• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.15 no.12
• /
• pp.4308-4325
• /
• 2021

The importance and necessity of artificial intelligence, particularly machine learning, has recently been emphasized. In fact, artificial intelligence, such as intelligent surveillance cameras and other security systems, is used to solve various problems or provide convenience, providing solutions to problems that humans traditionally had to manually deal with one at a time. Among them, information security is one of the domains where the use of artificial intelligence is especially needed because the frequency of occurrence and processing capacity of dangerous codes exceeds the capabilities of humans. Therefore, this study intends to examine the definition of artificial intelligence and machine learning, its execution method, process, learning algorithm, and cases of utilization in various domains, particularly the cases and contents of artificial intelligence technology used in the field of information security. Based on this, this study proposes a method to apply machine learning technology to the method of classifying and detecting malware that has rapidly increased in recent years. The proposed methodology converts software programs containing malicious codes into images and creates training data suitable for machine learning by preparing data and augmenting the dataset. The model trained using the images created in this manner is expected to be effective in classifying and detecting malware.

• ETRI Journal
• /
• v.36 no.3
• /
• pp.429-438
• /
• 2014

Semantic role labeling (SRL) is a task in natural-language processing with the aim of detecting predicates in the text, choosing their correct senses, identifying their associated arguments, and predicting the semantic roles of the arguments. Developing a high-performance SRL system for a domain requires manually annotated training data of large size in the same domain. However, such SRL training data of sufficient size is available only for a few domains. Constructing SRL training data for a new domain is very expensive. Therefore, domain adaptation in SRL can be regarded as an important problem. In this paper, we show that domain adaptation for SRL systems can achieve state-of-the-art performance when based on structural learning and exploiting a prior model approach. We provide experimental results with three different target domains showing that our method is effective even if training data of small size is available for the target domains. According to experimentations, our proposed method outperforms those of other research works by about 2% to 5% in F-score.

• Communications of Mathematical Education
• /
• v.26 no.1
• /
• pp.109-135
• /
• 2012

On the standards or elements of teaching evaluation, the Korea Institute of Curriculum and Evaluation(KICE) has carried out the following research such as : 1) development of the standards on teaching evaluation between 2004 and 2006, and 2) investigation on the elements of Teacher Knowledge. The purposes of development of evaluation standards for mathematics teaching through those studies were to improve not only mathematics teachers' professionalism but also their own teaching methods or strategies. In this study, the standards were revised and modified by analyzing the results of those studies focused on the knowledge of subject matter knowledge, knowledge of learners' understanding, teaching and learning methods and assessments, and teaching contexts. For this purpose, the part of subject matter knowledge was consisted of four evaluation domains such as the knowledge of curriculum reconstruction, knowledge of mathematical contents, methodological knowledge, mathematical value. The part of Learners' unders tanding included the evaluation domains such as students' intellectual and achievement level, students' misconception in math, students' motivation on learning, students' attitude on mathematics learning, and students' learning strategies. The part of teaching methods and evaluation was consisted of seventh evaluation domains such as instruction involving instructional goal and content, instruction involving problem-solving activity, instruction involving learners' achievement level and attitude, instruction on communication skills, planning of assessment method and procedure, development on assessment tool, application on assessment result in class were new established. Also, the part of teaching context was consisted of four evaluation domains such as application of instructional tools and materials, commercial manipulatives, environment of classroom including distribution and control of class group, atmosphere of classroom, management of teaching contexts including management of student. According to those evaluation domains of each teacher knowledge, elements on teaching evaluation focused on the teacher's knowledge were established using the instructional evaluation framework, which is developed in this study, including the four areas of obtaining, planning, acting, and reflecting.

• Journal of Korea Society of Industrial Information Systems
• /
• v.29 no.3
• /
• pp.79-87
• /
• 2024

Recently, the importance of pre-trained language models (PLM) has been emphasized for natural language processing (NLP) such as text classification, sentiment analysis, and question answering. Korean PLM shows high performance in NLP in general-purpose domains, but is weak in domains such as finance, medicine, and law. The main goal of this study is to propose a language model learning process and method to build a financial-specific language model that shows good performance not only in the financial domain but also in general-purpose domains. The five steps of the financial-specific language model are (1) financial data collection and preprocessing, (2) selection of model architecture such as PLM or foundation model, (3) domain data learning and instruction tuning, (4) model verification and evaluation, and (5) model deployment and utilization. Through this, a method for constructing pre-learning data that takes advantage of the characteristics of the financial domain and an efficient LLM training method, adaptive learning and instruction tuning techniques, were presented.

• Journal of Digital Convergence
• /
• v.16 no.3
• /
• pp.59-73
• /
• 2018

The purpose of this study is to verify the learning effect of domestic flipped learning in meta - analysis. We collected a total of 95 studies on flipped learning effectiveness published in Korea by 2017, of which 59 are dissertations and thesis and 36 are academic papers. The results were analyzed using CMA program. First, the learning effect of flipped learning was .58, which showed that the learning effect was higher than the lecture class. Second, the effect size of cognitive, affirmative, and interpersonal domains showed significant effects of flipped learning in all three domains. Third, the learning effect of flipped learning is influenced by the type of publishing, school type, core subject, when the type of publication are dissertation and thesis, when the type of school is high school. Based on the results, this study suggested implications for the design and implementation of flipped learning in Korea.

