• 한국지능시스템학회:학술대회논문집
• /
• 한국퍼지및지능시스템학회 2003년도 ISIS 2003
• /
• pp.447-450
• /
• 2003

In this research, we propose an automatic knowledge acquisition and composite knowledge expression mechanism based on machine learning and relational database. Most of traditional approaches to develop a knowledge base and inference engine of expert systems were based on IF-THEN rules, AND-OR graph, Semantic networks, and Frame separately. However, there are some limitations such as automatic knowledge acquisition, complicate knowledge expression, expansibility of knowledge base, speed of inference, and hierarchies among rules. To overcome these limitations, many of researchers tried to develop an automatic knowledge acquisition, composite knowledge expression, and fast inference method. As a result, the adaptability of the expert systems was improved rapidly. Nonetheless, they didn't suggest a hybrid and generalized solution to support the entire process of development of expert systems. Our proposed mechanism has five advantages empirically. First, it could extract the specific domain knowledge from incomplete database based on machine learning algorithm. Second, this mechanism could reduce the number of rules efficiently according to the rule extraction mechanism used in machine learning. Third, our proposed mechanism could expand the knowledge base unlimitedly by using relational database. Fourth, the backward inference engine developed in this study, could manipulate the knowledge base stored in relational database rapidly. Therefore, the speed of inference is faster than traditional text -oriented inference mechanism. Fifth, our composite knowledge expression mechanism could reflect the traditional knowledge expression method such as IF-THEN rules, AND-OR graph, and Relationship matrix simultaneously. To validate the inference ability of our system, a real data set was adopted from a clinical diagnosis classifying the dermatology disease.

• 농촌지도와개발
• /
• 제16권1호
• /
• pp.153-180
• /
• 2009

The previous researches about knowledge sharing were proceeded in terms of KMS (Knowledge Management System) in center. However, knowledge sharing is recently applied to Internet space, which is open to every users, as well as KMS, which is qualified for restricted people. For example, some portal sites, such as Naver, the most popular portal in Korea, have virtual spaces to share users' knowledges and it is common that many users use the spaces. Knowledge sharing online, compared with KMS, will be more advanced to promote intention for knowledge sharing because of the character of Internet space that is open to all users. Nevertheless, there are few researches about knowledge sharing in the Internet. Considering this situation, this study is attempted to figure out the factors to promote Internet knowledge sharing, based on social capital theory and self-expression concept. A survey of experienced Internet user and PLS (Partial Least Square) were utilized for analysis. The test of this study reveals that social capital and self-expression are significant factors to influence knowledge sharing intention, and that also personal innovation and self-efficacy are significantly related to the self-expression. However, personal innovation does not have significant impact on social capital. According to the result, self-expression, as well as trust and system itself, has significantly effect on knowledge sharing intention in order to promote knowledge sharing in the Internet.

• 한국정밀공학회:학술대회논문집
• /
• 한국정밀공학회 2003년도 춘계학술대회 논문집
• /
• pp.1-4
• /
• 2003

Knowledge classification and expression of constructed knowledge have been main research issues in the field of knowledge representation. Constructed design knowledge of the former product loses its utility when new products with different structures are introduced to the market. In order to construct the design knowledge for a new product. designers need to reconstruct the design knowledge with new relationships. The design knowledge has been constructed with level trees, but it is difficult to rearrange the relations. Design DNA is proposed in this work in order to facilitate the rearrangement of design knowledge and give flexibility to knowledge structure. Design DNA is based on Layout-oriented domain knowledge and Function-oriented domain knowledge, which enables to generate new design knowledge that will result in new part geometries for given constraints on the part functions. Design DNA is applied to the design knowledge of lever system of the automatic transmission of passenger cars as an example.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2003년도 ICCAS
• /
• pp.1338-1343
• /
• 2003

Data is the expression of the language or numerical values that show some characteristics. And information is extracted from data for the specific purposes. The knowledge is utilized as information to construct rules that recognize patterns and make decisions. Today, knowledge extraction and application of the knowledge are broadly accomplished to improve the comprehension and to elevate the performance of systems in several industrial fields. The knowledge extraction could be achieved by some steps that include the knowledge acquisition, expression, and implementation. Such extracted knowledge can be drawn by rules. Clustering (CU, input space partition (ISP), neuro-fuzzy (NF), neural network (NN), extension matrix (EM), etc. are employed for expression the knowledge by rules. In this paper, the various approaches of the knowledge extraction are examined by categories that separate the methods by the applied industrial fields. Also, the several test data and the experimental results are compared and analysed based upon the applied techniques that include CL, ISP, NF, NN, EM, and so on.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• 제3권2호
• /
• pp.194-199
• /
• 2003

Data are an expression of the language or numerical values that show some features. And the information is extracted from data for the specific purposes. The knowledge is utilized as information to construct rules that recognize patterns or make a decision. Today, knowledge extraction and application of that are broadly accomplished for the easy comprehension and the performance improvement of systems in the several industrial fields. The knowledge extraction can be achieved by some steps that include the knowledge acquisition, expression, and implementation. Such extracted knowledge is drawn by rules with data mining techniques. Clustering (CL), input space partition (ISP), neuro-fuzzy (NF), neural network (NN), extension matrix (EM), etc. are employed for the knowledge expression based upon rules. In this paper, the various approaches of the knowledge extraction are surveyed and categorized by methodologies and applied industrial fields. Also, the trend and examples of each approaches are shown in the tables and graphes using the categories such as CL, ISP, NF, NN, EM, and so on.

