• Journal of Korean Association for Spatial Structures
• /
• v.23 no.2
• /
• pp.29-36
• /
• 2023

Reinforcement learning (RL) is widely applied to various engineering fields. Especially, RL has shown successful performance for control problems, such as vehicles, robotics, and active structural control system. However, little research on application of RL to optimal structural design has conducted to date. In this study, the possibility of application of RL to structural design of reinforced concrete (RC) beam was investigated. The example of RC beam structural design problem introduced in previous study was used for comparative study. Deep q-network (DQN) is a famous RL algorithm presenting good performance in the discrete action space and thus it was used in this study. The action of DQN agent is required to represent design variables of RC beam. However, the number of design variables of RC beam is too many to represent by the action of conventional DQN. To solve this problem, multi-agent DQN was used in this study. For more effective reinforcement learning process, DDQN (Double Q-Learning) that is an advanced version of a conventional DQN was employed. The multi-agent of DDQN was trained for optimal structural design of RC beam to satisfy American Concrete Institute (318) without any hand-labeled dataset. Five agents of DDQN provides actions for beam with, beam depth, main rebar size, number of main rebar, and shear stirrup size, respectively. Five agents of DDQN were trained for 10,000 episodes and the performance of the multi-agent of DDQN was evaluated with 100 test design cases. This study shows that the multi-agent DDQN algorithm can provide successfully structural design results of RC beam.

• Journal of the Korean Chemical Society
• /
• v.67 no.4
• /
• pp.241-252
• /
• 2023

This study aims to increase students' understanding of equilibrium, one of the many concepts in chemistry that students find difficult. Dynamic equilibrium must be dealt with at the sub-microscopic level where the real and the representation overlap in order to microscopically understand the constant motion and interaction of particles and to understand the macroscopic characteristics expressed through this. However, as a result of analyzing 9 Chemistry I textbooks, the expression approach for equilibrium had some limitations. As a strategy to understand equilibrium at a sub-microscopic approach, the classes using scratch were consisted of a total of 4 hours, and it was implemented with 56 students. The classes were composed of 6 steps, and it was designed to understand equilibrium step by step. As a result of comparing the pretest and post- test, the number of students who got both the microscopic and macroscopic explanations of chemical equilibrium correct increased largely. Through this, it was possible to get a glimpse of the applicability of classes using scratch as the approach strategy of the sub-microscopic representation.

• Journal of Creative Information Culture
• /
• v.5 no.3
• /
• pp.237-243
• /
• 2019

The ability of problem-solving, communicating, and collaborating with computing technology is considered as core competencies for future society. In order to improve those competences, the algorithm and programming ability was set as the important goal of the Information curriculum of Korea. Algorithmic thinking is a key component of computing thinking, and it is known to play a very important role in designing and programming algorithms. It is used to set goals of Information curriculum and to measure student achievement. Therefore, in this study, developed a test to measure algorithmic thinking of students in elementary, middle and high schools, and applied the test to measure the levels of algorithmic thinking. As a result of the analysis, the higher the school level, the better the algorithmic thinking. And no difference was found between genders. This study is expected to provide a guide for constructing measures or setting the difficulty level for algorithmic thinking.

• The Journal of the Convergence on Culture Technology
• /
• v.9 no.1
• /
• pp.119-128
• /
• 2023

This study was conducted to present an alternative instructional model through natural experience activities by developing a natural experience activity program that can learn and feel how to recognize and act on nature based on flow learning. In order to achieve the purpose of the study, a nature experience program, which consists of four stages of meeting nature, exploring nature, playing with nature and sharing emotions, was developed based on the main procedures of each stage of the ADDlE instructional design model. Through the research process, activities and precautions for each stage of the nature experience activity program were presented, and major educational implications were discussed based on the developed program. The nature experience program developed through the study can provide teachers with a basic direction for nature experience activities along with changing their perception of how to do nature experience activities, and infants are expected to become learners who freely feel, experience nature and make up their own knowledge through the nature experience program.

• Journal of the Institute of Convergence Signal Processing
• /
• v.23 no.2
• /
• pp.70-75
• /
• 2022

With the spread of various digital devices, devices have become commonplace in modern society. Moreover, due to the increase in device usage and online learning while staying indoors during the COVID-19 pandemic, symptoms such as an increase in myopia in children due to eye fatigue, an increase in young presbyopia, and dry eye syndrome are increasing, and now people are paying attention to eye health. This is different from before. There are various prescriptions for eye health, but in this paper, we would like to propose a training method for enhancing visual function using VR contents. The analog methods of the existing teaching aids for visual function reinforcement training were planned and produced as digital contents, and VR-based training contents were selected from among the various methods carried out with teaching aids at the visual function training center, which can be made into contents. was developed with In the training process for each content, it was proposed to apply eye tracking to the VR device in order to give the user feedback on their participation in the training so that the management and concentration of the training process could be analyzed.

