• 지능정보연구
• /
• 제25권1호
• /
• pp.43-61
• /
• 2019

최근 4차 산업혁명과 함께 인공지능 기술에 대한 연구가 활발히 진행되고 있으며, 이전의 그 어느 때보다도 기술의 발전이 빠르게 진행되고 있는 추세이다. 이러한 인공지능 환경에서 양질의 지식베이스는 인공지능 기술의 향상 및 사용자 경험을 높이기 위한 기반 기술로써 중요한 역할을 하고 있다. 특히 최근에는 인공지능 스피커를 통한 질의응답과 같은 서비스의 기반 지식으로 활용되고 있다. 하지만 지식베이스를 구축하는 것은 사람의 많은 노력을 요하며, 이로 인해 지식을 구축하는데 많은 시간과 비용이 소모된다. 이러한 문제를 해결하기 위해 본 연구에서는 기계학습을 이용하여 지식베이스의 구조에 따라 학습을 수행하고, 이를 통해 자연어 문서로부터 지식을 추출하여 지식화하는 방법에 대해 제안하고자 한다. 이러한 방법의 적절성을 보이기 위해 DBpedia 온톨로지의 구조를 기반으로 학습을 수행하여 지식을 구축할 것이다. 즉, DBpedia의 온톨로지 구조에 따라 위키피디아 문서에 기술되어 있는 인포박스를 이용하여 학습을 수행하고 이를 바탕으로 자연어 텍스트로부터 지식을 추출하여 온톨로지화하기 위한 방법론을 제안하고자 한다. 학습을 바탕으로 지식을 추출하기 위한 과정은 문서 분류, 적합 문장 분류, 그리고 지식 추출 및 지식베이스 변환의 과정으로 이루어진다. 이와 같은 방법론에 따라 실제 지식 추출을 위한 플랫폼을 구축하였으며, 실험을 통해 본 연구에서 제안하고자 하는 방법론이 지식을 확장하는데 있어 유용하게 활용될 수 있음을 증명하였다. 이러한 방법을 통해 구축된 지식은 향후 지식베이스를 기반으로 한 인공지능을 위해 활용될 수 있을 것으로 판단된다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제13권8호
• /
• pp.3917-3941
• /
• 2019

The recent interest in artificial intelligence and machine learning has partly contributed to an interest in the use of such approaches for hyperspectral remote sensing (HRS) imagery classification, as evidenced by the increasing number of deep framework with deep convolutional neural networks (CNN) structures proposed in the literature. In these approaches, the assumption of obtaining high quality deep features by using CNN is not always easy and efficient because of the complex data distribution and the limited sample size. In this paper, conventional handcrafted learning-based multi features based on expert knowledge are introduced as the input of a special designed CNN to improve the pixel description and classification performance of HRS imagery. The introduction of these handcrafted features can reduce the complexity of the original HRS data and reduce the sample requirements by eliminating redundant information and improving the starting point of deep feature training. It also provides some concise and effective features that are not readily available from direct training with CNN. Evaluations using three public HRS datasets demonstrate the utility of our proposed method in HRS classification.

• 한국정보처리학회논문지
• /
• 제7권3호
• /
• pp.842-851
• /
• 2000

Developers can reuse not only class code but also wide range of knowledge on domain by reusing framework. Existing Object-Oriented Methodology and Catalysis Methodology were presented when redefining component in the course of redesigning framework. However, existing methodologies have weakness that entire process is waterfall mode or design of interface lays too much stress on implementation stage. So, this thesis will present Component-Oriented Methodology for the reuse of framework, and construct the environment for framework and domain development. That is, domain is analyzed by input of domain knowledge on real world to create software based on component, and hotspot is identified through analyzed information, and refactoring by putting additional information on users and developers. After that, I will create domain framework and application framework depending on domain. In this Component-Oriented Methodology, information is searched, understood and extracted or composite through component library storage internally. Then this information is classified into the information on component, and used as additional information in redesigning. With this, developer can obtain reusability, easiness and portability by constructing infrastructure environment that allows to register, update and delete component through Component Management System(CMS) under he development environment which can be easily applied to his own application using framework component, in this thesis, CoRBA(Common Object Request Broker Architecture) environment.

