• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.9 no.8
• /
• pp.3216-3230
• /
• 2015

A hot-issued research topic in the workflow intelligence arena is the emerging topic of "workflow-supported organizational social networks." These specialized social networks have been proposed to primarily represent the process-driven work-sharing and work-collaborating relationships among the workflow-performers fulfilling a series of workflow-related operations in a workflow-supported organization. We can discover those organizational social networks, and visualize its analysis results as organizational knowledge. In this paper, we are particularly interested in how to visualize the degrees of closeness centralities among workflow-performers by proposing a graphical representation schema based on the Graph Markup Language, which is named to ccWSSN-GraphML. Additionally, we expatiate on the functional expansion of the closeness centralization formulas so as for the visualization framework to handle a group of workflow procedures (or a workflow package) with organizational workflow-performers.

• Proceedings of the KIEE Conference
• /
• 2000.07d
• /
• pp.2296-2298
• /
• 2000

Fuzzy control has been researched for application of industrial processes which have no accurate mathematical model and could not controlled by conventional methods because of a lack of quantitative input-output data. Intelligent control approach based on fuzzy logic could directly reflex human thinking and natural language to controller comparing with conventional methods. In this paper, fuzzy controller is implemented to acquire operator's knowledge. The tested system is constructed for sending a ball to the goal position using wind from two DC motors in the path. This system contains non-linearity and uncertainty because of the characteristic of aerodynamics inside the path. Ball position is measured by a vision camera. The system used in this experiment could be hardly modeled by mathematic methods and could not be easily controlled by linear control manners. The controller, in this paper is designed based on the input-output data and experimental knowledge obtained by trials.

• Annual Conference on Human and Language Technology
• /
• 2020.10a
• /
• pp.529-534
• /
• 2020

인공신경망 기반 기계번역(Neural Machine Translation, NMT)이란 딥러닝(Deep learning)을 이용하여 출발 언어의 문장을 도착 언어 문장으로 번역해주는 시스템을 일컫는다. NMT는 종단간 학습(end-to-end learning)을 이용하여 기존 기계번역 방법론의 성능을 앞지르며 기계번역의 주요 방법론으로 자리잡게 됐다. 이러한 발전에도 불구하고 여전히 개체(entity), 또는 전문 용어(terminological expressions)의 번역은 미해결 과제로 남아있다. 개체나 전문 용어는 대부분 명사로 구성되는데 문장 내 명사는 주체, 객체 등의 역할을 하는 중요한 요소이므로 이들의 정확한 번역이 문장 전체의 번역 성능 향상으로 이어질 수 있다. 따라서 본 논문에서는 지식그래프(Knowledge Graph)를 이용하여 심볼릭 지식을 NMT와 결합한 뉴럴심볼릭 방법론을 제안한다. 또한 지식그래프를 활용하여 NMT의 성능을 높인 선행 연구 방법론을 한영 기계번역에 이용할 수 있도록 구조를 설계한다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2009.11a
• /
• pp.801-802
• /
• 2009

Currently, XML and its schema language have become the standard for data representation and information exchange format on the current web. Unfortunately, problems happen when integrating different data sources since XML mainly supports the document structure but lack consideration on sharing knowledge of data. Meanwhile, Semantic Web technologies, such as Web Ontology Language (OWL), can include the structure as well as the semantics of the data. Therefore, finding a way to integrate XML data as OWL ontology receives a high interest nowadays. In this paper we present a mapping notation to convert XML Schema to OWL domain knowledge and an effective method to transform XML instances into OWL individuals. While keeping the XML original structure, our work also adds more semantics for the XML document. Moreover, whole of the transformation processes are done automatically without any user interference. Further, our transforming approach provides the solution for duplicate element names in XML document which has not mentioned in the previous work. Our results in existing OWL syntaxes can be loaded immediately by OWL editors and Semantic Web applications.

• Annual Conference on Human and Language Technology
• /
• 2014.10a
• /
• pp.139-142
• /
• 2014

시맨틱웹의 구현 도구로써 온톨로지가 있다. 온톨로지는 지식개념의 의미적 연결을 하는데 사용된다. 영어 위키피디아를 토대로 한 영어 DBpedia 온톨로지는 스키마(owl파일 형태)와 인스턴스 모두 잘 구축이 되어있다. 그리고 영어 DBpedia의 각 Class에 한글은 레이블의 형태로 달려있다. 하지만 한글 레이블을 가지고 있지 않은 영어 DBpedia의 Class들이 절반이 넘기 때문에 한글 Class들만으로 된 스키마 구축은 의미가 있다. 한글 Class들로 만들어진 스키마가 있다면 두 한글 온톨로지 사이의 클래스 매칭 알고리즘을 위한 실험이나 한글 온톨로지 자동 증강 알고리즘의 연구 등에 유용하게 쓰일 수 있을 것이다. 본 논문에서 구축한 한글 DBpedia 온톨로지 스키마는 영문 DBpedia 온톨로지의 계층구조와 한글 클래스와 영문 클래스 사이의 매핑정보를 바탕으로 구축되었다. 그리고 기존에 제공되는 한글 DBpedia 온톨로지 클래스의 영어매핑 정보가 있는 한글 프로퍼티와 영어매핑 정보가 없는 한글 프로퍼티를 모두 한글 클래스의 프로퍼티로 입력해주었다.

