• The Journal of the Korea Contents Association
• /
• v.10 no.3
• /
• pp.463-471
• /
• 2010

The purpose of this study is to articulate learning model based on achievement level in blended learning environment. In order to investigate the variables and mechanisms in the blended learning environment, we started by attempt to develop two questionnaires using the components of web-based instruction and self-regulated learning. And its results were implemented to represent the topology and directed merging path within components. 154 students at a high school were required to take each web course respectively for two weeks. And questionnaires data, achievement levels data were collected and analyzed. Various statistical analysis methods such as correlation analysis, classical multidimensional scaling, multiple regression analysis, were applied to the data. As an result, the topology and directed path within factors of blended learning process were derived and revised as a final model.

• International Journal of Internet, Broadcasting and Communication
• /
• v.16 no.3
• /
• pp.262-273
• /
• 2024

We provide a detailed analysis of the data processing and model training process for vulnerability classification using Transformer-based language models, especially sentence text-to-text transformers (ST5)-XXL and XLNet. The main purpose of this study is to compare the performance of the two models, identify the strengths and weaknesses of each, and determine the optimal learning rate to increase the efficiency and stability of model training. We performed data preprocessing, constructed and trained models, and evaluated performance based on data sets with various characteristics. We confirmed that the XLNet model showed excellent performance at learning rates of 1e-05 and 1e-04 and had a significantly lower loss value than the ST5-XXL model. This indicates that XLNet is more efficient for learning. Additionally, we confirmed in our study that learning rate has a significant impact on model performance. The results of the study highlight the usefulness of ST5-XXL and XLNet models in the task of classifying security vulnerabilities and highlight the importance of setting an appropriate learning rate. Future research should include more comprehensive analyzes using diverse data sets and additional models.

• Journal of KIBIM
• /
• v.13 no.3
• /
• pp.12-20
• /
• 2023

Deep learning-based anomaly detection technology is used in various fields such as computer vision, speech recognition, and natural language processing. In particular, this technology is applied in various fields such as monitoring manufacturing equipment abnormalities, detecting financial fraud, detecting network hacking, and detecting anomalies in medical images. However, in the field of construction and architecture, research on deep learning-based data anomaly detection technology is difficult due to the lack of digitization of domain knowledge due to late digital conversion, lack of learning data, and difficulties in collecting and processing field data in real time. This study acquires necessary data through IoT (Internet of Things) from the viewpoint of monitoring for environmental management of architectural spaces, converts them into a database, learns deep learning, and then supports anomaly patterns using AI (Artificial Infelligence) deep learning-based anomaly detection. We propose an implementation process. The results of this study suggest an effective environmental anomaly pattern detection solution architecture for environmental management of architectural spaces, proving its feasibility. The proposed method enables quick response through real-time data processing and analysis collected from IoT. In order to confirm the effectiveness of the proposed method, performance analysis is performed through prototype implementation to derive the results.

• Proceedings of the Korean Institute of Building Construction Conference
• /
• 2022.04a
• /
• pp.73-74
• /
• 2022

Concrete structures occupy the largest proportion of modern infrastructure, and concrete structures often have cracking problems. Existing concrete crack diagnosis methods have limitations in crack evaluation because they rely on expert visual inspection. Therefore, in this study, we design a deep learning model that detects, visualizes, and outputs cracks on the surface of RC structures based on image data by using a CNN (Convolution Neural Networks) model that can process two- and three-dimensional data such as video and image data. do. An experimental study was conducted on an algorithm to automatically detect concrete cracks and visualize them using a CNN model. For the three deep learning models used for algorithm learning in this study, the concrete crack prediction accuracy satisfies 90%, and in particular, the 'InceptionV3'-based CNN model showed the highest accuracy. In the case of the crack detection visualization model, it showed high crack detection prediction accuracy of more than 95% on average for data with crack width of 0.2 mm or more.

• Journal of Korean Elementary Science Education
• /
• v.39 no.2
• /
• pp.228-242
• /
• 2020

The purpose of this study is to develop a student-led instructional strategy that is central to the teaching-learning process and to investigate its effects. For this study, we analyzed the learner-centered learning types (discovery learning, problem-based learning, inquiry learning) and extracted elements applicable to newly developed teaching-learning. Based on this, a student-led class strategy was established using pre-learning, teacher collaboration, small group composition, and limited open data and product presentation, and then science classes were conducted. As a result of the post-tests of the five science core competencies of the experimental group using the student-led instructional strategy and the comparative group conducting lecture-based classes, the experimental group showed higher scores than the comparative group in the scientific thinking, scientific communication, and scientific attitudes (p<.05). Based on these results, it was confirmed that the student-led class, in which the student self-adjusts the entire process of designing, exploring, and presenting learning, can help the student's scientific ability. In addition, I would like to discuss the implications of teachers' teaching-learning composition.

