• Journal of the Korea Society of Computer and Information
• /
• v.27 no.2
• /
• pp.43-51
• /
• 2022

In this paper, we suggest the method to improve the existing method leaning context-free grammar(CFG) using tabular representation(TBL) as a chromosome of genetic algorithm in grammatical inference and show the more efficient experimental result. We have two improvements. The first is to improve the formula to reflect the learning evaluation of positive and negative examples at the same time for the fitness function. The second is to classify partitions corresponding to TBLs generated from positive learning examples according to the size of the learning string, proceed with the evolution process by class, and adjust the composition ratio according to the success rate to apply the learning method linked to survival in the next generation. These improvements provide better efficiency than the existing method by solving the complexity and difficulty in the crossover and generalization steps between several individuals according to the size of the learning examples. We experiment with the languages proposed in the existing method, and the results show a rather fast generation rate that takes fewer generations to complete learning with the same success rate than the existing method. In the future, this method can be tried for extended CYK, and furthermore, it suggests the possibility of being applied to more complex parsing tables.

• Journal of The Korean Association of Information Education
• /
• v.26 no.3
• /
• pp.197-207
• /
• 2022

In this paper, we develop a machine learning based block code generation and recommendation model for the purpose of reducing cognitive load of learners during coding education that learns the learner's block that has been made in the block programming environment using natural processing model and fine-tuning and then generates and recommends the selectable blocks for the next step. To develop the model, the training dataset was produced by pre-processing 50 block codes that were on the popular block programming language web site 'Entry'. Also, after dividing the pre-processed blocks into training dataset, verification dataset and test dataset, we developed a model that generates block codes based on LSTM, Seq2Seq, and GPT-2 model. In the results of the performance evaluation of the developed model, GPT-2 showed a higher performance than the LSTM and Seq2Seq model in the BLEU and ROUGE scores which measure sentence similarity. The data results generated through the GPT-2 model, show that the performance was relatively similar in the BLEU and ROUGE scores except for the case where the number of blocks was 1 or 17.

• KNOM Review
• /
• v.24 no.1
• /
• pp.29-37
• /
• 2021

With the spread of the Internet, users can easily receive various services and exchange information through the web. There are several requirements for building a web system, and it must be developed using a programming language or platform for user purposes. Residual material information refers to information on medicines and pesticides added to food, and residual material standards are used to measure the level of residues in food produced by companies and farmers to determine whether those levels meet domestic or international standards. Currently, the Ministry of Food and Drug Safety provides residual acceptance standards for food additives, including food, pesticides and animal medicines, in the form of documents, which must be serviced smoothly and conveniently by users through the establishment of a web system. It must also meet a variety of requirements, including user accessibility, such as scalability and compatibility. This paper proposes react-based residual material information web system that allows users to access more conveniently and receive residual material information smoothly. We measured the speed for the three inportant functions of information provision and compared them with existing residual material information web systems and qualitatively evaluated the seven essential requirements: scalability, compatibility, and accessibility.

• Journal of The Korean Association For Science Education
• /
• v.42 no.1
• /
• pp.1-18
• /
• 2022

The two most influential rationales for the 21^st century science curriculum reform can be said to be core competence and scientific literacy. However, the relationship between the two has not been scrutinized but remained speculative - and this has made the harmonization of the general guideline and subject-matter curriculum difficult in Korean national curriculum system. This study compares the two discourses to derive implications for future science curriculum development. This study took a literature research approach. In chapter II, national curriculum or standards, position papers, and research articles were reviewed to delineate the historical development of the discourses. In chapter III and IV, the intersections of those two discourses are delineated. In chapter III, the commonalities of the two discourses are explicated with regard to crisis rhetoric, multi-faceted meanings (individual, community, and global aspects), organization of subject-matter content and teaching and learning method, and the role of high-stake exams. In chapter IV, their respective strengths and weaknesses are juxtaposed. In chapter V, it is suggested that understanding scientific literacy and core competence discourses to have a family resemblance as 21^st century science curriculum reform rationale, after Wittgenstein and Kuhn. Finally, the ways to resolve the conflict between the two ideas from the general guideline and subject-matter curriculum over crisis rhetoric were explored.

• Journal of the Korean Society for Library and Information Science
• /
• v.57 no.1
• /
• pp.93-114
• /
• 2023

Information extraction can facilitate the intensive analysis of documents by providing semantic triples which consist of named entities and their relations recognized in the texts. However, most of the research so far has been carried out separately for named entity recognition and relation extraction as individual studies, and as a result, the effective performance evaluation of the entire information extraction systems was not performed properly. This paper introduces two models of end-to-end information extraction that can extract various entity names in clinical records and their relationships in the form of semantic triples, namely pipeline and joint models and compares their performances in depth. The pipeline model consists of an entity recognition sub-system based on bidirectional GRU-CRFs and a relation extraction module using multiple encoding scheme, whereas the joint model was implemented with a single bidirectional GRU-CRFs equipped with multi-head labeling method. In the experiments using i2b2/VA 2010, the performance of the pipeline model was 5.5% (F-measure) higher. In addition, through a comparative experiment with existing state-of-the-art systems using large-scale neural language models and manually constructed features, the objective performance level of the end-to-end models implemented in this paper could be identified properly.

