• 제어로봇시스템학회:학술대회논문집
• /
• 1996.10a
• /
• pp.95-98
• /
• 1996

Universal Learning Network(U.L.N.), which can model and control the large scale complicated systems naturally, consists of nonlinearly operated nodes and multi-branches that may have arbitrary time delays including zero or minus ones. Therefore, U.L.N. can be applied to many kinds of systems which are difficult to be expressed by ordinary first order difference equations with one sampling time delay. It has been already reported that learning algorithm of parameter variables in U.L.N. by forward and backward propagation is useful for modeling, managing and controlling of the large scale complicated systems such as industrial plants, economic, social and life phenomena. But, in the previous learning algorithm of U.L.N., time delays between the nodes were fixed, in other words, criterion function of U.L.N. was improved by adjusting only parameter variables. In this paper, a new learning algorithm is proposed, where not only parameter variables but also time delays between the nodes can be adjusted. Because time delays are integral numbers, adjustment of time delays can be carried out by a kind of random search procedure which executes intensified and diversified search in a single framework.

• Proceedings of the KSME Conference
• /
• 2001.06b
• /
• pp.105-109
• /
• 2001

This paper discuss the real-time self-tuning learning control based on evolutionary computation, which proves its the superiority in the finding of the optimal solution at the off-line learning method. The individuals are reduced in order to learn the evolutionary strategy in real-time, and new method that guarantee the convergence of evolutionary mutations are proposed. It possible to control the control object varied as time changes. As the state value of the control object is generated, applied evolutionary strategy each sampling time because the learning process of an estimation, selection, mutation in real-time. These algorithms can be applied, the people who do not have knowledge about the technical tuning of dynamic systems could design the controller or problems in which the characteristics of the system dynamics are slightly varied as time changes.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.27 no.9
• /
• pp.1463-1468
• /
• 2003

This paper presented the real-time self-tuning learning control based on evolutionary computation, which proves its superiority in finding of the optimal solution at the off-line learning method. The individuals of the populations are reduced in order to learn the evolutionary strategy in real-time, and new method that guarantee the convergence of evolutionary mutations is proposed. It is possible to control the control object slightly varied as time changes. As the state value of the control object is generated, evolutionary strategy is applied each sampling time because the learning process of an estimation, selection, mutation is done in real-time. These algorithms can be applied; the people who do not have knowledge about the technical tuning of dynamic systems could design the controller or problems in which the characteristics of the system dynamics are slightly varied as time changes.

• The Journal of Korean Association of Computer Education
• /
• v.17 no.1
• /
• pp.65-73
• /
• 2014

The purpose of this study is to examine how time management, usefulness, and interest predict m-learning outcomes. For this study, 144 high school students participated in m-learning activities during science classes. After 5 week of classes, they responded the following surveys: time management, usefulness, interest, satisfaction, perceived achievement and learning persistence. Multiple regression analyses with correlation applied to this study as a data analysis method. The results showed that time management, usefulness, interest significantly predicted learning satisfaction and persistence. In addition, time management and usefulness significantly predicted perceived achievement, Therefore, these findings imply that time management, usefulness should be considered for designing m-learning activities in high school science class.

• Journal of Korea Society of Industrial Information Systems
• /
• v.16 no.5
• /
• pp.93-105
• /
• 2011

This study was performed to figure out the effects of perceived usefulness and ease of use in Technology Acceptance Model(TAM) affecting acceptance attitude and intention to use in smart learning. In addition, the study recognized the need for differentiation of learning time by analyzing the difference of effects influencing acceptance attitude of perceived usefulness and ease of use during learning time, which is at the beginning, midterm, and at the end of the term. As the results of the study, it showed that there were differences between the factors, the learning time of which was considered, affecting acceptance attitude and intention to use. Furthermore, in order to improve the effectiveness of building a smart campus, which is currently under the construction, the study argued that universities need to consider the learning relevance and subjective norm as important factors in perceived usefulness of smart learning. Finally, the need for the design of various smart learning types became accepted considering learning time.

• Journal of Information Processing Systems
• /
• v.8 no.3
• /
• pp.409-420
• /
• 2012

The decision-making by agents in games is commonly based on reinforcement learning. To improve the quality of agents, it is necessary to solve the problems of the time and state space that are required for learning. Such problems can be solved by Macro-Actions, which are defined and executed by a sequence of primitive actions. In this line of research, the learning time is reduced by cutting down the number of policy decisions by agents. Macro-Actions were originally defined as combinations of the same primitive actions. Based on studies that showed the generation of Macro-Actions by learning, Macro-Actions are now thought to consist of diverse kinds of primitive actions. However an enormous amount of learning time and state space are required to generate Macro-Actions. To resolve these issues, we can apply insights from studies on the learning of tasks through Programming by Demonstration (PbD) to generate Macro-Actions that reduce the learning time and state space. In this paper, we propose a method to define and execute Macro-Actions. Macro-Actions are learned from a human subject via PbD and a policy is learned by reinforcement learning. In an experiment, the proposed method was applied to a car simulation to verify the scalability of the proposed method. Data was collected from the driving control of a human subject, and then the Macro-Actions that are required for running a car were generated. Furthermore, the policy that is necessary for driving on a track was learned. The acquisition of Macro-Actions by PbD reduced the driving time by about 16% compared to the case in which Macro-Actions were directly defined by a human subject. In addition, the learning time was also reduced by a faster convergence of the optimum policies.

