• Journal of The Korean Association of Information Education
• /
• v.17 no.3
• /
• pp.305-316
• /
• 2013

Despite the potential implications of Facebook use, there is a distinct lack of empirically derived theory for designing learning environment. This may be because Facebook is a social tool and there has been limited opportunity for exploratory research regarding Facebook based learning. Therefore, the purpose of this study is to investigate learning presence factors affecting learning outcomes in Facebook-based collaborative learning. Forty two college students participated in the Facebook-based collaborative learning activity, and the data from thirty nine were used for step-wise multiple regression analysis. In addition focus group interview was conducted to examine learning presence of Facebook-based collaborative learning. The results reported that cognitive presence predicted significantly learning outcomes, however, social and emotional presence did not predict learning outcomes. The implication of this study and future research were discussed in this research.

• Journal of Korean Society for Quality Management
• /
• v.38 no.2
• /
• pp.161-170
• /
• 2010

Diffusion of e-learning has been accelerated according as the convenience and effectiveness have been increased rapidly due to the advancement of information technology. However, there has been few studies on systematic evaluation of its performance. SERVQUAL model was applied to evaluate the service quality of a 100% on-line lecture opened in a major Korean university. Two classes, one for 71 undergraduate students, the other for 79 graduate students, were opened for the lecture. The gaps between the expected service and the perceived service scores were compared with respect to sex, age, and e-learning experience. Although the gap score of male and female students were not different significantly, the gap scores among the other comparative groups were different. The perceived score of the older group with more than thirty ages was lower than that of the younger group. It seems that the older group evaluated the score based on the practical use of the subject since they are part-time students with jobs. Also, the perceived score of the group with previous e-learning experience was higher than that of the group with no e-learning experience. It seems that the experienced group evaluated it compared with the previous e-learning satisfaction. As it might be expected, the groups with higher perceived scores had stronger intention to recommend the e-learning lecture to other students.

• Journal of Semiconductor Engineering
• /
• v.2 no.2
• /
• pp.130-135
• /
• 2021

Recently, deep neural networks (DNNs) are actively used for action control so that an autonomous system, such as the robot, can perform human-like behaviors and operations. Unlike recognition tasks, the real-time operation is essential in action control, and it is too slow to use remote learning on a server communicating through a network. New learning techniques, such as reinforcement learning (RL), are needed to determine and select the correct robot behavior locally. In this paper, we propose an energy-efficient DNN processor with a LUT-based processing engine and near-zero skipper. A CNN-based facial emotion recognition and an RNN-based emotional dialogue generation model is integrated for natural HRI system and tested with the proposed processor. It supports 1b to 16b variable weight bit precision with and 57.6% and 28.5% lower energy consumption than conventional MAC arithmetic units for 1b and 16b weight precision. Also, the near-zero skipper reduces 36% of MAC operation and consumes 28% lower energy consumption for facial emotion recognition tasks. Implemented in 65nm CMOS process, the proposed processor occupies 1784×1784 um2 areas and dissipates 0.28 mW and 34.4 mW at 1fps and 30fps facial emotion recognition tasks.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.18 no.2
• /
• pp.494-510
• /
• 2024

Internet users are exposed to sophisticated cyberattacks that intrusion detection systems have difficulty detecting. Therefore, research is increasing on intrusion detection methods that use artificial intelligence technology for detecting novel cyberattacks. Unsupervised learning-based methods are being researched that learn only from normal data and detect abnormal behaviors by finding patterns. This study developed an anomaly-detection method based on unsupervised machines and deep learning for a network intrusion detection system (NIDS). We present a hybrid anomaly detection approach based on unsupervised learning techniques using the autoencoder (AE), Isolation Forest (IF), and Local Outlier Factor (LOF) algorithms. An oversampling approach that increased the detection rate was also examined. A hybrid approach that combined deep learning algorithms and traditional machine learning algorithms was highly effective in setting the thresholds for anomalies without subjective human judgment. It achieved precision and recall rates respectively of 88.2% and 92.8% when combining two AEs, IF, and LOF while using an oversampling approach to learn more unknown normal data improved the detection accuracy. This approach achieved precision and recall rates respectively of 88.2% and 94.6%, further improving the detection accuracy compared with the hybrid method. Therefore, in NIDS the proposed approach provides high reliability for detecting cyberattacks.

• Journal of The Korean Association of Information Education
• /
• v.5 no.1
• /
• pp.69-78
• /
• 2001

Recently, the current trend for computer based learning is moving from CAI environment to WBI environment. Most web documents for WBI learning are collected by aid of search engine. Instructors use those documents as learning materials after they evaluate availability of retrieved web documents. But, this method has the following problems. First, we search repeatedly the web documents selected by instructor. Second, there is a need for another course of instruction design in order to suggest the web documents for learner. Third, it is very difficult to analyze for relevance between the web documents and test results. In this work, we suggest WAILS(Web Agent Instruction Learning System) that retrieves web documents for WBI learning and guides learning course for learners. WAILS collects web documents for WBI learning by aid of web agent. Then, instructors can evaluate them and suggest to learners by using instruction-learning generating machine. Instructors retrieve web documents and the instruction-learning design at the same time. This can facilitate WBI learning.

