• Journal of Information Processing Systems
• /
• v.16 no.5
• /
• pp.1001-1007
• /
• 2020

In recent years, machine learning algorithms are continuously being used and expanded in various fields, such as facial recognition, signal processing, personal authentication, and stock prediction. In particular, various algorithms, such as deep learning, reinforcement learning, and Q-learning, are continuously being improved. Among these algorithms, the expansion of deep learning is rapidly changing. Nevertheless, machine learning algorithms have not yet been applied in several fields, such as personal authentication technology. This technology is an essential tool in the digital information era, walking recognition technology as promising biometrics, and technology for solving state-space problems. Therefore, algorithm technologies of deep learning, reinforcement learning, and Q-learning, which are typical machine learning algorithms in various fields, such as agricultural technology, personal authentication, wireless network, game, biometric recognition, and image recognition, are being improved and expanded in this paper.

• Journal of the Korea Society of Computer and Information
• /
• v.28 no.1
• /
• pp.27-38
• /
• 2023

In this paper, we propose a conversational AI agent based on continual learning that can continuously learn and grow with new data over time. A continual learning-based conversational AI agent consists of three main components: Task manager, User attribute extraction, and Auto-growing knowledge graph. When a task manager finds new data during a conversation with a user, it creates a new task with previously learned knowledge. The user attribute extraction model extracts the user's characteristics from the new task, and the auto-growing knowledge graph continuously learns the new external knowledge. Unlike the existing conversational AI agents that learned based on a limited dataset, our proposed method enables conversations based on continuous user attribute learning and knowledge learning. A conversational AI agent with continual learning technology can respond personally as conversations with users accumulate. And it can respond to new knowledge continuously. This paper validate the possibility of our proposed method through experiments on performance changes in dialogue generation models over time.

• Korean Institute of Interior Design Journal
• /
• v.14 no.2 s.49
• /
• pp.206-216
• /
• 2005

The purpose of this study is a development of $teaching{\cdot}learning$ program based on interior design WBI. WBI's meaning is Web Based Instruction. There can be several procedures that should be designed at the first step: Analyzing, Designing, Building, Testing, Recycling. These stages are constructed based on the theory of procedure about the computer and the $teaching{\cdot}learning$. Each stage is presented the contents of development, the contents of main, the method advantages and problem solving. These procedures and contents of development are the research method simultaneously with the result. Upon the completion of the system, it should undergo the same process continuously so that it can improve over a period of time, contribute to the interior design of students. In addition continuously repetitive requirements pop up in the phase. And it is necessary for this program try to map out a strategy developing and a policy support from university. It's very important that develop the contents of interior design from professor, students and field professor.

• Educational Technology International
• /
• v.22 no.2
• /
• pp.255-283
• /
• 2021

In the early 2020, COVID-19 changed the traditional way of teaching and learning. This paper aimed to explore the impact of college students' perception of course quality on their online learning satisfaction. A total of 4,812 valid samples were extracted, and the difference analysis and hierarchical regression analysis were used to make an empirical analysis of college students' online learning satisfaction. The research results were as follows. Firstly, there was no difference in online learning satisfaction among students by gender and grade. Secondly, learning assessment, course materials, course activities and learner interaction, and course production had a significant positive impact on online learning satisfaction. Course overview and course objectives had an insignificant correlation with online learning satisfaction. Thirdly, the total effect of online learning satisfaction was as follows. Course production had the greatest effect, followed by course activities and student-student interactions, followed by course materials. It was the learning evaluation that showed the least effect. This study can provide empirical reference for college teachers on how to continuously improve online teaching and increase students' satisfaction with online learning.

• Knowledge Management Research
• /
• v.10 no.1
• /
• pp.17-32
• /
• 2009

Cyber University has been continuously increased since it is of great necessity of education through lifelong study. Recently, the management of cyber universities does not ensure education success, because some problems are coming out. Now we are to take an interest in qualitative level of e-learning. The purpose of this study is to classify and investigate interaction factors of e-learning, which were one of the restrictions to develop e-learning, influence learning flow and satisfaction. The authors discuss the implications of the findings for interaction and learning flow theory and practice.