• Journal of Information Processing Systems
• /
• v.20 no.3
• /
• pp.345-359
• /
• 2024

A regression model represents the relationship between explanatory and response variables. In real life, explanatory variables often affect a response variable with a certain time lag, rather than immediately. For example, the marriage rate affects the birth rate with a time lag of 1 to 2 years. Although deep learning models have been successfully used to model various relationships, most of them do not consider the time lags between explanatory and response variables. Therefore, in this paper, we propose an extension of deep learning models, which automatically finds the time lags between explanatory and response variables. The proposed method finds out which of the past values of the explanatory variables minimize the error of the model, and uses the found values to determine the time lag between each explanatory variable and response variables. After determining the time lags between explanatory and response variables, the proposed method trains the deep learning model again by reflecting these time lags. Through various experiments applying the proposed method to a few deep learning models, we confirm that the proposed method can find a more accurate model whose error is reduced by more than 60% compared to the original model.

• The Journal of the Korea Contents Association
• /
• v.22 no.5
• /
• pp.643-655
• /
• 2022

The purpose of this study was to verify the moderating effect of parental learning involvement in the effect of adolescents' time management ability on face-to-face and non-face-to-face learning flow. The participants were 363 middle and high school adolescents, and data were collected through an online survey. The main statistical analysis methods were ANOVA, correlation analysis, and regression analysis. The major findings were as follows. First, learning flow was significantly higher in the face-to-face class than in the non-face-to-face class. Second, there was a statistically significant positive correlation among time management ability, parental involvement in learning, and learning flow. Third, in the effect of time management ability on face-to-face learning flow, the moderating effect of parental learning involvement was statistically significant. Fourth, in the effect of time management ability on non-face-to-face learning flow, the moderating effect of parental learning involvement was statistically significant. In other words, the higher the positive parental involvement in learning, the stronger the effect of adolescents' time management ability on learning flow. Finally, the importance of positive parental involvement for the improvement of adolescents' learning flow and methods of enhancing time management ability were discussed.

• 제어로봇시스템학회:학술대회논문집
• /
• 1989.10a
• /
• pp.1069-1074
• /
• 1989

A discrete-time learning control for robotic manipulators is studied using its pulse transfer function. Firstly, discrete-time learning stability condition which is applicable to single-input two-outputs systems is derived. Secondly, stability of learning algorithm with position signal is studied. In this case, when sampling period is small, the algorithm is not stable because of an unstable zero of the system. Thirdly, stability of algorithm with position and velocity signals is studied. In this case, we can stabilize the learning control system which is unstable in learning with only position signal. Finally, simulation results on the trajectory control of robotic manipulators using the discrete-time learning control are shown. This simulation results agree well with the analytical ones.

• Journal of Industrial Convergence
• /
• v.20 no.11
• /
• pp.157-164
• /
• 2022

This study attempted to understand the mediating effect of learning time in the effect of academic burnout on self-esteem of middle school students. To this end, a survey of 1,045 middle school students in Gyeongsangnam-do was conducted on academic burnout, learning time, and self-esteem. It was analyzed in four ways through questionnaire responses. First, as a result of analyzing the differences according to the collective characteristics of academic burnout, learning time, and self-esteem, there was no difference between groups, and self-esteem was significantly different by gender and grade. Second, as a result of correlation analysis, academic burnout and learning time showed a negative correlation with self-esteem, and learning time and self-esteem showed a positive correlation. Third, as a result of regression analysis, all learning times were partially mediated in the effect of academic burnout on self-esteem. This not only directly affects the self-esteem of middle school students, but also indirectly through learning time. Fourth, in the analysis by gender, it was confirmed that male students had no statistically significant effect on self-esteem, but female students had a significant statistical effect on self-esteem, so only female students had a partial mediating effect. As a result of the analysis by grade, the effect of learning time on self-esteem was significant in the 1st and 2nd graders of middle school, but the effect of learning time on self-esteem was not significant in the 3rd graders of middle school. Through the survey of this study, it was suggested that education and counseling should be conducted in the middle school period, which is a rapid growth period, considering that academic burnout has a different effect on learning time and self-esteem by grade as well as gender approach.