• Convergence Security Journal
• /
• v.22 no.5
• /
• pp.107-113
• /
• 2022

The AR/VR-based education and training system is expected to contribute greatly to accident prevention and budget reduction as well as practical training effects similar to the battlefield environment. Research to use AR/VR for learning is ongoing, and technology can be improved without experiencing failures that can occur in the real world. Major advanced countries in defense recognized the advantages of AR/VR technology early on, and developed and utilized systems using them in various fields, from mastery of individual weapon system operation to comprehensive combat training systems, war history education, and post-traumatic stress treatment. Therefore, the purpose of this study is to examine the cases of AR/VR application education and training in advanced defense countries and to draw implications for the South Korean military.

• Journal of The Korean Society of Integrative Medicine
• /
• v.12 no.2
• /
• pp.111-119
• /
• 2024

Purpose : This study aimed to demonstrate the effects of visiting cognitive activities using brain training on cognition, subjective memory complaints and depression among elderly participants residing in community living in Gwangmyeong city. Methods : Over a 14-month period (October 2022 to December 2023), four brain training instructors visited the homes of older adults and conducted the intervention using a brain training kit. The participants included 32 elderly individuals aged 65 years and older, who were living in Gwangmyeong city. The assessments were conducted by an occupational therapist, a nurse and a social worker at the Gwangmyeong dementia relief center. These assessments included the following the subjective memory complaints questionnaire (SMCQ), short geriatric depression scale-Korean (SGDS-K), a cognitive impairment screening test (CIST), the consortium to establish a registry for Alzheimer's disease-Korean (CERAD-K). The participants were divided into three groups (A: 20-30 points, B: 10-19 points, C: 1-9 points) based on the CIST score. For data analysis, descriptive statistics and wilcoxon signed-rank test were performed using SPSS 24.0, and the statistical level was at a=.05. Results : The results of the intervention showed that the SMCQ score of group A improved significantly (p<.05), the CIST score of group B also improved significantly (p<.05). However, the SGDS-K score of group C improved, but did not demonstrate statistical significance (p=.080). Conclusion : The visiting cognitive activities using brain training produced significant effects on cognition, depression, and subjective memory disorders, depending on the cognitive level of the elderly participants. In the future, it will be necessary to demonstrate the effects according to cognitive level in various aspects with more elderly people.

• Journal of Korea Multimedia Society
• /
• v.25 no.11
• /
• pp.1643-1652
• /
• 2022

Most of the existing machine reading research has used Recurrent Neural Network (RNN) and Convolutional Neural Network (CNN) algorithms as networks. Among them, RNN was slow in training, and Question Answering Network (QANet) was announced to improve training speed. QANet is a model composed of CNN and self-attention. CNN extracts semantic and syntactic information well from the local corpus, but there is a limit to extracting the corresponding information from the global corpus. Graph Convolutional Networks (GCN) extracts semantic and syntactic information relatively well from the global corpus. In this paper, to take advantage of this strength of GCN, we propose I-QANet, which changed the CNN of QANet to GCN. The proposed model performed 1.2 times faster than the baseline in the Stanford Question Answering Dataset (SQuAD) dataset and showed 0.2% higher performance in Exact Match (EM) and 0.7% higher in F1. Furthermore, in the Korean Question Answering Dataset (KorQuAD) dataset consisting only of Korean, the learning time was 1.1 times faster than the baseline, and the EM and F1 performance were also 0.9% and 0.7% higher, respectively.

• Journal of the Korea Convergence Society
• /
• v.8 no.10
• /
• pp.9-17
• /
• 2017

The current study attempted to develop and operate an exercise prescription expert system based on cloud computing. Recently, concerns on health are increasing due to the development of healthcare technology, increased life expectancy, and enhanced concerns on the body figure and wellbeing among Koreans. This trend pushes up the demand for the personal trainers and exercise specialists. However, supply of the exercise specialists are less than the demand. This study tries to develop exercise prescription system, aggregate diverse data, develop artificial intelligence rule, and operate exercise prescription expert system and education system. This system may assist training exercise professionals by replacing off-line training programs into on-line training programs. Further researches are recommended to connect diverse IoT devices and big data.

• Journal of the Korea Convergence Society
• /
• v.6 no.5
• /
• pp.241-248
• /
• 2015

Nursing clinical practice, especially because it is required to reproduce this fusion education is very urgent. This Study was done to examine the effect of action learning techniques in simulation class. The study was designed using a nonequivalent control group pretest-posttest design. The participants consisted of control group 92, experimental group 92. The data analyzed using SPSS 18.0 program. Professional self-concept are higher than in the control group were measured.(t=-5.118, p=>.001). communication competence and self-directed learning capability of experimental group increased significantly from those control group. This result means that can help to significantly improve the professional nursing students learning techniques to simulate the application of an action class. In other words, if the act of creative training techniques such as future action learning hands-on training to be a big help.

