• Journal of the Korean Society of Environmental Restoration Technology
• /
• v.24 no.6
• /
• pp.89-96
• /
• 2021

In this study, a deep-learning image analysis model was established and validated for AI-based monitoring of the tidal flat ecosystem for marine protected creatures Ocypode stimpsoni and their habitat. The data in the study was constructed using an unmanned aerial vehicle, and the U-net model was applied for the deep learning model. The accuracy of deep learning model learning results was about 0.76 and about 0.8 each for the Ocypode stimpsoni and their burrow whose accuracy was higher. Analyzing the distribution of crabs and burrows by putting orthomosaic images of the entire study area to the learned deep learning model, it was confirmed that 1,943 Ocypode stimpsoni and 2,807 burrow were distributed in the study area. Through this study, the possibility of using the deep learning image analysis technology for monitoring the tidal ecosystem was confirmed. And it is expected that it can be used in the tidal ecosystem monitoring field by expanding the monitoring sites and target species in the future.

• ETRI Journal
• /
• v.46 no.1
• /
• pp.137-153
• /
• 2024

This study introduces a new approach in Korean morphological analysis combining dictionary-based techniques with Transformer-based deep learning models. The key innovation is the use of a BERT-based reranking system, significantly enhancing the accuracy of traditional morphological analysis. The method generates multiple suboptimal paths, then employs BERT models for reranking, leveraging their advanced language comprehension. Results show remarkable performance improvements, with the first-stage reranking achieving over 20% improvement in error reduction rate compared with existing models. The second stage, using another BERT variant, further increases this improvement to over 30%. This indicates a significant leap in accuracy, validating the effectiveness of merging dictionary-based analysis with contemporary deep learning. The study suggests future exploration in refined integrations of dictionary and deep learning methods as well as using probabilistic models for enhanced morphological analysis. This hybrid approach sets a new benchmark in the field and offers insights for similar challenges in language processing applications.

• The Journal of the Korea Contents Association
• /
• v.21 no.10
• /
• pp.594-602
• /
• 2021

This study aims to identify the learning behavior patterns recognized by students to find effective tutoring operational methods, and further analyze the impact of learning behavior patterns on academic performance and learning satisfaction. To this end, 105 participants in the tutoring program at D University based in Busan Metropolitan City collected data and conducted descriptive statistics, correlation analysis and regression analysis according to research problems. First, the study found that students who participated in tutoring had the most environment-dependent and self-taught learning behavioral styles and environment-independent and self-taught learning behavioral style. Second, the correlation between learning behavioral styles and academic achievement and learning satisfaction shows that there is a high correlation between positive and cooperative learning behavioral styles and environment-independent and self-taught learning behavioral styles. Third, regression analysis on academic achievement and learning satisfaction showed that positive and cooperative learning behavioral styles significantly affects learning satisfaction, but environment-independent and self-taught learning behavioral style, environment-dependent and self-taught learning behavioral style, and passive learning behavioral style were not significant. These results suggest that from the school perspective, learning behavior can be recognized as an important factor in students' academic success and failure, so instructors need to check learners' learning behavior patterns and provide appropriate tutoring teaching and learning design plans.

• Knowledge Management Research
• /
• v.13 no.3
• /
• pp.105-125
• /
• 2012

Previous studies have focused on individual and organizational learning. Amid an increasingly complex business environment, a team system designed to improve flexibility and adaptability constitutes the most basic part of an organization. Still, team learning has rarely been discussed. In addition, team learning behavior, despite being an important part of a team process, is often mentioned as a team-level outcome variable. Given that team learning behavior involves constant changes in thinking and behavior, a shared belief among team members is needed in order to positively influence innovative performance of a team. In spite of that, there has been only limited discussion of it. Besides, few domestic studies have dealt with R&D teams that can clearly demonstrate team learning behavior and team innovative performance. This study is an empirical analysis of the impact of team efficacy on team innovative performance and the mediating role of team learning behavior based on materials collected from team leaders and their immediate subordinates in 268 R&D teams. The analysis showed that team learning behavior actually has a positive effect on team innovative performance. Team efficacy also turned out to have a positive influence on team learning behavior. Lastly, the study found that team learning behavior played a mediating role in the relationship between team efficacy and team innovative performance. Based on those results, the study has identified implications and suggested directions for future research.

• Journal of the Korean Society of Clothing and Textiles
• /
• v.45 no.2
• /
• pp.271-284
• /
• 2021

This study presents the educational utility of blended learning by analyzing the effectiveness of learning after class by blending team project learning and smart device app-based learning methods. Qualitative analysis and survey analysis were conducted and the results were as follows. First, team project activities based on task resolution were conducted freely through detailed activities such as sharing roles, planning meetings, and coordinating opinions. Team activities were carried out with respect and consideration, team member bonding, and a sense of responsibility. Second, the smart device app is recognized as a medium for work and communication, and fast feedback has been made, making it highly impactful on classroom activities. Third, in terms of learning satisfaction, most learners showed an interest in the course and were satisfied with the project results. The smart device app was used as a learning and communication medium for personal and team activities and was analyzed as a blended method applicable to classes that conduct practical activities as an efficient tool to further activate project activities.

