• International journal of advanced smart convergence
• /
• v.9 no.4
• /
• pp.115-119
• /
• 2020

Recently, CCTV installations are rapidly increasing in the public and private sectors to prevent various crimes. In accordance with the increasing number of CCTVs, video-based abnormal behavior detection in control systems is one of the key technologies for safety. This is because it is difficult for the surveillance personnel who control multiple CCTVs to manually monitor all abnormal behaviors in the video. In order to solve this problem, research to recognize abnormal behavior using deep learning is being actively conducted. In this paper, we propose a model for detecting abnormal behavior based on the deep learning model that is currently widely used. Based on the abnormal behavior video data provided by AI Hub, we performed a comparative experiment to detect anomalous behavior through violence learning and fainting in videos using 2D CNN-LSTM, 3D CNN, and I3D models. We hope that the experimental results of this abnormal behavior learning model will be helpful in developing intelligent CCTV.

• Proceedings of the Korea Contents Association Conference
• /
• 2007.11a
• /
• pp.719-723
• /
• 2007

It is very active that existing companies of providing e-Learning contents try to differentiate themselves through a business model based on Web 2.0. For instance, Etoos, online education website (www.etoos.com) run by SK Communications has made more space where students can participate in the Web 2.0 era and overhauled its website completely, turning into an open-ended one, which strengthens learning and fun in 2007. This study is to analyze the present state of e-Learning contents with representative e-learning sites for middle and high school students, to find that the development direction for next generation e-Learning lies in developing contents focusing on learners that can get effective feedback and drawing collective intelligence grounded on the essence of Web 2.0, and to suggest 'the project to form virtual private tutor community in e-Learning contents.'

• Educational Technology International
• /
• v.10 no.1
• /
• pp.1-23
• /
• 2009

Learners are often posited in a paradoxical situation where they are not fully involved in decision making processes on how to learn, in designing their tools. Cognitive artifacts in e-learning are supposed to effectively support learner-centered e-learning. The purpose of the study is to analyze cases of cognitive artifacts and to inquire those design principles for facilitating the learner-centered e-learning. Four research questions are suggested: First, it will be analyzed the characteristics of learners with respect to design of cognitive artifacts for supporting the learner-centered e-learning. Second, characteristics of four cases to design cognitive artifacts in learner-centered e-learning environment are analyzed. Third, it will be suggested the appropriate design principles of cognitive artifacts to facilitating learner-centered learning in e-learning environment. Four cases of cognitive artifacts design in learner-centered e-learning was identified as follows: Wiki software as cognitive artifacts in computer-supported collaborative learning; 'Play Around Network (PAN)' as cognitive artifact to monitor learning activities in knowledge community; Knowledge Forum System (KFS) as a cognitive artifact in knowledge building; cognitive artifacts in Courses-as-seeds applied meta-design. Five design principles are concluded as follows: Promoting externalization of cognitive artifacts to private media; Helping learners to initiate their learning processes; Encouraging learners to make connections with other learners' knowledge building and their cognitive artifacts; Promoting monitoring of participants' contributions in collaborative knowledge building; Supporting learners to design their cognitive artifacts.

• The Journal of Advanced Prosthodontics
• /
• v.10 no.6
• /
• pp.395-400
• /
• 2018

PURPOSE. This study tried to find the most significant factors predicting implant prognosis using machine learning methods. MATERIALS AND METHODS. The data used in this study was based on a systematic search of chart files at Seoul National University Bundang Hospital for one year. In this period, oral and maxillofacial surgeons inserted 667 implants in 198 patients after consultation with a prosthodontist. The traditional statistical methods were inappropriate in this study, which analyzed the data of a small sample size to find a factor affecting the prognosis. The machine learning methods were used in this study, since these methods have analyzing power for a small sample size and are able to find a new factor that has been unknown to have an effect on the result. A decision tree model and a support vector machine were used for the analysis. RESULTS. The results identified mesio-distal position of the inserted implant as the most significant factor determining its prognosis. Both of the machine learning methods, the decision tree model and support vector machine, yielded the similar results. CONCLUSION. Dental clinicians should be careful in locating implants in the patient's mouths, especially mesio-distally, to minimize the negative complications against implant survival.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.13 no.12
• /
• pp.6260-6276
• /
• 2019

With the rapid development of cloud computing, it raises real questions on privacy protection, which greatly limits the use of cloud computing. However, fully homomorphic encryption (FHE) can make cloud computing consistent with privacy. In this paper, we propose a simpler FHE scheme based on ring LWE problem, with a smaller size of ciphertext and a lower noise-expansion factor for homomorphic multiplication. Then based on our optimized RLWE-based FHE scheme, we propose a fast single-database private information retrieval protocol, combining with batching and number theoretic transform technology.

