• Journal of the Society of Naval Architects of Korea
• /
• v.29 no.1
• /
• pp.1-13
• /
• 1992

The objective of this study is to develop knowledge-based system for the preliminary design and midship section design of bulk carrier and to enhance the applicability of knowledge engineering in the field of Naval Architecture. First, expert system shell called E.1 is developed in C language. E.1 supports backward-chaining, automatic iteration procedure and reiterative inference mechanism for efficient application of knowledge-based system in structural design. Knowledge representation in E.1 includes IF-THEN rules, 'facts'and 'tables'. Second, knowledge bases for the principal particulars and midship section design are developed by experimental formula, design standard and experiential knowlege. Third, hybrid system combined this knowledge-based system with the optimization program of midship section is developed. Finally, the simplified design method utilizing the regression analysis of the optimum results of stiffened plate is developed for facilitating the design process. Using this knowledge-based system, the design process and results for Bulk carrier and stiffened plates are discussed. It is concluded that knowledge-based system is efficient for preliminary design and midship section design of the ship. It is expected that the performance of the CAD system would be enhanced if the better knowledge-base is accumulated in the E.1 tool.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.64 no.2
• /
• pp.214-221
• /
• 2015

A new classification system with 9 main categories and 56 subcategories for the Open Korean Knowledge Dictionary is proposed. The classification system setup is to prepare for the standard classification system to be used to manage effectively vast of terminologies which were published in the Open Korean Knowledge Dictionary and is meant to enhance the fifteen-year old classification system for the standard korean great dictionary to match up to the trend of the modern terminology. The new terminology classification system covering all the academic areas such as humanity, sociology, politics, science, medicine, agriculture, engineering, etc, is designed and proposed after investigating several classification systems. The classification system setup procedures follow as ${\circ}$ The classification system is designed and planed by both the classification system and the academic expert. ${\circ}$ Classification system design covers all the academic areas following National Science and Technology standard classification system after investigating several classification systems such as the National Research Foundation, National Science and Technology Standard Act, Ministry of Knowledge Economy. ${\circ}$ Poll and survey is made to collect comments from total 93 members of several academic areas. ${\circ}$ The poll result is reviewed among working group members and utilized to update the new terminology classification system. Reclassifications are made for the around 200,000 terms in electricity, computer, medicine, pharmacy, biology, and economics according to the new terminology classification system.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.13 no.4
• /
• pp.821-827
• /
• 2009

Currently, with the development of web 2.0 knowledge sharing system became more and more important. In this paper, we proposed and implemented seminar assistant system using database system and knowledge sharing system on public seminar. We recorded speaker's voice and presentation files on our system and user can review past talks on our seminar review systems. Our database system is implemented using MS SQL, and Input/Output Completion Port(IOCP) socket model as our server side network module. Also we used presentation software using Direct Show with MFC and Windows Presentation Foundation(WPF). and our review system is based on WFP programmed with C# language.

• Annual Conference on Human and Language Technology
• /
• 2022.10a
• /
• pp.289-294
• /
• 2022

의존구문분석은 문장을 의존관계(의존소-지배소)로 분석하는 구문분석 방법론이다. 현재 사전학습모델을 사용한 전이 학습의 딥러닝이 좋은 성능을 보이며 많이 연구되지만, 데이터셋에 의존적이며 그로 인한 자료부족 문제와 과적합의 문제가 발생한다는 단점이 있다. 본 논문에서는 언어학적 지식에 기반한 강화된 지배소-의존소 제약규칙 에지 알고리즘을 심층학습과 결합한 모델을 제안한다. TTAS 표준 가이드라인 기반 모두의 말뭉치로 평가한 결과, 최대 UAS 96.28, LAS 93.19의 성능을 보였으며, 선행연구 대비 UAS 2.21%, LAS 1.84%의 향상된 결과를 보였다. 또한 적은 데이터셋으로 학습했음에도 8배 많은 데이터셋 학습모델 대비 UAS 0.95%의 향상과 11배 빠른 학습 시간을 보였다. 이를 통해 심층학습과 언어지식의 결합이 딥러닝의 문제점을 해결할 수 있음을 확인하였다.

• The Journal of Korean Institute for Practical Engineering Education
• /
• v.2 no.1
• /
• pp.58-63
• /
• 2010

The purpose of this study is to establish a knowledge based system for education of CNC machining. The program is made based on various educational courses, teaching methodology and teaching medium etc. and has a good accessibility which can be used anywhere if computer is available. For the system, various variables according to materials, tools or shapes for machining are reviewed and analyzed. Also, the intelligent educational program is developed using Visual Basic language. It can be used to help trainees who want to refer cutting conditions for actual cutting process and also can be useful for beginner who wants to learn and to practice for CNC machining.