• Journal of the Korea Convergence Society
• /
• v.13 no.1
• /
• pp.141-147
• /
• 2022

In a broad sense, the definition of digital health care is an industrial area that manages personal health and diseases through the convergence of the health care industry and ICT. In a narrow sense, various medical technologies are used to manage medical services to improve patient health. This paper aims to provide design guidelines so that artificial intelligence technology can be applied stably and efficiently to more diverse digital health care fields in the future by introducing use cases of artificial intelligence and machine learning techniques applied in the digital health care field. For this purpose, in this thesis, the medical field and the daily life field are divided and examined. The two regions have different data characteristics. By further subdividing the two areas, we looked at the use cases of artificial intelligence algorithms according to data characteristics and problem definitions and characteristics. Through this, we will increase our understanding of artificial intelligence technologies used in the digital health care field and examine the possibility of using various artificial intelligence technologies.

• Asia-pacific Journal of Multimedia Services Convergent with Art, Humanities, and Sociology
• /
• v.7 no.3
• /
• pp.889-899
• /
• 2017

Various efforts and technical development for integrating the ICT technologies to the area of special needs education have been continuing. In this paper we have studied and implemented various ICT-based disability evaluation websites and mobile applications for special needs education and also verified their usefulness from the field test at disability schools. The valuer can access the websites and mobile applications for autistic behavior or learning disability evaluation at the any places and by any devices such as laptop, PC, smartphone and tablet PC. And all the evalation results are stored into and managed at the server database and shared with websites and mobile applications to integrate together easily. From the study about disability evaluation and implementation results we have a confidence that they will be useful to support the seamless evaluation and the continuous monitoring services for the disabled at the special needs education fields.

• Journal of the Korean Society for information Management
• /
• v.40 no.2
• /
• pp.33-57
• /
• 2023

This study aims to analyze students' information needs and information-seeking behavior at science schools for gifted through in-depth interviews. The research design was conducted based on previous studies. Through in-depth interviews, this study examined ten students from six out of eight science schools for the gifted in Korea for information needs and overall information-seeking behavior. The results showed the information needs of students at science schools for gifted in the areas of curricular and extracurricular activities as well as the information-seeking behavior in teaching, learning, and research activities, which were the main topics of interest to students based on the ISP model. Based on these results, we identified the preferred information sources in the information-seeking process and discussed the peculiarities and implications of students' information-seeking behavior. The research is meaningful as it can be used as a basis for further research on the science school for gifted library and as a resource for providing services for students with deep interests and talents in science subject areas.

• Journal of Powder Materials
• /
• v.30 no.3
• /
• pp.217-222
• /
• 2023

Machine learning-based data analysis approaches have been employed to overcome the limitations in accurately analyzing data and to predict the results of the design of Nb-based superalloys. In this study, a database containing the composition of the alloying elements and their room-temperature tensile strengths was prepared based on a previous study. After computing the correlation between the tensile strength at room temperature and the composition, a material science analysis was conducted on the elements with high correlation coefficients. These alloying elements were found to have a significant effect on the variation in the tensile strength of Nb-based alloys at room temperature. Through this process, a model was derived to predict the properties using four machine learning algorithms. The Bayesian ridge regression algorithm proved to be the optimal model when Y, Sc, W, Cr, Mo, Sn, and Ti were used as input features. This study demonstrates the successful application of machine learning techniques to effectively analyze data and predict outcomes, thereby providing valuable insights into the design of Nb-based superalloys.

• Education of Primary School Mathematics
• /
• v.26 no.1
• /
• pp.29-43
• /
• 2023

The purpose of this study was to synthesize intervention studies, which utilized single case experimental design, on teaching mathematical word problems for elementary school students with disabilities and evaluate each of their methodological rigor. The researchers reviewed all studies from 2000 to 2022 that involved teaching mathematical word problems to individuals with disabilities. A total of 12 studies was included for a final analysis. Most of the interventions were delivered by researchers for about 30-40 minutes per session to elementary school students with disabilities. Schema-based instruction, cognitive-metacognitive strategy, and technology-based instruction were used as intervention methods, and explicit instruction was mostly used in conjunction with them. On the other hand, the researchers found that none of research articles met quality indicators for single case experimental design according to Cook et al. (2015). Limitation and directions for future research were also discussed.