• Journal of the Korea Convergence Society
• /
• v.12 no.10
• /
• pp.265-275
• /
• 2021

The purpose of this study was to examine the effect of educational environment on satisfaction among trainees of beauty vocational training institutions. By examining the literature of previous studies, the research model and research hypothesis were established, and empirical analysis was conducted through questionnaires to establish theoretical concepts and identify variables of the educational environment to verify the effects on trainee satisfaction. A questionnaire was collected from 180 beauty trainees in Gyeong-gi, Seoul, and the collected data was analyzed using AMOS 22.0. As a result of this study, first, it was found that the educational environment had a significant positive effect on the NCS education method and instructor competency. Second, the NCS education method had a negative effect on the trainee satisfaction. Third, it was found that the instructor's competency had a significant positive effect on the satisfaction of trainees. Based on the study results, implications and limitations were presented.

• The Journal of Korea Robotics Society
• /
• v.12 no.3
• /
• pp.356-364
• /
• 2017

This paper presents a force control based on the observer without taking any force or torque measurement from the robot which allows realizing more stable and robust human robot interaction for the developed multi-functional upper limb rehabilitation robot. The robot has four functional training modes which can be classified by the human robot interaction types: passive, active, assistive, and resistive mode. The proposed observer consists of internal disturbance observer and external force observer for distinctive performance evaluation. Since four training modes can be quantitatively identified as impedance variation, position-based impedance control with feedback and feedforward controller was applied to the assistive training mode. The results showed that the proposed sensorless observer estimated cleaner and more accurate force compared to the force sensor and the impedance controller embedded with the proposed observer completed the assistive training mode safely and properly.

• Journal of Korean Clinical Health Science
• /
• v.9 no.2
• /
• pp.1520-1525
• /
• 2021

Purpose. This study conducted visual function training for children under 12 years of age who relapsed after surgery for intermittent exotropia. We are trying to find out whether the visual function has been improved by visual function training. Methods. After surgery, the subject with recurrent exotropia was given a prescription for refractive error, followed by visual function training and vision therapy with visual sence using prisms and lenses. Results. The subjects' positive relative convergence improved to 19.69𝚫, corrected visual acuity improved to 0.88, and stereoscopic vision function improved to 53.08 arc second. It was found that the smaller the angle of deviation at the time of recurrence after surgery, the better the vision therapy effect. Conclusions. It can be seen that visual function training is helpful in improving visual function, and the importance of visual function training can be known.

• International Journal of Contents
• /
• v.14 no.4
• /
• pp.24-29
• /
• 2018

EEG-based brain-computer interfaces has focused on explicitly expressed intentions to assist physically impaired patients. For EEG-based-computer interfaces to function effectively, it should be able to understand users' implicit information. Since it is hard to gather EEG signals of human brains, we do not have enough training data which are essential for proper classification performance of implicit intention. In this paper, we improve the subject independent classification of implicit intention through the generation of additional training data. In the first stage, we perform the PCA (principal component analysis) of training data in a bid to remove redundant components in the components within the input data. After the dimension reduction by PCA, we train ICA (independent component analysis) network whose outputs are statistically independent. We can get additional training data by adding Gaussian noises to ICA outputs and projecting them to input data domain. Through simulations with EEG data provided by CNSL, KAIST, we improve the classification performance from 65.05% to 66.69% with Gamma components. The proposed sample generation method can be applied to any machine learning problem with fewer samples.

• Journal of information and communication convergence engineering
• /
• v.19 no.4
• /
• pp.228-233
• /
• 2021

In this study, we analyze the credit information (loan, delinquency information, etc.) of individual business owners to generate voluminous training data to establish a bankruptcy prediction model through a partial synthetic training technique. Furthermore, we evaluate the prediction performance of the newly generated data compared to the actual data. When using conditional tabular generative adversarial networks (CTGAN)-based training data generated by the experimental results (a logistic regression task), the recall is improved by 1.75 times compared to that obtained using the actual data. The probability that both the actual and generated data are sampled over an identical distribution is verified to be much higher than 80%. Providing artificial intelligence training data through data synthesis in the fields of credit rating and default risk prediction of individual businesses, which have not been relatively active in research, promotes further in-depth research efforts focused on utilizing such methods.