• Journal of Technologic Dentistry
• /
• v.44 no.4
• /
• pp.132-143
• /
• 2022

Purpose: The study aims to analyze differences in the satisfaction level of dental technology students regarding in-person and online classes. It also aims to provide fundamental resources for the improvement of major subject class methods that will improve students' self-directed learning abilities, thereby affecting their class satisfaction. Methods: In this study, a self-administered questionnaire was conducted from November 8 to November 30, 2021, for 256 dental technology students. The collected data were analyzed using the IBM SPSS Statistics ver. 21.0 statistical program. Frequency and percentage, mean, standard deviation, t-test, ANOVA, post-hoc test, correlation analysis, and linear regression analysis were performed to analyze the data. Results: In the self-directed learning abilities, the attitude of the learners was shown to have the highest positive (+) correlation in both in-person and online classes, with a statistically significant effect (p<0.001) on class satisfaction in major subject classes. Moreover, the explanatory power of the model was 52.2% and 39.7%, respectively. Conclusion: We concluded from the study that there is a need for professors to improve teaching methods to increase learners' self-directed learning competence, through problem-based learning, discussion learning, team-based collaborative learning, and mentor-mentee learning, thereby enabling learners to lead classes themselves.

• Journal of The Korean Association of Information Education
• /
• v.24 no.6
• /
• pp.519-528
• /
• 2020

Due to COVID-19, most schools are conducting online learning. In this study, a total of 12 block-type educational programming tool classes were conducted in the form of online learning for 6th grade elementary school students, and then quantitatively and qualitatively analyzed students' perceptions of their learning experience on entry learning. As a result of the analysis, it was found that the learner easily recognized the use of the entry program and the difficulty of learning contents, and the learning satisfaction was high. When students face difficulties, it was found that they received the most help from the hint function provided by the site itself, and they were found to be less aware of the necessity of teachers when learning entry. As a result of the qualitative analysis, it was found that the learner felt a lot of novelty and fun through easy and simple operation. On the other hand, it was found that the learning contents and hints were not understood, which made them difficult and felt that the hint contents were insufficient. It was found that students felt a sense of accomplishment by creating and manipulating programs as they wish.

• The Journal of the Convergence on Culture Technology
• /
• v.7 no.4
• /
• pp.511-517
• /
• 2021

This study is a descriptive investigative study to correlate of learning flow, self-directedness, self-regulated learning ability and learning achievement of nursing students who in non-face-to-face learning environment. The subjects of the study were 179 nursing college students based in B, G city, who collected data from September to October 2021. The data analysis used the SPSS 24.0 program and performed descriptive statistics and correlation analysis. As a result of the study, the average learning flow was 38.54±7.87 points, self-directedness was 134.83±19.81 points, self-regulated learning ability was 42.93±5.98 points and learning achievement was 15.03±2.56 points. The relationships among learning flow, self-directedness, self-regulated learning ability, and learning achievement showed significant positive correlations. Therefore, strategies to increase the learning achievement of nursing college students in a non-face-to-face environment, and environmental improvement and institutional support to increase learning flow are needed.

• KIPS Transactions on Software and Data Engineering
• /
• v.2 no.1
• /
• pp.7-18
• /
• 2013

These days, the teaching and learning system has been increasing for the rapid advancement of the information technologies. We can access education systems of good quality anytime, anywhere and we can use the individually personalized teaching and learning system depending on developing the wireless communication technology and the multimedia processing technology. The more the various systems develop, the more software security systems become important. There are a lot kind of fault analysis methods to evaluate software security systems. However, the only assessment method to evaluate software security system is not enough to analysis properly on account of the various types and characteristic of software systems by progressing information technology. Therefore, this paper proposes an integrative method of Fault Tree Analysis (FTA) and Fault Modes and Effect Analysis(FMEA) to evaluate the security of e-teaching and learning system as an illustration.

• Journal of Engineering Education Research
• /
• v.20 no.6
• /
• pp.3-11
• /
• 2017

The purpose of this study is to investigate the variables that learners should consider for learning persistence when applying blended learning to mathematics class which is a basic curriculum of engineering college. For this purpose, this study compared the basic mathematics class with the blended learning and the class without it. In addition, this study analyzed the influence of the learning outcomes of the blended learning on the willingness to learning persistence by using the self-efficacy and self-regulated learning variables that can predict it. As a result, it was found that the blended learning applied mathematics class of K university which is the subject of analysis in this study has higher self - efficacy, self - regulated learning, and learning persistence intention than general classroom. Finally, the results of this study are meaningful to provide the points to be considered for improving the learning performance when applying the blended learning to the subject class in the future.