• Journal of the Korea Convergence Society
• /
• v.10 no.4
• /
• pp.73-80
• /
• 2019

The purpose of this study was to examine how flipped learning strategy affects learners' self-regulating ability in both general English and Spanish, based on the study hypothesis that self-regulating learning ability of general English learners will make a meaningful difference in comparison to that of traditional learning. The study was also focused on how flipped learning was related to learners' self-regulating ability. From September 10, 2018 to December 10, 2018, a total of 81 students in general English and Spanish were surveyed in which three sub areas of self-regulating learning (cognitive, motivational, and behavioral control) were considered, and which were divided into six sub-domains, a total of 65 items were composed. Although not very significant results were shown in the case of motivational control, both English and Spanish classes have statistically significant differences in cognitive and behavioral self-regulating learning abilities.

• Journal of Korea Multimedia Society
• /
• v.23 no.1
• /
• pp.31-42
• /
• 2020

During the 4th Industrial Revolution, service platforms utilizing diverse contents are emerging, and research on recommended systems that can be customized to users to provide quality service is being conducted. hybrid recommendation systems that provide high accuracy recommendations are being researched in various domains, and various filtering techniques, machine learning, and deep learning are being applied to recommended systems. However, in a recommended service environment where data must be analyzed and processed real time, the accuracy of the recommendation is important, but the computational speed is also very important. Due to high level of model complexity, a hybrid recommendation system or a Deep Learning-based recommendation system takes a long time to calculate. In this paper, a Cascade-hybrid recommended algorithm is proposed that can reduce the computational time while maintaining the accuracy of the recommendation. The proposed algorithm was designed to reduce the complexity of the model and minimize the computational speed while processing sequentially, rather than using existing weights or using a hybrid recommendation technique handled in parallel. Therefore, through the algorithms in this paper, contents can be analyzed and recommended effectively and real time through services such as SNS environments or shared economy platforms.

• Journal of Multimedia Information System
• /
• v.6 no.4
• /
• pp.225-234
• /
• 2019

Deep learning has become increasingly popular in both academic and industrial areas nowadays. Various domains including pattern recognition, Computer vision have witnessed the great power of deep neural networks. However, current studies on deep learning mainly focus on quality data sets with balanced class labels, while training on bad and imbalanced data set have been providing great challenges for classification tasks. We propose in this paper a method of data analysis-based data reduction techniques for selecting good and diversity data samples from a large dataset for a deep learning model. Furthermore, data sampling techniques could be applied to decrease the large size of raw data by retrieving its useful knowledge as representatives. Therefore, instead of dealing with large size of raw data, we can use some data reduction techniques to sample data without losing important information. We group PCB characters in classes and train deep learning on the ResNet56 v2 and SENet model in order to improve the classification performance of optical character recognition (OCR) character classifier.

• International Journal of Internet, Broadcasting and Communication
• /
• v.14 no.4
• /
• pp.58-63
• /
• 2022

Recently, the improvement of computational processing ability due to the rapid development of computing technology has greatly advanced the field of artificial intelligence, and research to apply it in various domains is active. In particular, in the national defense field, attention is paid to intelligent recognition among machine learning techniques, and efforts are being made to develop object identification and monitoring systems using artificial intelligence. To this end, various image processing technologies and object identification algorithms are applied to create a model that can identify friendly and enemy weapon systems and personnel in real-time. In this paper, we conducted image processing and object identification focused on tanks among various weapon systems. We initially conducted processing the tanks' image using a convolutional neural network, a deep learning technique. The feature map was examined and the important characteristics of the tanks crucial for learning were derived. Then, using YOLOv5 Network, a CNN-based object detection network, a model trained by labeling the entire tank and a model trained by labeling only the turret of the tank were created and the results were compared. The model and labeling technique we proposed in this paper can more accurately identify the type of tank and contribute to the intelligent recognition system to be developed in the future.

• International Journal of Computer Science & Network Security
• /
• v.23 no.10
• /
• pp.115-128
• /
• 2023

Deep learning has been incorporating various optimization techniques motivated by new pragmatic optimizing algorithm advancements and their usage has a central role in Machine learning. In recent past, new avatars of various optimizers are being put into practice and their suitability and applicability has been reported on various domains. The resurgence of novelty starts from Stochastic Gradient Descent to convex and non-convex and derivative-free approaches. In the contemporary of these horizons of optimizers, choosing a best-fit or appropriate optimizer is an important consideration in deep learning theme as these working-horse engines determines the final performance predicted by the model. Moreover with increasing number of deep layers tantamount higher complexity with hyper-parameter tuning and consequently need to delve for a befitting optimizer. We empirically examine most popular and widely used optimizers on various data sets and networks-like MNIST and GAN plus others. The pragmatic comparison focuses on their similarities, differences and possibilities of their suitability for a given application. Additionally, the recent optimizer variants are highlighted with their subtlety. The article emphasizes on their critical role and pinpoints buttress options while choosing among them.