• Genomics & Informatics
• /
• 제6권4호
• /
• pp.202-209
• /
• 2008

Biological pathways are known as collections of knowledge of certain biological processes. Although knowledge about a pathway is quite significant to further analysis, it covers only tiny portion of genes that exists. In this paper, we suggest a model to extend each individual pathway using a microarray expression data based on the known knowledge about the pathway. We take the Rosetta compendium dataset to extend pathways of Saccharomyces cerevisiae obtained from KEGG (Kyoto Encyclopedia of genes and genomes) database. Before applying our model, we verify the underlying assumption that microarray data reflect the interactive knowledge from pathway, and we evaluate our scoring system by introducing performance function. In the last step, we validate proposed candidates with the help of another type of biological information. We introduced a pathway extending model using its intrinsic structure and microarray expression data. The model provides the suitable candidate genes for each single biological pathway to extend it.

• 한국생산제조학회지
• /
• 제26권3호
• /
• pp.328-336
• /
• 2017

The exit surface of a lens is designed using a three-dimensional free-form expression in order to easily modify a curved surface. This enables the design of numerical values and mathematical things using three-dimensional free-form expression, and enhances precision because it can be fine-tuned via numerical control. The standard of "Classification of Luminaire Light Distribution" for outdoor lighting fixtures by IESNA is adopted in order to examine the correlation between three-dimensional free-form surface expression and lighting performance. The variation of light distribution type and range is analyzed using the values of maximum light intensity and 50% light intensity. The actual tolerance occurs owing to parameters such as the thickness of the lens, the distance between LEDs, and the movement of the center of the incident surface; the effects of changes in these parameters on the performance are compared and analyzed.

• 지식경영연구
• /
• 제18권3호
• /
• pp.147-162
• /
• 2017

As social media started to work as important communication tools, social media users have tried to manage their image, identity, and impression through social media. Social media service providers have been interested in providing various functions effectively disclosing users' emotion, such as posting, commenting, and sharing content; on the other hand, relatively few efforts have been made to provide social media functions for information suppression. In this study, therefore, we attempt to examine the relationship between Facebook users' personality and impression management behaviors. Personal traits of users including public self-consciousness, positive self-expression, and honest self-expression were considered as independent variables. Impression management behaviors are composed of two variables, which are suppression and projection. The survey was conducted, targeting 230 Facebook users. The research findings show that public self-consciousness and positive self-expression are positively associated with information suppression while both positive and honest self-expression is positively associated with information projection.

• 한국콘텐츠학회논문지
• /
• 제22권7호
• /
• pp.486-497
• /
• 2022

본 연구의 목적은 대학 글쓰기 수업에서 내용지식으로부터 학생의 통합지식을 구성함에 있어 지식통합의 단위와 기준을 세분화하여 제시하는 것이다. 이를 위하여 전형성 있는 대학 글쓰기 교재 세 권을 분석하고 내용지식의 구성에 대한 제시방법을 텍스트 질적 분석방법을 통해 살폈다. 분석 절차와 제시방법은 Creswell의 질적 연구에서의 나선형 분석 모델을 따랐다. 이는 자료 수집부터 분석, 제시까지 순환적으로 반복되는 자료 분석 방법이다. 이를 통해 내용지식 구성단위에는 글 전체 단위, 단락 단위, 문장 단위의 세 가지 차원이 있음을 발견하였다. 또한 내용지식 구성의 체계화된 교육을 위해서 이 세 가지 단위 차원을 모두 다루는 것이 바람직함을 제시하였다. 다음으로 지식통합의 과정별 기준과 교육내용을 제안하였다. 지식의 선별 과정에서는 논지와의 적합성과 보충성의 기준을, 지식의 조직과 통합과정에서는 통일적 통합, 모순적 통합, 배경적 통합, 종합적 통합 등의 기준과 내용을, 지식의 표현과 인용 과정에서는 정확한 표현과 표기법, 출처표시 등의 절차 지식을 제안하였다. 나아가 표현의 차원에서 일반 글쓰기 교재에서 빈번하게 연습되는 '바꿔 말하기' 과정도 '요약, 연계, 해석과 변용'이라는 세 가지 차원에서 연습될 필요가 있음을 제안하였다. 그러나 이러한 결과는 몇 차례 더 세분화의 과정을 거쳐야 대학 수준의 글쓰기 교재에 활용하기 적합하고 체계화된 지식통합의 요목들을 정련할 수 있을 것으로 보이며 이를 추후 연구의 과제로 남긴다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제17권11호
• /
• pp.2903-2923
• /
• 2023

Knowledge recommendation is a type of recommendation system that recommends knowledge content to users in order to satisfy their needs. Although using graph neural networks to extract data features is an effective method for solving the recommendation problem, there is information loss when modeling real-world problems because an edge in a graph structure can only be associated with two nodes. Because one super-edge in the hypergraph structure can be connected with several nodes and the effectiveness of knowledge graph for knowledge expression, a dual-channel hypergraph convolutional neural network model (DCHC) based on hypergraph structure and knowledge graph is proposed. The model divides user data and knowledge data into user subhypergraph and knowledge subhypergraph, respectively, and extracts user data features by dual-channel hypergraph convolution and knowledge data features by combining with knowledge graph technology, and finally generates recommendation results based on the obtained user embedding and knowledge embedding. The performance of DCHC model is higher than the comparative model under AUC and F1 evaluation indicators, comparative experiments with the baseline also demonstrate the validity of DCHC model.