• Industrial Engineering and Management Systems
• /
• v.9 no.1
• /
• pp.1-9
• /
• 2010

Increasing product variety based on product family and product platform provides a company with a competitive advantage over its competitors. As products become more complex, short-life cycled and customized, the design efforts require more knowledge-intensive, collaborative and coordinating efforts for information sharing. By sharing knowledge, information, component and process across different families of products, the product realization process will be more efficient, cost-effective and quick-responsive. Formal Concept Analysis (FCA) is used for analyzing data and forming semantic structures that are formal abstractions of concepts of human thoughts. A Web Ontology Language (OWL) is designed for applications that need to process the content of information instead of simply presenting information to humans. OWL also captures the evolution of different components of the product family. The purpose of this paper is to develop product variety modeling to increase the usefulness of common platform. In constructing and analyzing product ontology, FCA is adopted for conceptual knowledge processing. For the selected product family, product variety Ontology is constructed and implemented using prot$\'{e}$g$\'{e}$-2000.

• KIPS Transactions on Software and Data Engineering
• /
• v.9 no.8
• /
• pp.243-250
• /
• 2020

Knowledge graph-based question answering not only requires deep understanding of the given natural language questions, but it also needs effective reasoning to find the correct answers on a large knowledge graph. In this paper, we propose a deep neural network model for effective reasoning on a knowledge graph, which can find correct answers to complex questions requiring multi-hop inference. The proposed model makes use of highly expressive bilinear graph neural network (BGNN), which can utilize context information between a pair of neighboring nodes, as well as allows bidirectional feature propagation between each entity node and one of its neighboring nodes on a knowledge graph. Performing experiments with an open-domain knowledge base (Freebase) and two natural-language question answering benchmark datasets(WebQuestionsSP and MetaQA), we demonstrate the effectiveness and performance of the proposed model.

• Journal of the Korean institute of surface engineering
• /
• v.26 no.3
• /
• pp.121-126
• /
• 1993

In this study, a user-friendly expert system is developed for bright nickel plating processes which have a number of influence factors related to the plating quality. Because the mutual relations between these factors in the processes are not quantitatively identified, the expert system deals mainly with the troubleshooting process problems by using the production rule which is able to utilize effectively the qualitatives knowledge and the accumulated experience. Especially, to provide the system user with more timely and convenient informations about the cause of problem symptom and the corresponding countermeasure, it is introduced the interactive user interface using the Korean language. Also the knowledge base and inference engine of the expert system are completely separated, so that the substance of knowledge base can be easily updated and extended.

• Journal of Engineering Education Research
• /
• v.13 no.6
• /
• pp.57-71
• /
• 2010

This paper is a study on the perception of current competency and expected competency of engineering freshmen by extracting core competencies acquired from university education. It also aims to suggest proper way for engineering university education. This study extracts competencies in the following five areas as core competencies: 'knowledge on major area', 'cultural ability', 'foreign language ability', 'basic learning ability', 'intercommunication ability'. To achieve this purpose, this study surveyed 'C' university engineering department freshmen (584 students) with questionnaires about their perception of core competencies. The results are as follows. First, engineering freshmen perceived current competencies were weak in every area, especially their capacities in 'foreign language ability' area were perceived to be weakest. Their demand for education is the highest in 'foreign language ability' area, and the second higher in 'knowledge on major area'. Secondly, there exists meaningful difference between perception of current competency and expected competency depending on the gender, high school department (science/liberal arts), high school location, types of college admissions, and types of mathematics in NAST. According to these results, this study suggests enhancement of foreign language (English) education in engineering department, design and implementation of various educational program to overcome individual difference, promoting importance of competencies in the 'cultural abilty' and 'intercommunication abilty', necessity of continuous adjustment and complementation for engineering educational program through accumulation of feedback processes, activation of career education through engineering education and special programs.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2000.10b
• /
• pp.1227-1230
• /
• 2000

본 연구는 서로 다른 형식(format)으로 작성된 무선인터넷 문서들간의 상호 변환(reformatting)을 다루고 있다. 무선인터넷에 접속하는 단말기는 보통 하나의 형식만을 지원하는데 비해서, 무선인터넷 문서를 작성하는데 필요한 마크업 언어(markup language)로는 WML, HDML, mHTML 등 다양한 형식들이 존재하고 있다. 이에 본 연구에서 지식 기반 시스템(knowledge based system)과 XML(extensible Markup Language)을 이용하는 문서 형식 변환 기술을 제공하여, 무선인터넷 컨텐츠 구축시 특정 형식에 구애받지 않도록 하였다.