• Journal of The Korean Association of Information Education
• /
• v.26 no.4
• /
• pp.249-263
• /
• 2022

The purpose of this study is to investigate the effects of assessment by adopting adaptive learning in higher education that are rarely examined in previous studies. In particular, this study applied research questions: 1) How does technical perception, perceived contents and features, and perceived integration of the AI-based adaptive system with lecture affect overall satisfaction, overall effectiveness, overall usefulness, overall motivation for the study, and intention to use it with other classes? 2) How do overall satisfaction, overall effectiveness, overall usefulness, motivation for the class, and intention to use affect loyalty on the AI-based adaptive system? This study conducted online surveys after the completion of the classes adopted AI-based adaptive learning system, ALEKS. This study applied ANOVA, regression, and factor analyses. The results of this study found that perceived integration of the AI-based adaptive learning system with the lectures on overall satisfaction, effectiveness, motivation, and intention to use for other classes showed significant with higher effect size. The results of this study provides implication that the AI-based learning system help improve learning outcomes in graduate level studies. The results provide policy and managerial implications that the AI-based adaptive learning system should improve better customer relationships in higher education.

• International Journal of Computer Science & Network Security
• /
• v.24 no.4
• /
• pp.127-134
• /
• 2024

The article highlights the problems of the digitalization of the educational process, which affect the pedagogical cluster and are of a psychological nature. The authors investigate the transformational changes in education in general and the individual beliefs of each subject of the educational process, caused by both the change in the format of learning (distance, mixed), and the use of new technologies (digital, communication). The purpose of the article is to identify the strategic trend of the educational process, which is a synergistic combination of pedagogical methodology and psychological practice and avoiding dialectical opposition of these components of the educational space. At the same time, it should be noted that the introduction of digital technologies in the educational process allows for short-term difficulties, which is a usual phenomenon for innovations in the educational sphere. Consequently, there is a need to differentiate the fundamental problems and temporary shortcomings that are inherent in the new format of learning (pedagogical features). Based on the awareness of this classification, it is necessary to develop psychological techniques that will prevent a negative reaction to the new models of learning and contribute to a painless moral and spiritual adaptation to the realities of the present (psychological characteristics). The methods used in the study are divided into two main groups: general-scientific, which investigates the pedagogical component (synergetic, analysis, structural and typological methods), and general-scientific, which are characterized by psychological direction (dialectics, observation, and comparative analysis). With the help of methods disclosed psychological and pedagogical features of the process of digitalization of education in a mixed learning environment. The result of the study is to develop and carry out methodological constants that will contribute to the synergy for the new pedagogical components (digital technology) and the psychological disposition to their proper use (awareness of the effectiveness of new technologies). So, the digitalization of education has demonstrated its relevance and effectiveness in the pedagogical dimension in the organization of blended and distance learning under the constraints of the COVID-19 pandemic. The task of the psychological cluster is to substantiate the positive aspects of the digitalization of the educational process.

• English Language & Literature Teaching
• /
• v.16 no.1
• /
• pp.143-170
• /
• 2009

The purpose of this experimental study is to investigate the effects of repeating vocabulary exercises on learning and retaining the meaning, the form, and the use of L2 words. To achieve this purpose, the data from the 87 participants who performed the assigned vocabulary exercises were collected immediately and two weeks later on their learning and retention of the target words. In addition, their attitudes toward the given vocabulary exercises were examined. The results show that the participants repeating exercises showed significantly better results in the immediate posttest, whereas no significant differences were found in the delayed posttest. Consequently, although the repetition effect influence positively on the learning of the target words, these effects are not maintained if they are not reinforced subsequently after the initial introduction to them. Most of the participants in this study identified the importance of repetition in learning new words and also noted that only one encounter with words was not enough for them to acquire the words fully.

• Proceedings of the IEEK Conference
• /
• 2003.07d
• /
• pp.1239-1242
• /
• 2003

The neural networks are a famous model to learn the nonlinear function or nonlinear system. The main point of neural network is that the difference actual output from desired output is used to update weights. Usually, the gradient descent method is used for the learning process. On training process, if learning rate is too large, neural networks hardly guarantee convergence of neural networks. On the other hand, if learning rate is too small, the training spends much time. Therefore, one major problem in use of neural networks are to decrease the teaming time while neural networks are guaranteed convergence. In this paper, we suggest the model of fuzzy logic to neural networks to calibrate learning rate. This method is to tune learning rate dynamically according to error and demonstrates the optimization of training.

• International Journal of Contents
• /
• v.10 no.2
• /
• pp.42-46
• /
• 2014

This study suggests a teaching-learning method to improve creative design abilities of students majoring in design. By suggesting a creative design-inducing (CDI) teaching-learning method process and a creative design-inducing (CDI) teaching-learning method, this study aims to expand creative thinking among students with the aim of producing produce creative output as well as improving the effectiveness of design teaching. It also presents a case of the teaching-learning method in a design-related department, the process of teaching where the new method is applied is also examined. The teaching method this study suggests has the following merits: First, it allows the teacher to use various tools depending on the creative thinking abilities of individuals. By providing students with custom-made teaching, the method motivates and focuses students during the lesson. Second, it is easier for students to generate creative ideas than with other teaching methods.