• Journal of The Korean Association of Information Education
• /
• v.14 no.3
• /
• pp.427-435
• /
• 2010

As the e-Learning plays an increasingly larger important part in education and has been increased as an alternative to offline education, academic organizations are moving ahead to set guidelines for quality assurance in e-Learning. And various quality assurance techniques in e-Learning have been developed because the e-Learning does not always match well traditional models of teaching and learning, much care needs to be taken in the design, creation and implementation of service. But the present quality assurances in e-Learning which are focused in learning objects have much problems because they use partial and static management. In this thesis we suggested dynamic quality assurance using CLD(Causal Loop Diagram) in e-Learning. The suggested method has more efficiency than existing methods and it can provide important strategies with regard to administrative issues in e-Learning.

• Asian Pacific Journal of Cancer Prevention
• /
• v.15 no.14
• /
• pp.5607-5609
• /
• 2014

Introduction: Although continuing education is necessary for practicing nurses, it is very difficult to organize traditional classes because of large numbers of nurses and working shifts. Considering the increasing development of mobile electronic learning, we carried out a study to compare effects of the traditional face to face method with mobile learning delivered as text messages by cell phone. Materials and Methods: Sixty female nurses working in our hospital were randomly divided into class and short message service (SMS) groups. Lessons concerning breast cancer screening were prepared as 54 messages and sent in 17 days for the SMS group, while the class group participated in a class held by a university lecturer of breast and cancer surgery. Pre- and post-tests were undertaken for both groups at the same time; a retention test also was performed one month later. For statistical analysis, the paired T test and the independent sample T test were used with SPSS software version 16; p<0.05 was considered significant. Results: Mean age and mean work experience of participants in class and SMS groups was $35.8{\pm}7.2$, $9.8{\pm}6.7$, $35.4{\pm}7.3$, and $11.5{\pm}8.5$, respectively. There was a significant increase in mean score post-tests (compared with pretests) in both groups (p<0.05). Although a better improvement in scores of retention tests was demonstrated in the SMS group, the mean subtraction value of the post- and pretests as well as retention- and pretests showed no significant difference between the 2 groups (p=0.3 and p =0.2, respectively). Conclusions: Our study shows that teaching via SMS may probably replace traditional face to face teaching for continuing education in working nurses. Larger studies are suggested to confirm this.

• Journal of the Korea Convergence Society
• /
• v.9 no.12
• /
• pp.47-52
• /
• 2018

Named Entity Recognition is a system that extracts entity names such as Persons(PS), Locations(LC), and Organizations(OG) that can have a unique meaning from a document and determines the categories of extracted entity names. Recently, Bi-LSTM-CRF, which is a combination of CRF using the transition probability between output data from LSTM-based Bi-LSTM model considering forward and backward directions of input data, showed excellent performance in the study of object name recognition using deep-learning, and it has a good performance on the efficient embedding vector creation by character and word unit and the model using CNN and LSTM. In this research, we describe the Bi-LSTM-CNN-CRF model that enhances the features of the Korean named entity recognition system and propose a method for constructing the traditional culture corpus. We also present the results of learning the constructed corpus with the feature augmentation model for the recognition of Korean object names.

• Journal of Korea Foundry Society
• /
• v.42 no.4
• /
• pp.209-217
• /
• 2022

In the present study, in order to prevent the misrun defects that occur during traditional brass casting, a method for selecting the proper casting process conditions is proposed. A learning model was developed and demonstrated to be able to learn the presence or absence of defects according to the casting process conditions and to predict the occurrence of defects depending on the certain process given. Appropriate process conditions were determined by applying the proposed method, and the determined conditions were verified through a comparison of different simulation results with additional conditions. With this method, it is possible to determine the casting process conditions that will prevent defects in the desired sand model. This technology is expected to contribute to realization of smart traditional brass farming workshops.

• Journal of The Korean Society of Agricultural Engineers
• /
• v.66 no.4
• /
• pp.27-39
• /
• 2024

Soil texture is determined by the proportions of sand, silt, and clay within the soil, which influence characteristics such as porosity, water retention capacity, electrical conductivity (EC), and pH. Traditional classification of soil texture requires significant sample preparation including oven drying to remove organic matter and moisture, a process that is both time-consuming and costly. This study aims to explore an alternative method by developing an AI model capable of predicting soil texture from images of pre-sorted soil samples using computer vision and deep learning technologies. Soil samples collected from agricultural fields were pre-processed using sieve analysis and the images of each sample were acquired in a controlled studio environment using a smartphone camera. Color distribution ratios based on RGB values of the images were analyzed using the OpenCV library in Python. A convolutional neural network (CNN) model, built on PyTorch, was enhanced using Digital Image Processing (DIP) techniques and then trained across nine distinct conditions to evaluate its robustness and accuracy. The model has achieved an accuracy of over 80% in classifying the images of pre-sorted soil samples, as validated by the components of the confusion matrix and measurements of the F1 score, demonstrating its potential to replace traditional experimental methods for soil texture classification. By utilizing an easily accessible tool, significant time and cost savings can be expected compared to traditional methods.

