-34
• /
• 2016

Nowadays, there are a lot of Korean documents, which often need to be identified in one of printed or handwritten text. Early methods for the identification use structural features, which can be simple and easy to apply to text of a specific font, but its performance depends on the font type and characteristics of the text. Recently, the bag-of-words model has been used for the identification, which can be invariant to changes in font size, distortions or modifications to the text. The method based on bag-of-words model includes three steps: word segmentation using connected component grouping, feature extraction, and finally classification using SVM(Support Vector Machine). In this paper, bag-of-words model based method is proposed using SURF(Speeded Up Robust Feature) for the identification of machine printed and handwritten text in Korean documents. The experiment shows that the proposed method outperforms methods based on structural features.

• 한국멀티미디어학회논문지
• /
• 제7권5호
• /
• pp.601-616
• /
• 2004

구조적 문서들에 대한 검색시스템은 구조 기반 검색 질의를 지원하여 다양한 수준의 검색 기능을 제공한다. 완전한 구조 기반 질의를 처리하기 위해서는 구조적 문서가 가지는 엘리먼트 간의 구조적 포함관계나 순서에 관한 정보를 유지되어야 한다. 본 논문에서는 엘리먼트와 엘리먼트 사이의 구조적 상관관계와 엘리먼트의 발생순서에 관련된 질의 등 여러 유형의 순수 구조 질의를 처리할 수 있는 네 가지 색인구조를 제시하고 그 성능을 평가한다. 제안된 색인 알고리즘은 전체 문서 인스턴스 트리 개념에 바탕을 두고 있다.

• 안보군사학연구
• /
• 통권2호
• /
• pp.237-260
• /
• 2004

As the research work about XML based on the development of Internet and according to the information exchange standard is being carried out, the need of discovering new methods to store XML documents and manage them efficiently according to the frequency of large-capacity XML documents increases. Consequently, as a kind of back-end database system, XML storage systems such as RDBMS, OODBMS and Native XML DBMS etc. are coming forth in order to save XML documents. It is an urgent task to make comparisons among usage expense, function comparison storage, inquiry, and manage dimension for each DBMS. This paper makes an analysis and comparison of DTD-independent XML document access methods in RDBMS, OODBMS and Native XML DBMS for XML storage and management. After analyzing the advantages and disadvantages of each access method and comparing the function of typical commerce DBMS such as Oracle 8i, eXcelon and Tamino for finding the possibility of military applications, an another appropriate method to save XML documents is proposed as to find an implementation approach to save structural XML documents.

• 한국정보통신학회:학술대회논문집
• /
• 한국정보통신학회 2018년도 춘계학술대회
• /
• pp.462-463
• /
• 2018

기존의 문서 분석 시스템들은 형태소 분석기나 TF-IDF 기법을 통해 단어 위주의 분석을 진행하였다. 이러한 시스템들은 키워드들의 가중치를 계산하여 주요 키워드를 도출할 수 있는 장점이 있다. 이에 반해 문서의 내용을 분석하기에는 구조적인 한계로 인해 부적합한 실정이다. 이를 해결하기 위해 본 논문에서 제안하는 알고리즘은 문서 내에 있는 문단들의 가중치를 계산한 뒤 문단들을 영역별로 분할한다. 그리고 분할된 영역별로 중요도를 계산하여 해당 문서 내에 가장 중요한 문단들이 있는 영역을 사용자에게 알려준다. 이를 통해 사용자는 기존의 문서 분석 시스템들을 사용할 때보다 문서를 분석하기에 적합한 서비스를 제공받을 것으로 사료된다.

• International Journal of Contents
• /
• 제13권3호
• /
• pp.38-42
• /
• 2017

Documents of the last few decades typically include more than one kind of language, so linguistic classification of each word is essential, especially in terms of English and Korean in handwritten documents. Traditional methods mostly use conventional features of structural or stroke features, but sometimes they fail to identify many characteristics of words because of complexity introduced by handwriting. Therefore, traditional methods lead to a considerably more-complicated task and naturally lead to possibly poor results. In this study, convolutional neural network (CNN) is used for classification of English and Korean handwritten words in text documents. Experimental results reveal that the proposed method works effectively compared to previous methods.

• 한국건축시공학회:학술대회논문집
• /
• 한국건축시공학회 2023년도 봄 학술논문 발표대회
• /
• pp.273-274
• /
• 2023

Although there are many old school buildings that is more than 40 years in Korea, it is difficult to rebuild all of them due to limitations in budget management. Therefore, objective feasibility evaluation criteria are necessary to determine which school buildings should be rebuilt preferentially among the numerous old school buildings. One of the rebuilding feasibility evaluation items, economic evaluation generally requires documents such as construction statements and facility drawings. However, because most buildings older than 40 years do not have these documents, an economic analysis model that requires only basic building information should be developed. In this study, the economic analysis model that can be used for evaluating the rebuilding feasibility only with the number of years, total floor area, and structural information of school buildings was established. This model can contribute to the objective feasibility evaluation of old school buildings because it can evaluate numerous buildings on the same criteria based on basic building information.

• 한국콘크리트학회:학술대회논문집
• /
• 한국콘크리트학회 1995년도 봄 학술발표회 논문집
• /
• pp.231-236
• /
• 1995

The object of this thesis is an analytical study on flexural deformation of high strength concrete structures using reliability theory. Using the established experimental data that have been presented in various documents the stress-strain relationship curves of high strength(500kgf/$\textrm{cm}^2$)models are proposed. Based on both methods of logarithm regression analysis and multiple regression analysis adopted in order to establish the relationships between design parameters, response random variables and flexural deformation analyzed using Monte Carlo simulation and Simpson composite formula. Additional random variables are introduced to incorporate both the confidence in the analytical accuracy of engineering mechanics associated with structural response quantities and the uncertainty in the construction quality control. The result is expected to accomodate other important design parameter of high strength concrete design in treating reliability theory that practicing engineers, structural engineering often face.

• Nuclear Engineering and Technology
• /
• 제54권5호
• /
• pp.1726-1746
• /
• 2022

This paper presents fracture mechanics analysis results for various cracks located at pressurized water reactor pressure vessel nozzle crotch corners taking into consideration constraint effect. Technical documents such as the ASME B&PV Code, Sec.XI were reviewed and then a fracture mechanics analysis procedure was proposed for structural integrity assessment of various nozzle crotch corner cracks under normal operation conditions considering the constraint effect. Linear elastic fracture mechanics analysis was performed by conducting finite element analysis with the proposed analysis procedure. Based on the evaluation results, elastic-plastic fracture mechanics analysis taking into account the constraint effect was performed only for the axial surface crack of the reactor pressure vessel outlet nozzle with cladding. The fracture mechanics analysis result shows that only the axial surface crack in the reactor pressure vessel outlet nozzle has the stress intensity factor exceeding the low bound of upper-shelf fracture toughness irrespectively of considering the constraint effect. It is confirmed that the J-integral for the axial crack of the outlet nozzle does not exceed the ductile crack initiation toughness. Hence, it can be ensured that the structural integrity of all the cracks is maintained during the normal operation.