• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2001년도 ICCAS
• /
• pp.173.5-173
• /
• 2001

Q-Learning is a most widely used reinforcement learning, which addresses the question of how an autonomous agent can learn to choose optimal actions to achieve its goal about any one problem. Q-Learning can acquire optimal control strategies from delayed rewards, even when the agent has no prior knowledge of the effects of its action in the environment. If agent has an ability using previous knowledge, then it is expected that the agent can speed up learning by interacting with environment. We present a novel reinforcement learning method using domain knowledge, which is represented by problem-independent features and their classifiers. Here neural network are implied as knowledge classifiers. To show that an agent using domain knowledge can have better performance than the agent with standard Q-Learner. Computer simulations are ...

• East Asian mathematical journal
• /
• 제35권4호
• /
• pp.451-465
• /
• 2019

Textbooks are official materials so that these are the most frequently used teaching materials in school. The teacher constructs the lesson based on the contents of the textbook to achieve the learning goal. Thus, textbooks play an important role because the quality of the contents in textbooks affects the cognitive level of students. This study investigates the cognitive domain based on Bloom's Taxonomy of Educational Objectives(knowledge, understanding, application, analysis, synthesis and evaluation) of 'Values and Expression' in the mathematics textbook of the first grade of middle school reflecting the 2015 revised mathematics curriculum. We also looked at cognitive levels based on Bloom's Taxonomy of Educational Objectives. As a result, it was found that understanding was dominant in 'Values and Expression'. Also, although the problem of requiring a higher level of cognition is increasing as the unit finishes, there are still a high percentage of low level of problems.

• International journal of advanced smart convergence
• /
• 제12권3호
• /
• pp.75-88
• /
• 2023

In a specific domain, experts have different understanding of domain knowledge or different purpose of constructing ontology. These will lead to multiple different ontologies in the domain. This phenomenon is called the ontology heterogeneity. For research fields that require cross-ontology operations such as knowledge fusion and knowledge reasoning, the ontology heterogeneity has caused certain difficulties for research. In this paper, we propose a novel ontology matching model that combines word embedding and a concatenated continuous bag-of-words model. Our goal is to improve word vectors and distinguish the semantic similarity and descriptive associations. Moreover, we make the most of textual and structural information from the ontology and external resources. We represent the ontology as a graph and use the SimRank algorithm to calculate the structural similarity. Our approach employs a similarity queue to achieve one-to-many matching results which provide a wider range of insights for subsequent mining and analysis. This enhances and refines the methodology used in ontology matching.

• 한국수학교육학회지시리즈A:수학교육
• /
• 제50권3호
• /
• pp.367-381
• /
• 2011

It is important to concern about individual difference on every subject and every class. How can we know the individual difference? It is helpful for that to find out students' math learning style and learning type. In this paper, I conducted a survey to look for math learning style and math learning type of 4th, 5th and 6th grade students, and analyzed those data. The research findings are summarized as follows; First, 4th, 5th and 6th grade students prefer the visual learning style to the verbal style, and they have more wholistic tendency than analytical tendency in the domain of the cognitive learning style. Second, they prefer the authoritative and goal-oriented learning style to the practical and recreational learning style, and they have more interior-oriented than exterior-oriented in the domain of affective learning style. Third, the representative math learning type of 4th, 5th and 6th grade students is visual/holistic/authoritative and goal-oriented/interior-oriented. The math learning styles of students have a lot of influence on their learning, so that an appropriate teaching method for each student could arouse a maximum effect in the math study.

• 한국콘텐츠학회논문지
• /
• 제11권4호
• /
• pp.312-320
• /
• 2011

이 논문에서는 일개 POC(Point Of Care) 시스템을 사용하는 의료기관을 중심으로 의약품 처방조제지원 시스템(Clinical Decision Support System, CDSS)과 조직성과와의 관계를 규명하는 것에 목적을 두고 있다. 이를 위하여 정보시스템 평가요소에 대해 정의를 내리고, CDSS의 성과 평가 모형을 제시하여 설문조사 분석을 통해 의약품 처방조제지원시스템의 도입 효과를 밝히고자 하였다. 분석결과 시스템 품질을 제외하고는 각 평가 영역들 사이에 인과성이 존재하는 것으로 분석되었으며, 통계적으로 유의하게 지지되는 것으로 분석되었다. 평가모형 검증결과 의약품처방최적화를 위한 CDSS의 시스템 품질이 사용자 만족도에 영향을 미친다는 근거를 발견할 수 없었다. 그러나 정보품질이 사용자의 만족도에 긍정적인 영향을 미치며 사용자 만족은 조직성과에 긍정적인 영향을 미치는 것으로 나타났다.

• 전자통신동향분석
• /
• 제34권4호
• /
• pp.55-64
• /
• 2019

In this study, we introduce trends in neural-network-based deep learning research applied to dialogue systems. Recently, end-to-end trainable goal-oriented dialogue systems using long short-term memory, sequence-to-sequence models, among others, have been studied to overcome the difficulties of domain adaptation and error recognition and recovery in traditional pipeline goal-oriented dialogue systems. In addition, some research has been conducted on applying reinforcement learning to end-to-end trainable goal-oriented dialogue systems to learn dialogue strategies that do not appear in training corpora. Recent neural network models for end-to-end trainable chit-chat systems have been improved using dialogue context as well as personal and topic information to produce a more natural human conversation. Unlike previous studies that have applied different approaches to goal-oriented dialogue systems and chit-chat systems respectively, recent studies have attempted to apply end-to-end trainable approaches based on deep neural networks in common to them. Acquiring dialogue corpora for training is now necessary. Therefore, future research will focus on easily and cheaply acquiring dialogue corpora and training with small annotated dialogue corpora and/or large raw dialogues.

