• 한국디지털정책학회:학술대회논문집
• /
• 2005.06a
• /
• pp.559-570
• /
• 2005

This paper presents how to establish an efficient e-Learning environment using open source software. A LMS with additional functionalities on the top of dotLRN. which is a open source project for LMS, is presented. Additional functionalities include modification of the language for Korean, adoption of SCORM educational standard, and management of learning outcome. This system had been serviced for Kongju cyber university for one year on stable basis. The scope of this paper covers introduction, characteristics review, and the learner's learning outcome analysis.

• Journal of the Korean Society for Library and Information Science
• /
• v.34 no.3
• /
• pp.37-60
• /
• 2000

Recent developments and integration of IT are expanding the possibility of various instructional learning methods in education environments. Contemporary learning theory such as open education, self-directed learning, student's centered learning describes the students as an active and engaged information user and underscores the importance of information literacy. Therefore, school library today focus on the process of learning-teaching process rather than dissemination information, and emphasized the focus of the school electronic library as information center. The purpose of this study is examined physical components of School Electronic Library, design a model of information system and suggests a strategy for implementing teaching-learning process support services based on school electronic library and information system.

• Journal of Korea Multimedia Society
• /
• v.21 no.10
• /
• pp.1195-1202
• /
• 2018

Artificial neural network is widely used for its excellent performance and implementability. However, traditional neural network needs to learn the system from scratch, with the addition of new input data, the variation of the observation environment, or the change in the form of input/output data. To resolve such a problem, the technique of transfer learning has been proposed. Transfer learning constructs a newly developed target system partially updating existing system and hence provides much more efficient learning process. Until now, transfer learning is mainly studied in the field of image processing and is not yet widely employed in acoustic data processing. In this paper, focusing on the scalability of transfer learning, we apply the concept of transfer learning to the problem of guitar chord classification and evaluate its performance. For this purpose, we build a target system of convolutional neutral network (CNN) based 48 guitar chords classification system by applying the concept of transfer learning to a source system of CNN based 24 guitar chords classification system. We show that the system with transfer learning has performance similar to that of conventional system, but it requires only half the learning time.

• International Journal of Computer Science & Network Security
• /
• v.22 no.9
• /
• pp.224-230
• /
• 2022

The intent of this paper is to unveil the effectiveness of different learning environments (traditional, electronic, blended) in educational institutions through a set of dimensions: an introduction to traditional education and e-learning, the importance and objectives of e-learning, the difference between e-learning and traditional education and teachers' roles in e-learning, the challenges facing the use of e-learning. It also introduces blended learning, providing an account about its emergence, concept, importance, the difference between blended learning and e-learning, the advantages of blended learning, and the challenges confront using blended learning.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• v.8 no.1
• /
• pp.31-36
• /
• 2008

This paper presents adaptive learning data of evolvable neural networks (ENNs) for time series prediction of nonlinear dynamic systems. ENNs are a special class of neural networks that adopt the concept of biological evolution as a mechanism of adaptation or learning. ENNs can adapt to an environment as well as changes in the enviromuent. ENNs used in this paper are L-system and DNA coding based ENNs. The ENNs adopt the evolution of simultaneous network architecture and weights using indirect encoding. In general just previous data are used for training the predictor that predicts future data. However the characteristics of data and appropriate size of learning data are usually unknown. Therefore we propose adaptive change of learning data size to predict the future data effectively. In order to verify the effectiveness of our scheme, we apply it to chaotic time series predictions of Mackey-Glass data.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.14 no.4
• /
• pp.701-706
• /
• 2019

The advent of the AI(: Artificial Intelligence) has applied to many industrial and general applications have havingact on our lives these days. Various types of machine learning methods are supported in this field. The supervised learning method of the machine learning has features and targets as an input in the learning process. There are many supervised learning methods as well and their performance varies depends on the characteristics and states of the big data type as an input data. Therefore, in this paper, in order to compare the performance of the various supervised learning method with a specific big data set, the supervised learning methods supported in the Tensorflow and the Sckit-Learn are simulated and analyzed in the Jupyter Notebook environment with python.

• International Journal of Internet, Broadcasting and Communication
• /
• v.15 no.3
• /
• pp.166-175
• /
• 2023

Reinforcement learning can be applied to a wide variety of problems. However, the fundamental limitation of reinforcement learning is that it is difficult to derive an answer within a given time because the problems in the real world are too complex. Then, with the development of neural network technology, research on deep reinforcement learning that combines deep learning with reinforcement learning is receiving lots of attention. In this paper, two types of neural networks are combined with reinforcement learning and their characteristics were compared and analyzed with existing value-based reinforcement learning algorithms. Two types of neural networks are FNN and CNN, and existing reinforcement learning algorithms are SARSA and Q-learning.

• IEIE Transactions on Smart Processing and Computing
• /
• v.2 no.6
• /
• pp.323-331
• /
• 2013

An extreme learning machine (ELM) is an efficient learning algorithm that is based on the generalized single, hidden-layer feed-forward networks (SLFNs), which perform well in classification applications. Many studies have demonstrated its superiority over the existing classical algorithms: support vector machine (SVM) and BP neural network. This paper presents a novel face recognition approach based on a multi-class project extreme learning machine (MPELM) classifier and 2D Gabor transform. First, all face image features were extracted using 2D Gabor filters, and the MPELM classifier was used to determine the final face classification. Two well-known face databases (CMU-PIE and ORL) were used to evaluate the performance. The experimental results showed that the MPELM-based method outperformed the ELM-based method as well as other methods.

• International Journal of Computer Science & Network Security
• /
• v.21 no.5
• /
• pp.98-112
• /
• 2021

This study aimed at measuring students' interaction in distance education through the electronic platform among intermediate school students, by identifying the level of students' interaction in distance education and differences between them, as well as its impact on their motivation to learn. To achieve the aim of the study, two scales were designed for this purpose and were applied to a sample consisting of (268) individuals. The results showed that the level of students' interaction through the e-learning platform was at a high level. The results also showed that there was no statistically significant difference between the mean scores of males and females in the scale of students' interaction through the e-learning platform. There was no statistically significant difference between them in their motivation for distance learning via the online platform. There were also no statistically significant differences related to the grade variable in the level of interaction through the electronic platform and in the motivation to learn, while there was a positive statistically significant effect of interaction through the electronic platform on students' motivation to learn.

• 제어로봇시스템학회:학술대회논문집
• /
• 2003.10a
• /
• pp.1794-1797
• /
• 2003

We developed a web-based virtual laboratory system for electronic circuit experiments on the client/ server distributed environment. Through our virtual laboratory, the learners will be capable of learning the concepts and theories related to electronic circuit experiments and how to operate the experimental equipments such as multimeters, function generators, digital oscilloscopes and DC power suppliers. The proposed virtual laboratory system is composed of four important components: Principle Classroom to explain the concepts and theories of electronic circuit operations, Virtual Experiment Classroom to provide interactive multimedia contents about the syllabus of off-line laboratory class, Assessment Classroom, and Management System. With the aid of the Management System every classroom is organically tied together collaborating to achieve maximum learning efficiency. We have obtained several affirmative effects such as high learning standard, reducing the total experimental hours and the damage rate for experimental equipments.