• 근관절건강학회지
• /
• 제28권3호
• /
• pp.252-262
• /
• 2021

Purpose: To define the concept of digital health literacy and identify its attributes. Methods: Walker and Avant's approach was employed for concept analysis. Attributes, antecedents, consequences, and the definition of digital health literacy were derived from a review of 28 studies. Results: Digital health literacy was identified to possess the following five attributes: health information seeking, health information processing, health information communication, health-related knowledge translation, and utilizing digital technology. Basic literacy skills, health concerns, motivation to use technology for health information, and access to digital technologies were all antecedents of the concept. The consequences of the concept were health behaviors, patient engagement, health status, and quality of life. Digital health literacy is the ability to seek relevant health information utilizing digital technology to solve health problems and improve quality of life. Furthermore, it refers to the translation of health-related knowledge obtained through health information processing-finding, understanding, and evaluating health information and health information communication-into the context in which individual and social factors interact. Conclusion: This study presented a new definition of digital health literacy that goes beyond existing internet-based eHealth literacy, by incorporating the context of emerging digital technologies. This proposed definition can serve as a foundation for the development of instruments and educational programs to improve individuals' digital health literacy.

• Journal of Information Processing Systems
• /
• 제15권4호
• /
• pp.986-1016
• /
• 2019

Mobile user interface pattern (MUIP) is a kind of structured representation of interaction design knowledge. Several studies have suggested that MUIPs are a proven solution for recurring mobile interface design problems. To facilitate MUIP selection, an effective clustering method is required to discover hidden knowledge of pattern data set. In this paper, we employ the semi-supervised kernel fuzzy c-means clustering (SSKFCM) method to cluster MUIP data. In order to improve the performance of clustering, clustering parameters are optimized by utilizing the global optimization capability of particle swarm optimization (PSO) algorithm. Since the PSO algorithm is easily trapped in local optima, a novel PSO algorithm is presented in this paper. It combines an improved intuitionistic fuzzy entropy measure and a new population search strategy to enhance the population search capability and accelerate the convergence speed. Experimental results show the effectiveness and superiority of the proposed clustering method.

• 정보처리학회논문지D
• /
• 제13D권4호
• /
• pp.525-534
• /
• 2006

시맨틱 웹 기반의 서비스를 제공하기 위해서는 특정 도메인 지식에 대한 명시적인 명세화 및 지식의 개념과 개념과의 관계를 정형화하는 온톨로지를 통해서 이루어진다. 그러므로 특정 도메인 지식의 명세화와 정형화를 위해서는 관심 있는 도메인내의 지식을 개념화하는 온톨로지의 생성이 필수적이다. 이 논문에서는 택배 마케팅의 잠재 고객에 대한 정보를 검색하기 위해, 시맨틱 웹 기반의 온톨로지 생성을 위한 구체적인 도메인을 설계하고, 생성된 온톨로지를 이용하는 정보 검색 방법을 제안하였다. 제안된 온톨로지를 기반으로 고객의 정보를 수집하는 데이터 검색 로봇을 구현 하였다. 아울러 온톨로지의 생성과 데이터 검색 로봇이 데이터 검색을 정확하게 수행함을 확인 하였다.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• 제8권4호
• /
• pp.254-259
• /
• 2008

Uncertainty of result of context awareness always exists in any context-awareness computing. This falling-off in accuracy of context awareness result is mostly caused by the imperfectness and incompleteness of sensed data, because of this reasons, we must improve the accuracy of context awareness. In this article, we propose a novel approach to model the uncertain context by using ontology and context reasoning method based on Bayesian Network. Our context aware processing is divided into two parts; context modeling and context reasoning. The context modeling is based on ontology for facilitating knowledge reuse and sharing. The ontology facilitates the share and reuse of information over similar domains of not only the logical knowledge but also the uncertain knowledge. Also the ontology can be used to structure learning for Bayesian network. The context reasoning is based on Bayesian Networks for probabilistic inference to solve the uncertain reasoning in context-aware processing problem in a flexible and adaptive situation.