• The Korean Journal of Applied Statistics
• /
• v.32 no.1
• /
• pp.41-68
• /
• 2019

Multi-view learning considers data from various viewpoints as well as attempts to integrate various information from data. Multi-view learning has been studied recently and has showed superior performance to a model learned from only a single view. With the introduction of deep learning techniques to a multi-view learning approach, it has showed good results in various fields such as image, text, voice, and video. In this study, we introduce how multi-view learning methods solve various problems faced in human behavior recognition, medical areas, information retrieval and facial expression recognition. In addition, we review data integration principles of multi-view learning methods by classifying traditional multi-view learning methods into data integration, classifiers integration, and representation integration. Finally, we examine how CNN, RNN, RBM, Autoencoder, and GAN, which are commonly used among various deep learning methods, are applied to multi-view learning algorithms. We categorize CNN and RNN-based learning methods as supervised learning, and RBM, Autoencoder, and GAN-based learning methods as unsupervised learning.

• Journal of Practical Engineering Education
• /
• v.15 no.1
• /
• pp.39-44
• /
• 2023

With the development of e-learning teaching methods, the demand for blended learning, which combines face-to-face education and e-learning, is increasing, and it shows a learning effect that can replace the existing face-to-face class. Engineering subjects have various learning activities such as practice, so it is not easy to operate them with traditional blended learning. Therefore, a different teaching and learning design is required according to the learning activities required for the subject. In this paper, examples of teaching method design and operation for blended learning in engineering subjects were introduced, and their effects investigated and analyzed. Learning activities were subdivided into theoretical classes, practical classes, quizzes and Q&A, assignments and solutions, and teaching and learning methods such as online videos, LMS utilization, and face-to-face classes were applied according to learning activities. According to the results of the student satisfaction survey, blended learning showed higher satisfaction than pure online and face-to-face classes in engineering subjects, and showed differentiated satisfaction for each learning activity.

• Journal of The Korean Association of Information Education
• /
• v.9 no.2
• /
• pp.309-318
• /
• 2005

e-learning has been recently introduced in all educational domains and it has expanded rapidly in educational field. Blended learning, which has emerged with e-learning nowadays, is an exact example of a new paradigm. It has not only educational effects of traditional classroom learning, but it also has effects of e-learning which provides learner-centered classroom environment and removes barriers of time and space. This study looked into several e-learning contents evaluation criteria that were already studied, And arranged with the evaluation question item that can evaluate learning effectiveness of e-learning contents in elementary school through a questionnaire executed in elementary school teachers. And it used this evaluation question item and the study accomplishment results of an education ruler, and applied to learning effectiveness evaluation of e-learning contents. This paper will give future directions and assessment criteria of e-learning. Moreover, this thesis will provide theoretical and practical materials for developing e-learning contents to improve quality of blended learning.

• Journal of the Korean earth science society
• /
• v.25 no.2
• /
• pp.63-73
• /
• 2004

This study investigated the effect of cooperative learning on the middle school students’ conceptual change of atmospheric and water cycle and also examined the verbal interaction patterns in a cooperative group. The study also analyzed the relationship between the verbal interaction and students’ conceptual change in the cooperative learning situation. Two classes from a middle school were selected as an experimental group (cooperative learning group, n = 37) and a control group (traditional learning group, n = 37), respectively. The experimental group was taught by STAD cooperative learning model and received collaborative skill training. The results of the study can be summarized as follows: first, there were no significant differences in conceptual change between the two groups. As for the middle-achieving students on the pretest, however, the score of the cooperative learning group was significantly higher than that of the traditional learning group. Secondly, verbal interaction in the cooperative learning situation mainly happened among high- and middle achieving students. In addition, the students who were successful in undergoing conceptual change had more frequent verbal interactions than the students who were not. The study suggests that it is more important to interact between a teacher and students than to interact between the students and students in order to correct students’ misconception.

• Journal of Convergence for Information Technology
• /
• v.9 no.6
• /
• pp.44-51
• /
• 2019

This study was performed to explore the difference in communication anxiety and class satisfaction after taking the traditional lecture and flipped learning lecture. Fifty four nursing students participated in this study. The study design was one group pretest-posttest design. 4 weeks traditional lecture and 4 weeks flipped learning lecture was applied. Flipped learning was ineffective in improving communication anxiety (t=1.85, p=.069) of nursing students. But emotional state variables and activity variables in the emotional domain were significantly higher after taking the flipped learning lecture(t=-3.80, p=.000; t=-3.35, p=.001). In addition, all of the variables were higher in the flipped learning based team, in the control of the class activities (t=-3.07, p=.003), personal ability (t=-2.48, p=.016), and class participation(t=-3.25, p=.002). Flipped learning is therefore considered to be effective in training nursing students. This study suggested to investigate the effectiveness of flipped learning and learners' satisfaction.