• Korea Journal of Hospital Management
• /
• v.9 no.2
• /
• pp.1-22
• /
• 2004

This study was designed to suggest a learning organization in a medical center by examining the factors to influence effectiveness of the learning organization. We collected the data of 586 persons who participated once or more times in the learning organization managed from 2000 to 2002 by Y Medical Center located in Seoul, and included the data of 285 persons in the final analysis. The results of the study are summarized as follows. First, as the results of examining the regression coefficients to predict the effectiveness of and satisfaction with the learning organization through the learning level, learning method and learning organization constructing level as the general variables, the important influential factors were shown as follows: 1)knowledge creation, knowledge storing, private learning, organizational learning, and learning organization construction of occupational and human levels as the factors to predict the working competency; 2) learning organization construction of the human level as the factors to assume the duty satisfaction; 3) gender, working years, private learning, team learning and organizational construction level for the prediction of the organizational commitment; and 4) medical technical service, knowledge creation, organization learning, and constructing level of the environmental and human levels for the assumption of the satisfaction with experience in the learning organization. Based on the study results of the effects in managing the learning organization, we can conclude the followings. First, the members who are in various working positions and occupations need to continuously participate in the learning organization. Second, to raise the organizational outcome from the management of the learning organization, it is necessary to establish systematic concepts in the constituents of the organizational effectiveness such as working competency improvement, duty satisfaction and organizational commitment, and the experience satisfaction of the learning organization. Finally, the future of the organization depends on the learning competencies of the organization members. To continuously exist and develop the organization, the private learning of the organizational members should be constantly spread and shared over the organizational level, and the usual innovations such as repetitive and habitual organizational learning should be generally tried out throughout the whole field of the management.

• 제어로봇시스템학회:학술대회논문집
• /
• 1990.10a
• /
• pp.186-189
• /
• 1990

The automization of manufacturing lines may be accomplished by replacing the human operator with computer system. This paper describes an idea to fully automize the razor qrinding process. Now, in this system, to control the process, human operator must estimate the qrinded states and control the grinding machine continuously. We propose two methods to automize this process by using CMAC memory. One is about learning expert-rules without direct communication with operator. And the other is complete self-learning method based on CMAC's learning algorithm. These ideas may be applied for another manufacturing processes.

• The Transactions of the Korea Information Processing Society
• /
• v.4 no.7
• /
• pp.1759-1769
• /
• 1997

The Error BackPropagation (EBP) algorithm for multi-layered neural networks is widely used in various areas such as associative memory, speech recognition, pattern recognition and robotics, etc. Nevertheless, many researchers have continuously published papers about improvements over the original EBP algorithm. The main reason for this research activity is that EBP is exceeding slow when the number of neurons and the size of training set is large. In this study, we developed new learning speed acceleration methods using variable learning rate, variable momentum rate and variable slope for the sigmoid function. During the learning process, these parameters should be adjusted continuously according to the total error of network, and it has been shown that these methods significantly reduced learning time over the original EBP. In order to show the efficiency of the proposed methods, first we have used binary data which are made by random number generator and showed the vast improvements in terms of epoch. Also, we have applied our methods to the binary-valued Monk's data, 4, 5, 6, 7-bit parity checker and real-valued Iris data which are famous benchmark training sets for machine learning.

• Journal of Electrical Engineering and Technology
• /
• v.10 no.1
• /
• pp.408-421
• /
• 2015

Because the wheel of V-belt continuously variable transmission (CVT) system driven by permanent magnet synchronous motor (PMSM) has much unknown nonlinear and time-varying characteristics, the better control performance design for the linear control design is a time consuming job. In order to overcome difficulties for design of the linear controllers, a hybrid recurrent Chebyshev neural network (NN) control system is proposed to control for a PMSM servo-driven V-belt CVT system under the occurrence of the lumped nonlinear load disturbances. The hybrid recurrent Chebyshev NN control system consists of an inspector control, a recurrent Chebyshev NN control with adaptive law and a recouped control. Moreover, the online parameters tuning methodology of adaptive law in the recurrent Chebyshev NN can be derived according to the Lyapunov stability theorem and the gradient descent method. Furthermore, the optimal learning rate of the parameters based on discrete-type Lyapunov function is derived to achieve fast convergence. The recurrent Chebyshev NN with fast convergence has the online learning ability to respond to the system's nonlinear and time-varying behaviors. Finally, to show the effectiveness of the proposed control scheme, comparative studies are demonstrated by experimental results.

• Journal of Korean Elementary Science Education
• /
• v.25 no.1
• /
• pp.15-26
• /
• 2006

This study investigated the characteristics of contents of the Atmosphere and Weather in the elementary science curriculum. For this study, elementary science textbooks reflecting the elementary science curriculum from 1st to 7th were analyzed with a number of tools. The results were as follows: Several parts of the contents about Atmosphere and Weather were dealt continuously through the all of science curriculum. Atmospheric Pressure, Humidity and Atmospheric Pressure and Weather were applied at the fifth grade above continuously. And Cloud$\cdot$Fog$\cdot$Dew was applied at the third and fifth grade. Quantity of learning about Atmosphere was more than it's of Weather always. Especially, Movement of Atmosphere and Temperature Change were maintained continuously above $10\%$ of the contents about Atmosphere and Weather. Some of the detailed learning themes related Atmosphere and Weather were dealt commonly through the all of the elementary science curriculum. Finally, the results showed that the contents of Physical Nature of Atmosphere, Atmospheric Pressure, Movement of Atmosphere, Temperature and it's Change and Cloud$\cdot$Fog$\cdot$Dew had been learned always with the experiments and practical training.