• 한국정보과학회 언어공학연구회:학술대회논문집(한글 및 한국어 정보처리)
• /
• 한국정보과학회언어공학연구회 1997년도 제9회 한글 및 한국어 정보처리 학술대회
• /
• pp.416-420
• /
• 1997

다양한 응용 목적의 대규모 실용적 언어지식 구축을 위해서는 한국어의 모든 언어현상을 수용할 수 있는 이상적인 언어지식(optimal linguistic knowledge) 획득을 목표로 연구해 나가야 한다. 본 연구에서 언어지식의 획득은 주어진 말뭉치의 분석을 통해 이루어진다. 주어진 말뭉치에서 새로운 언어현상이 발견되었을 경우, 기존의 언어지식은 새로운 언어현상을 수용할 뿐만 아니라 기존에 발견되었던 언어현상도 함께 수용할 수 있도록 바뀌어져야 한다. 이러한 변화의 원칙이 보장되어야만 언어지식의 양적 확장과 함께 질적 확장을 이룰 수 있다. 본 연구에서는 언어지식의 질적 확장을 언어지식의 수렴성이라고 정의하고 수렴성 보장을 위한 방법론을 연구한다. 수렴성 보장을 위해서는 먼저 언어지식 획득과정이 공정화, 자동화되어야 하고 언어지식이 변화할 때 수렴을 확인하는 과정이 필요하다. 수렴을 확인하기 위하여 구문구조 데이터베이스와 역사전(Inverted Dictionary)을 이용하는 방법을 제안한다. 지금까지는 언어지식의 양적 확장에만 치중해 왔으나 본 연구에서 제안된 방법으로 언어지식이 구축된다면 질적 확장도 함께 도모할 수 있을 것으로 기대된다.

• 아동학회지
• /
• 제31권6호
• /
• pp.15-34
• /
• 2010

The present study examines the sex differences in 5-year-old preschoolers' aggression according to the type of aggression (overt, relational) and the effect of components of social information processing (SIP : interpretation, goal clarification, response generation, response evaluation) and emotional factors (emotionality, emotional knowledge, emotion regulation) on their aggression. The subjects were 112 5-year-olds (56 boys, 56 girls) and their 11 teachers recruited from 9 day-care centers in Seoul and Kyung-Ki province. Each child's SIP and emotional knowledge were individually assessed with pictorial tasks and teachers reported on children's aggression, emotionality, and emotion regulation by questionnaires. Results indicated that there was a significant sex difference only in the preschoolers' overt aggression. Overtly aggressive response generation in SIP was the strongest predictor of preschoolers' overt aggression while anger of negative emotionality in emotional factors was the strongest predictor of preschoolers' relational aggression.

• 통상정보연구
• /
• 제12권2호
• /
• pp.325-355
• /
• 2010

Knowledge-based exporting companies in Korea have reached a stage to develop new technological innovation and to pioneer new markets. But, developing new technologies and launching new products require an enormous sum of money for Research and Development(R&D) and there is still uncertainty in technological development and markets. Therefore, through open technological innovation, they are encouraged to actively use external technological sources and ideas. They also need to enhance the efficiency of the relatively little R&D investment. In this paper, firstly, it conducts a precedent study on the concept and influence factors of knowledge-based exporting companies and open technological innovation. Secondly, it sets a study model and estimates a regression coefficient to analyze the influence factors of open technological innovation of knowledge-based exporting companies which are using external resources on the process of innovation. Through case study and empirical analysis, we are going to find the implication of open technological innovation and prepare the way of the innovation for the knowledge-based exporting companies. According to the empirical analysis, variables such as firm size, processing degree, product life, patent registration, maintaining internal security didn't have positive effects on open innovation performance. On the other hand, research capability and market preoccupancy had positive effects. Therefore, to succeed in open innovation, knowledge-based exporting companies not only need to secure research capability through open innovation, but also need to preoccupy the market through commercialization of developed product.