• 한국초등과학교육학회지:초등과학교육
• /
• 제19권2호
• /
• pp.29-41
• /
• 2000

The purpose of this study is to examine the effects of the Portfolio applied science instruction on the students' scientific affective domain and perceptions of portfolio in elementary schools. Portfolio applied science instruction of the 6th grade science unit 'Environment pollution and Nature protection' was developed for this study. Traditional instruction was implemented to the control group and portfolio applied science instruction was implemented to the experimental group. Pretests of the scientific affective domain were administered to both groups. The treatment was given for about seven weeks for both groups. Instruments about scientific affective domain were administered to both groups. A questionnaire on perception of portfolio applied science instruction was given to the experimental group after the treatment. The results were analyzed using t-test on the students' scientific affective domain. The results of this study are as follows: 1. Portfolio applied science instruction program for elementary schools was developed. Students themselves determine the portfolio learning goal in a portfolio applied science instruction. Students construct the portfolio and they evaluate themselves and other colleagues. Also teachers go on portfolio applied science instruction considering portfolio purpose, concepts, evaluation. 2. There was not a statistically meaningful difference between an experimental group and a control group o]1 the students' scientific affective domain. In three sub categories of a scientific affective domain, the science perception, the interest on science and scientific attitude, there were not statistically meaningful difference among them. 3. As the results of the questionnaire on perceptions of portfolio, they didn't understand it very well but after learning portfolio, they showed positive attitude to perceptions of portfolio. Students in portfolio applied science instruction like more the portfolio applied science instruction than general instruction. 4. Portfolio applied science instruction has an useful value as a method of teaching and evaluation. Students and teachers can produce various portfolios products in portfolio applied science instruction. As a conclusion, portfolio applied science instruction was not statistically meaningful on the students' scientific affective domain, but it gives positive effects on perceptions of portfolio in elementary schools. Therefore, portfolio has an educational value as a method of teaching and evaluation for students' growth. In the future, teachers and students must have interaction and feedback in portfolio applied science instruction.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제12권3호
• /
• pp.1205-1223
• /
• 2018

Image enhancement is an emerging method for analyzing the images clearer for interpretation and analysis in the spatial domain. The goal of image enhancement is to serve an input image so that the resultant image is more suited to the particular application. In this paper, a novel method is proposed based on Mamdani fuzzy inference system (FIS) using multiple fuzzy membership functions. It is observed that the shape of membership function while converting the input image into the fuzzy domain is the essential important selection. Then, a set of fuzzy If-Then rule base in fuzzy domain gives the best result in image contrast enhancement. Based on a different combination of membership function shapes, a best predictive solution can be determined which can be suitable for different types of the input image as per application requirements. Our result analysis shows that the quality attributes such as PSNR, Index of Fuzziness (IOF) parameters give different performances with a selection of numbers and different sized membership function in the fuzzy domain. To get more insight, an optimization algorithm is proposed to identify the best combination of the fuzzy membership function for best image contrast enhancement.

• 한국정보시스템학회지:정보시스템연구
• /
• 제7권1호
• /
• pp.181-208
• /
• 1998

In many literatures of model management, various schemes for representing model base schema have proposed. Ultimately, the goal is to arrive at a set of mutually supportive and synergistic methodologies and tools for the modeling problem domain and model base design. This paper focus on how best to structure and represent conceptual model of problem domain and schema of model base. Semantic concepts and modeling constructs are valuable conceptual tools for understanding the structural relationships and constraints involved in an model management environment. To this end, we reviewed the model management literature, and analyzed the constructs of modeling tools of data model management graph-based approach. Although they have good tools but most of them are not enough for the representation of structural relationships and constraints. So we wanted more powerful tools which can represent diverse constructs in a decision support modeling and model base schema design. For the design of a model base, we developed object modeling framework which uses Object Modeling Techniques (OMT). In Object Modeling Framework, model base schema are classified into conceptual schema, logical schema, and physical schema. The conceptual schema represents the user's view of problem domain, and the logical schema represents a model formatted by a particular modeling language. The schema design, this paper proposes an extension of Object Model to overcome some of the limitations exhibited by the OMT. The proposed tool, Extended Object Model(EOM) have diverse constructs for the representation of decision support problem domain and conceptual model base schema.

• 방송공학회논문지
• /
• 제24권1호
• /
• pp.48-57
• /
• 2019

본 연구는 목적 지향 대화 시스템 내에서 단일 한국어 텍스트 형식의 질문으로부터 질의자의 의도를 파악하는 것을 목적으로 한다. 목적 지향 대화 시스템은 텍스트 또는 음성을 통한 사용자의 특수한 요구를 만족시켜주는 대화 시스템을 의미한다. 의도 분석 과정은 답변 생성에 앞서 사용자의 질의 의도를 파악하는 단계로, 목적 지향 대화 시스템 전체의 성능에 큰 영향을 준다. 생활화학제품이라는 특정 분야에 제안 모델을 사용하였고, 해당 분야와 관련된 한국어 텍스트 데이터를 이용하였다. 특정 분야에 독립적이며 범용적인 의도를 의미하는 화행과, 특정 분야에 종속적인 의도를 의미하는 개념열로 나누어 분석한다. 화행과 개념열을 분석하기 위하여 단어 임베딩 모델, 합성곱 신경망을 이용한 분류 방법을 제안한다. 단어 임베딩 모델을 통하여 단어의 의미정보를 추상화하고, 추상화된 단어의 의미정보를 기반으로 합성곱 신경망을 통하여 개념열 및 화행 분류를 수행한다.