• Journal of Digital Convergence
• /
• v.7 no.1
• /
• pp.137-147
• /
• 2009

The main purpose of cyber home education in public sector is to promote public education and restrain expensive private education expenses. The primary purpose of this study is to explore the effects of motivation, immersion and tutor on the effectiveness of cyber home learning. The variables of motivation, immersion and tutor participation were incorporated in this study as follows: 1) tutor participation was classed as a single independent variable, which has interaction and also effects passion; 2) motivation and 3) immersion were classed as two mediatory variables: motivation which include relevance and confidence; and immersion which includes attention and controllability. 4) learning effect was classed as a single dependent variable of learning influence factor which has learning attitude and learning satisfaction. The results show that a tutor had a direct influence on the effects of the learners' study but motivation and immersion had an indirect influence on the effects of learners' study independently. Based on these findings a tutor should provide motivation and immersion with various learning methods and contents for learners to get maximum benefits from cyber home learning.

• English Language & Literature Teaching
• /
• v.17 no.2
• /
• pp.247-270
• /
• 2011

The purpose of this study is to investigate the effects of multimedia-assisted language learning on vocabulary learning and attention for elementary school students who are ADHD-prone. Among thirty-three students attending a private English academy in Daegu, four students who were prone to develop ADHD were chosen for this study. They were observed in a multimedia-assisted language learning class for four months and they were given a series of tests designed to measure their attention period and vocabulary ability. The results of the study are as follows. First, studying English by using multimedia was effective in improving the attention of those children prone to develop ADHD. Second, studying English through multimedia was effective in improving their vocabulary ability. Based on the findings, some pedagogical suggestions have been made for further study.

• Journal of Gifted/Talented Education
• /
• v.7 no.2
• /
• pp.47-67
• /
• 1997

Fourteen Special high schools for developing talents in Science, Foreign Languages, and Arts in Seoul Metropolitan city were analyzed in terms of their educational objectives, Students screening system, curriculum, teaching-learning methods, teachers, and consistency with higher education. Special high schools in talent area were more or less similar to each other in all the above aspects. However, special high schools in different talent areas were quite different in student screening, teaching-learning methods, teachers, and consistency with higher education. Public schools were more affluent than the private ones. Special high schools in Science, arts and Sports were providing individualized, activity oriented, process-oriented teaching-learning methods, while the Foreign languages high schools excercised teacher-centered, grammar oriented, lecture-focused teaching methods more. Special high schools in arts and sports could have consistency with higher education because the university focuses on talents in the specified field rather than academic scores. In conclusion, the schools have a great deal of rooms to improve in teaching-learning methods with which students can maximize their potential development. However, the special high schools were equipped with better learning environments than regular high schools in many aspects.

• International Journal of Human Ecology
• /
• v.14 no.1
• /
• pp.115-130
• /
• 2013

This study reviews the current status of Korean first graders, their experience with early care and education (ECE) programs, and their participation in private and after-school education. The research also examines how school adjustment during the first grade is related to family income, types of ECE programs, and participation in private and after-school education. Using the first year data of the Korean Child and Youth Panel Survey (KCYPS) 2010, this study analyzes 752 first graders who attended only one of two types of ECE programs (child care centers or kindergartens), after which two 25% income extremes were examined. The analysis demonstrates that children from low-income households attended child care centers more often, while children from high-income households attended kindergartens more often. For both low-income and high-income groups, child care centers had a lower starting age and longer attendance periods than did kindergartens. High-income household children started attending ECE programs earlier, experienced more private and after-school education, and received a larger number of private and after-school educational lessons. For the second research purpose, children from low-income families showed better peer relations in school adjustment, while children attending child care centers showed better teacher relations than children attending kindergartens. Children with after-school education also exhibited better peer relations. These findings show the importance of government support for early learning, especially for low-income families and offer a foundation for developing private education polices for early childhood before and after school entry.

• The Korean Journal of Applied Statistics
• /
• v.37 no.1
• /
• pp.13-38
• /
• 2024

As economic uncertainties have increased recently due to COVID-19, there is a growing need to quickly grasp private consumption trends that directly reflect the economic situation of private economic entities. This study proposes a method of estimating private consumption in real-time by comprehensively utilizing big data as well as existing macroeconomic indicators. In particular, it is intended to improve the accuracy of private consumption estimation by comparing and analyzing various machine learning methods that are capable of fitting ultra-high-dimensional big data. As a result of the empirical analysis, it has been demonstrated that when the number of covariates including big data is large, variables can be selected in advance and used for model fit to improve private consumption prediction performance. In addition, as the inclusion of big data greatly improves the predictive performance of private consumption after COVID-19, the benefit of big data that reflects new information in a timely manner has been shown to increase when economic uncertainty is high.