• Journal of Distribution Science
• /
• v.20 no.11
• /
• pp.121-129
• /
• 2022

Purpose: Artificial intelligence is widely used, particularly in the popular neural network theory called Deep learning. The improvement of computing speed and capability expedited the progress of Deep learning applications. The application of Deep learning in education has various effects and possibilities in creating and managing educational content and services that can replace human cognitive activity. Among Deep learning, Deep fake technology is used to combine and synchronize human faces with voices. This paper will show how to develop e-Learning content videos using those technologies and open-source tools. Research design, data, and methodology: This paper proposes 4 step development process, which is presented step by step on the Google Collab environment with source codes. This technology can produce various video styles. The advantage of this technology is that the characters of the video can be extended to any historical figures, celebrities, or even movie heroes producing immersive videos. Results: Prototypes for each case are also designed, developed, presented, and shared on YouTube for each specific case development. Conclusions: The method and process of creating e-learning video contents from the image, video, and audio files using Deep fake open-source technology was successfully implemented.

• Journal of Korea Society of Digital Industry and Information Management
• /
• v.19 no.1
• /
• pp.13-21
• /
• 2023

This study was conducted with students who participated in an online extracurricular after COVID-19 in order to analyze the effects of college students' learning strategy, learning attitude, and achievement motivation on satisfaction. After participating in the online extracurricular, an online survey was conducted, and responses from 163 students were collected. Based on the collected data, the study results were analyzed. The results of the study are as follows. First, learning strategy was found to have a positive effect on satisfaction. These results can be inferred that positive recognition worked in the process of actually applying the learning strategies acquired through the extracurricular to their own learning. Second, learning attitude had a positive effect on satisfaction. The learner's learning attitude to develop necessary skills through experience and the sense of achievement experienced in the process of participating in the online extracurricular had a positive effect on satisfaction. Third, achievement motivation was found to have a positive effect on satisfaction. It can be inferred that the learner's active behavior by participating in the program acts as a motivation for achievement and affects satisfaction. Finally, through this study, a plan for effectively operating extracurricular in an online environment was presented.

• Journal of Korean Elementary Science Education
• /
• v.34 no.1
• /
• pp.86-94
• /
• 2015

This study is to investigate how do elementary students' eye movements appear in cognitive process that they perceive science learning materials depending on motivation system of science learning. For this study we had a random sampling of 301, 6th grade students. And we had selected 32 students through the three tests for the final; motivation system test of science learning, a learning styles test, an Edinburgh inventory for handedness test. We were analysis the cognitive process during learning tasks for the selected student using eye-tracking equipment. The results of the research are as follows: First, when students see a science learning material, we found out that SL-BAS group that has tendency searched various areas than SL-BIS group in learning task. Second, results confirmed through the data of integrational count that students looked alternately texts, images and graphs in the learning material, SL-BIS group were more than SL-BAS group on integrated count, but they had a simple and insignificant eye movement. Especially SL-BAS students showed that integrated eye movement between texts, images and graphs in the learning material, and they explored important areas of the graph compared with SL-BIS group that there was no eye movement in graph. These results may be utilized as a useful resource for designing students' learning.

• Korean Journal of Adult Nursing
• /
• v.26 no.1
• /
• pp.107-116
• /
• 2014

Purpose: The purpose of this study was to identify the effects of multi-mode simulation learning on critical thinking disposition, on the problem solving process and on clinical competence of nursing students. Methods: A non-equivalent control group with pre-posttest was designed. The participants in this study were 65 students who were enrolled in an emergency and critical nursing course at N university. The treatment group consisted of 33 juniors in 2010 and the control group 32 juniors in 2011. Collected data were analyzed using chi-square, independent t-test, and ANCOVA with the SPSS/WIN 18.0 for Window Program. Results: There were significant increases in problem solving process and clinical competence in the treatment group who participated in the multi-mode simulation learning compared to the control group who did not (t=-2.39, p=.020; F=12.76, p=.001). However, there were no significant differences in critical thinking disposition between the treatment and control group (t=0.40, p=.692). Conclusion: Multi-mode simulation is an effective teaching and learning method to enhance the problem solving process and clinical competence of nursing students. Further exploration is needed to develop and utilize multi-mode simulation for diverse scenarios, depending on emergency nursing educational goals and environments and to develop a universal method to measure outcomes.

• Journal of the Korea Society of Computer and Information
• /
• v.22 no.1
• /
• pp.23-32
• /
• 2017

We can obtain useful knowledge from data by using a subgroup discovery algorithm. Subgroup discovery is a rule model learning method that finds data subgroups containing specific information from data and expresses them in a rule form. Subgroups are meaningful as they account for a high percentage of total data and tend to differ significantly from the overall data. Subgroup is expressed with conjunction of only literals previously. So, the scope of the rules that can be derived from the learning process is limited. In this paper, we propose a method to increase expressiveness of rules through internal disjunctive representation of attribute values. Also, we analyze the characteristics of existing subgroup discovery algorithms and propose an improved algorithm that complements their defects and takes advantage of them. Experiments are conducted with the traffic accident data given from Busan metropolitan city. The results shows that performance of the proposed method is better than that of existing methods. Rule set learned by proposed method has interesting and general rules more.