• Journal of Korean Academy of Fundamentals of Nursing
• /
• v.12 no.3
• /
• pp.278-283
• /
• 2005

Purpose: The purpose of this study was to compare changes in learning objectives in Fundamentals of Nursing which were established between 2000 and 2004. Method: 2000, 2004 learning objectives were analyzed with frequencies and percents. Results: There was an increase in the total number of learning objectives used in 2004(n=534) over 2000(n=527). In 2004 compared to 2000, there was an increase in learning objectives related to nursing process, need of oxygenation, need of nutrition, need of temperature regulation, need of activity and exercise, need of comfort, medication, preoperative care. According to Bloom's taxonomy, learning objectives established in 2004, mainly consisted of three domains, 35.5% for comprehension, 23.6% for synthesis, 20.4% for knowledge Changes in learning objectives established in 2004 compared to 2000 decreases in the comprehension domain and increases in the synthesis domain. Conclusion: The learning objectives established in 2004 showed remarkable change when compared to those established in 2000. But the learning objective domains in Bloom's taxonomy were distributed unevenly. For better learning objectives in Fundamentals of Nursing, constant revision will be needed.

• Journal of Korea Multimedia Society
• /
• v.25 no.6
• /
• pp.819-832
• /
• 2022

Cross-domain recommender system transfers knowledge across different domains to improve the recommendation performance in a target domain that has a relatively sparse model. However, they suffer from the "negative transfer" in which transferred knowledge operates as noise. This paper proposes a novel Multiple Fusion-based Deep Cross-Domain Recommendation named MFDCR. We exploit Doc2Vec, one of the famous word embedding techniques, to fuse data user-wise and transfer knowledge across multi-domains. It alleviates the "negative transfer" problem. Additionally, we introduce a simple multi-layer perception to learn the user-item interactions and predict the possibility of preferring items by users. Extensive experiments with three domain datasets from one of the most famous services Amazon demonstrate that MFDCR outperforms recent single and cross-domain recommendation algorithms. Furthermore, experimental results show that MFDCR can address the problem of "negative transfer" and improve recommendation performance for multiple domains simultaneously. In addition, we show that our approach is efficient in extending toward more domains.

• Hwankyungkyoyuk
• /
• v.12 no.1
• /
• pp.294-310
• /
• 1999

Firstly, the goals and the domains of contents of environmental education was classified in order to systematize the contents of environmental education which would be taught in each subject. According to these goals and domains of contents, the contents of 10 subjects (Korean Language, Ethics, Social Studies, Mathematics, Science, Music, Arts, Physical Practicum(Technology and Heme Economics), English were analyzed. The norms in the analysis of the goals of environmental education by each subject were 4 domains: information and knowledge, skills, value & attitudes, & action and participation. The norms in the analysis of the contents of environmental education by each subject were 11 domains: natural environment, artificial environment, population, industrialization/urbanization, resources, environmental pollution, environmental preservation and measures, environmental sanitation, environmental ethics, environmentally sound and sustainable development(ESSD), and sound consumption life. As a result, it was found that all the 4 domains of goals in environmental education could come true. Furthermore, the goals of environmental education were found to be reached in the subjects of Korean Language, Music, Arts, Physical Education, Mathematics, English, etc., which had been thought to have nothing to do with environmental education. It was also found that the contents of each subject could deal with its own unique environmental contents. The result of this study can keep all subject from overlapping in environmental contents, and can make the most of each subject’s characteristics. Also, the result of this study will be referenced in developing the teaching and learning materials for environmental education according to each subject.

• Korean Educational Research Journal
• /
• v.43 no.1
• /
• pp.125-152
• /
• 2022

The purpose of this study is to examine the differences of perceptions of teachers and students regarding teaching skills. For the analysis, data was collected by ICALT(International Comparative Analysis of Learning and Teaching) class observation tool and students survey called My Teacher Questionnaire. a student survey. The data of teachers and students can be compared because as the two tools have seven common domains(Safe and stimulating learning climate, Efficient organization, Clear and structured instructions, Intensive and activating teaching, Adjusting instructions and learner processing to inter-learner differences, Teaching learning strategies, Learner engagement). In 2016, in Daejeon, Chungbuk and Chungnam. trained teachers collected data from 106 classes, and 2,866 students responded the survey. The reliability and validity of the two tools, class observation and MTQ(My Teacher Questionnaire) are proven to be satisfactory for use in Korean schools. Students perception on teaching was high, particularly when students are in lower grades and learning major subjects like English, Korean, and math. The domain of higher teaching skills, male students show higher perceptions while female students reported higher perceptions on lower-level teaching skill domains. To compare the perceptions of teachers and students, the predictive reliability of students engagement against teaching skill domains was used. Teachers showed higher predictive reliability on lower teaching skill domains while students showed higher predictive reliability on higher teaching skill domains. It is recommended for further study to develop a professional development model using a teacher class observation tool and the My Teacher Questionnaire for pre-service teachers and school teachers.

• Journal of Korea Multimedia Society
• /
• v.10 no.6
• /
• pp.754-759
• /
• 2007

Methodology of ontology building based on Web resources will not only reduce significantly the ontology construction period, but also enhance the quality of the ontology. Remarkable progress has been achieved in this regard, but they encounter similar difficulties, such as the Web data extraction and knowledge acquisition. This paper researches on the characteristics of ontology construction data, including dynamics, largeness, variation and openness and other features, and the fundamental issue of ontology construction - formalized representation method. Then, the key technologies used in and the difficulties with ontology construction are summarized. A software Model-OntoMaker (Ontology Maker) is designed. The model is innovative in two regards: (1) the improvement of generality: the meta learning machine will dynamically pick appropriate ontology learning methodologies for data of different domains, thus optimizing the results; (2) the merged processing of (semi-) structural and non-structural data. In addition, as known to all wetland researchers, information sharing is vital to wetland exploitation and protection, while wetland ontology construction is the basic task for information sharing. OntoMaker constructs the wetland ontologies, and the model in this work can also be referred to other environmental domains.