• International conference on construction engineering and project management
• /
• 2007.03a
• /
• pp.337-345
• /
• 2007

Nowadays, it is convenient to use 3D modeling tools for general planning before construction. Normally, a 3D model is built with 3D CAD such as 3D Studio Max, Maya, etc. or simply with AutoCAD. All these software packages are effective in building 3D models but difficult to use, because many provided functions and tools require prior knowledge to build both 2D and 3D designs. Moreover, the traditional method of building 3D models is most time-consuming as experienced operators and manual input are required. Therefore, how to minimize the building time of 3D models and provide easy-to-use functions for users who are not familiar with 3D modeling becomes important. In this paper, the VisualLISP programming language is used to create a convenient tool for efficient generation of 3D components for the AutoCAD environment. This tool will be demonstrated with the generation of a 3D sluice, an artificial passage for water fitted with a valve or gate to stop or regulate water flow. With the tool, users only need to enter the parameters of a sluice in the edit box and the 3D model will be automatically generated in a few seconds. By changing parameters in the edit box and pressing the "OK" button, a new 3D sluice model will be generated in a short while.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.10a
• /
• pp.164-167
• /
• 2022

In table Machine comprehension, the knowledge required for language models or the structural form of tables changes depending on the domain, showing a greater performance degradation compared to text data. In this paper, we propose a pre-learning data construction method and an adversarial learning method through meaningful tabular data selection for constructing a pre-learning table language model robust to these domain changes in table machine reading. In order to detect tabular data sed for decoration of web documents without structural information from the extracted table data, a rule through heuristic was defined to identify head data and select table data was applied. An adversarial learning method between tabular data and infobax data with knowledge information about entities was applied. When the data was refined compared to when it was trained with the existing unrefined data, F1 3.45 and EM 4.14 increased in the KorQuAD table data, and F1 19.38, EM 4.22 compared to when the data was not refined in the Spec table QA data showed increased performance.

• Annual Conference on Human and Language Technology
• /
• 2019.10a
• /
• pp.272-275
• /
• 2019

단어 중의성 해소 방법은 지식 정보를 활용하여 문제를 해결하는 지식 기반 방법과 각종 기계학습 모델을 이용하여 문제를 해결하는 지도학습 방법이 있다. 지도학습 방법은 높은 성능을 보이지만 대량의 정제된 학습 데이터가 필요하다. 반대로 지식 기반 방법은 대량의 정제된 학습데이터는 필요없지만 높은 성능을 기대할수 없다. 최근에는 이러한 문제를 보완하기 위해 지식내에 있는 정보와 정제된 학습데이터를 기계학습 모델에 학습하여 단어 중의성 해소 방법을 해결하고 있다. 가장 많이 활용하고 있는 지식 정보는 상위어(Hypernym)와 하위어(Hyponym), 동의어(Synonym)가 가지는 의미설명(Gloss)정보이다. 이 정보의 표상을 기존의 문장의 표상과 같이 활용하여 중의성 단어가 가지는 의미를 파악한다. 하지만 정확한 문장의 표상을 얻기 위해서는 단어의 표상을 잘 만들어줘야 하는데 기존의 방법론들은 모두 문장내의 문맥정보만을 파악하여 표현하였기 때문에 정확한 의미를 반영하는데 한계가 있었다. 본 논문에서는 의미정보와 문맥정보를 담은 단어의 표상정보를 만들기 위해 구문정보, 의미관계 그래프정보를 GCN(Graph Convolutional Network)를 활용하여 임베딩을 표현하였고, 기존의 모델에 반영하여 문맥정보만을 활용한 단어 표상보다 높은 성능을 보였다.

• Annual Conference on Human and Language Technology
• /
• 2023.10a
• /
• pp.319-323
• /
• 2023

일반 상식 기반의 지식 그래프는 대규모 코퍼스에 포함되어 있는 일반 상식을 수집하고 구조화하는 지식의 표현 방법이다. 일반 상식 기반의 지식 그래프는 코퍼스 내에 포함되어 있는 다양한 일반 상식의 형태와 관계를 모델링하며, 주로 질의응답 시스템, 상식 추론 등의 자연어처리 하위 작업에 활용할 수 있다. 가장 잘 알려진 일반 상식 기반의 지식 그래프로는 ConceptNet [1], ATOMIC [2]이 있다. 하지만 한국어 기반의 일반 상식 기반의 지식 그래프에 대한 연구가 존재했지만, 자연어처리 태스크에 활용하기에는 충분하지 않다. 본 연구에서는 대규모 언어 모델과 프롬프트의 활용을 통해 한국어 일반 상식 기반의 지식 그래프를 효과적으로 구축하는 방법론을 제시한다. 또한, 제안하는 방법론으로 구축한 지식 그래프와 기존의 한국어 상식 그래프의 품질을 양적, 질적으로 검증한다.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.40 no.5
• /
• pp.429-437
• /
• 2022

Recently, the demand for a QA (Question Answering) system for human-machine communication has increased. Among the QA systems, a closed domain QA system that can handle spatial-related questions is called GeoQA. In this study, a new type of graph database, LPG (Labeled Property Graph) was used to overcome the limitations of the RDF (Resource Description Framework) based database, which was mainly used in the GeoQA field. In addition, GraphQL (Graph Query Language), an API-type query language, is introduced to address the fact that the LPG query language is not standardized and the GeoQA system may depend on specific products. In this study, database was built so that answers could be retrieved when spatial-related questions were entered. Each data was obtained from the national spatial information portal and local data open service. The spatial relationships between each spatial objects were calculated in advance and stored in edge form. The user's questions were first converted to GraphQL through FOL (First Order Logic) format and delivered to the database through the GraphQL server. The LPG used in the experiment is Neo4j, the graph database that currently has the highest market share, and some of the built-in functions and QGIS were used for spatial calculations. As a result of building the system, it was confirmed that the user's question could be transformed, processed through the Apollo GraphQL server, and an appropriate answer could be obtained from the database.