• Journal of the Architectural Institute of Korea Planning & Design
• /
• v.34 no.3
• /
• pp.61-72
• /
• 2018

This study pursued to obtain 3 consecutive purposes. First, a conceptual model for comparing 3 constructivist teaching and learning strategies( problem-based learning[$P_bBL$], case-based learning[CBL] and project-based learning[$P_jBL$]) was developed. Relationships of these constructivist strategies with the development of expertise for learners were discussed. Second, specific differences between $P_bBL$, CBL and $P_jBL$ as applied in architectural design courses were analyzed under each of the teaching and learning category. Some analytical indexes were developed by content analysis, which are applicable effectively to reveal the differences. Based on the previous findings, third, a set of strategic guidelines for use in class were made and suggested in order to develop and improve expertise in architectural design. These guidelines were largely targeted for university design courses as well as education or reeducation of practicing architects. Expecially, combined application of $P_bBL$, CBL and $P_jBL$ was hypothesized and suggested as class management guidelines. In sum, a variety of $P_bBL$ problems, CBL cases and $P_jBL$ projects should be developed for expecting audience based on design subjects and tasks. As working domains of practicing architects, exploring/analyzing, understanding/making applications, and criticizing/self-reflecting should be considered in the development process.

• The Transactions of the Korea Information Processing Society
• /
• v.13 no.2
• /
• pp.76-90
• /
• 2024

Although artificial intelligence (AI) can be utilized in various domains such as smart city, healthcare, it is limited due to concerns about the exposure of personal and sensitive information. In response, the concept of distributed machine learning has emerged, wherein learning occurs locally before training a global model, mitigating the concentration of data on a central server. However, overall learning phase in a collaborative way among multiple participants poses threats to data privacy. In this paper, we systematically analyzes recent trends in privacy protection within the realm of distributed machine learning, considering factors such as the presence of a central server, distribution environment of the training datasets, and performance variations among participants. In particular, we focus on key distributed machine learning techniques, including horizontal federated learning, vertical federated learning, and swarm learning. We examine privacy protection mechanisms within these techniques and explores potential directions for future research.

• Child Health Nursing Research
• /
• v.12 no.3
• /
• pp.405-416
• /
• 2006

Purpose: The purpose of this study was to explore health behavior and perception of therapeutic restrictions in chronically ill children and their parents in Korea. Method: Nine children with chronic disease and of six of their parents were interviewed using semi-structured a questionnaire. The data were analyzed using explorative content analysis. Results: Health behaviors related to therapeutic restrictions was classified into four domains, and the perceptions of therapeutic restrictions into two domains. The domains regarding compliance in health behavior with therapeutic restrictions included control-centered restrictions (maintaining food limitations, avoiding harmful environments, restriction on physical activity, restriction on social activity, restriction on learning activity), and everyday pursuit of balance(preference for healthy diet, maintaining a regular life style, maintaining a standard body weight, pursuing psychological well-being, family participation). Domains regarding perception of therapeutic restrictions included obstacles to growth and development (bridled life, opportunity deprivation, prevented from playing proper role), origin of conflict (tenacity, conflict, stressor, cover-up), task for normal life (doing proper duty), and everyday affairs (becoming ordinary, familiarity). Conclusion: This study will help to enhance understanding the behavior and perception of therapeutic restrictions by chronically ill children and their families and to establish educational programs and counseling for these children and their families.

• Communications of Mathematical Education
• /
• v.24 no.3
• /
• pp.503-523
• /
• 2010

The current mathematics curriculum are consist of the following domains: 'Characteristics', 'Objectives', 'Contents', 'Teaching and learning method', and 'Assessment'. The mathematics standards which students have to learn in the school are presented in the domain of 'Contents'. 'Contents' are consist of the following sub-domains: 'Number and Operation', 'Geometric Figures', 'Measures', 'Probability and Statistics', and 'Pattern and Problem-Solving' (Elementary School); 'Number and Operation', 'Geometry', 'Letter and Formula', 'Function', and 'Probability and Statistics' (Junior and Senior High School). These sub-domains of 'Contents' are dealing with mathematical subjects, except 'Problem-Solving' at the elementary school level. In this study, the sub-domain of 'mathematical process' was suggested in an equal position to the typical sub-domains of 'Contents'.

• Journal of The Korean Association For Science Education
• /
• v.37 no.4
• /
• pp.599-609
• /
• 2017

The goal of this research is to analyze the trend of Korean fourth grade students' achievement in TIMSS 2011 and TIMSS 2015 science content domains and to suggest implications for science curriculum and teaching & learning improvement. With four elementary science teachers and three science educators, we analyzed Korean fourth grade students' percentage of correct responses in TIMSS 2015 science content and cognitive domains, and conducted item-curriculum matching analysis for test items. According to the results, Korean students performed relatively better in test topics covered in the science curriculum for 3-4 grades regardless of the science content domain (i.e., Life science, Physical science, or Earth science). Korean students showed low percentage of correct answers for items related to such topics as heat conduction, the action of electricity, the motion of the earth and the moon, etc., which were covered in the 5th-6th grades in the 2009 revised curriculum. For science cognitive domains, Korean students' achievement dropped significantly in reasoning between TIMSS 2011 and TIMSS 2015. Discussed in the conclusion are implications to reconstruct elementary school science curriculum, and ways to improve science teaching and learning.