• Journal of the Korea Society for Simulation
• /
• v.32 no.3
• /
• pp.23-31
• /
• 2023

Software development involves a series of stages, including requirements analysis, design, implementation, unit testing, and integration testing, similar to those used in the system engineering process. This study utilized MathWorks' model-based design platform to develop multi-function radar software and evaluated its feasibility and efficiency. Because the development of conventional radar software is performed by a unit algorithm rather than in an integrated form, it requires additional efforts to manage the integrated software, such as requirement analysis and integrated testing. The mode-based platform applied in this paper provides an integrated development environment for requirements analysis and allocation, algorithm development through simulation, automatic code generation for deployment, and integrated requirements testing, and result management. With the platform, we developed multi-level models of the multi-function radar software, verified them using test harnesses, managed requirements, and transformed them into hardware deployable language using the auto code generation tool. We expect this Model-based integrated development to reduce errors from miscommunication or other human factors and save on the development schedule and cost.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.22 no.2
• /
• pp.195-211
• /
• 2023

For the commercialization For the commercialization of autonomous vehicles (AV), the operational design domain (ODD) of automated driving systems (ADS) is to be clearly defined. A common language and consistent format must be prepared so that AV-related stakeholders can understand ODD at the same level. Therefore, overseas countries are presenting a standardized ODD framework and developing scenarios that can evaluate ADS-specific functions based on ODD. However, ODD includes conditions reflecting the characteristics of each country, such as road environment, weather environment, and traffic environment. Thus, it is necessary to clearly understand the meaning of the items defined overseas and to harmonize them to reflect the specific domestic conditions. Therefore, in this study, domestic optimization of the ODD classification system was performed by analyzing the domestic driving environment based on international standards. The driving environment of currently operating self-driving car test districts (Sangam, Seoul, and Gwangju) was investigated using the developed domestic ODD items. Then, based on the results obtained, the ranges of the ODDs in each test district were determined and compared.

• Journal of Intelligence and Information Systems
• /
• v.29 no.2
• /
• pp.219-240
• /
• 2023

Conversational AI which allows users to interact with satisfaction is a long-standing research topic. To develop conversational AI, it is necessary to build training data that reflects real conversations between people, but current Korean datasets are not in question-answer format or use honorifics, making it difficult for users to feel closeness. In this paper, we propose a conversation dataset (KOMUChat) consisting of 30,767 question-answer sentence pairs collected from online communities. The question-answer pairs were collected from post titles and first comments of love and relationship counsel boards used by men and women. In addition, we removed abuse records through automatic and manual cleansing to build high quality dataset. To verify the validity of KOMUChat, we compared and analyzed the result of generative language model learning KOMUChat and benchmark dataset. The results showed that our dataset outperformed the benchmark dataset in terms of answer appropriateness, user satisfaction, and fulfillment of conversational AI goals. The dataset is the largest open-source single turn text data presented so far and it has the significance of building a more friendly Korean dataset by reflecting the text styles of the online community.

• Journal of Christian Education in Korea
• /
• v.72
• /
• pp.147-164
• /
• 2022

Stories have been studied as an important educational method in Christian education. In recent discussions on religious education, stories are positively evaluated in terms of stimulating children's unique fantasy, as opposed to visual media, and in terms of face-to-face direct communication. Our most profound and passionate orientation to the world is shaped by stories. This is because stories move us by moving us and shape our unconscious to act accordingly. However, the subjects that supply stories to children now are various mass media and consumer culture. The story it tells instills a secular worldview and makes us dream of a world completely different from the kingdom of God. Our children need a story to imagine the kingdom of God. This paper focuses on story-style sermons in children's worship and tries to deal with the Christian educational implications of story-style sermons. To this end, first of all, I would like to treat the Bible as a story according to the approximate concept of the story and the position of literary criticism who approached the Bible as a story. The second will deal with narrative preaching. First, we will look at narrative sermons for adults, and then deal with narrative sermons for children. The two narrative sermons were treated separately in the sense of considering the characteristics of children rather than being separated. Lastly, I would like to draw out the Christian educational implications of narrative preaching.

• Communications of Mathematical Education
• /
• v.37 no.1
• /
• pp.1-19
• /
• 2023

Mathematics Listening Ability(MLA) refers to the ability to listen to and grasp the meaning of speech language containing mathematical concepts and principles, distinguishing it from daily life and listening in other subject classes. According to literature, MLA might be divided into six types. Among them, interpretation, discovering, evaluating, and evaluation may indicate an attitude that correctly listens to the meaning of the language used in mathematics classes. On the other hand, selective, pretend, and ignore are types of listening attitudes that are not appropriate. Based on the statistical analysis of 834 3rd to 6th graders and a total of 44 homeroom teachers I developed a MLA survey items for elementary school students. In this study, principal component analysis was conducted to verify reliability in the development of survey items, and expert review and correlation analysis of survey results were conducted to verify validity. In addition, the validity was verified by statistically analyzing the survey results of students and their homeroom teachers. Based on literature and statistical analysis, I developed a MLA Survey items(for students) consisting of 25 questions and a mathematical resolution measurement tool(for teachers) consisting of 26 questions.