• 제어로봇시스템학회논문지
• /
• 제8권7호
• /
• pp.607-612
• /
• 2002

An automatic design method of behaviors in behavior-based robotics is proposed. With this method, a robot can design its behaviors by itself without aids of human designer. Automating design procedure of behaviors can make the human designer free from somewhat tedious endeavor that requires to predict all possible situations in which the robot will work and to design a suitable behavior for each situation. A simple reinforcement learning strategy is the main frame of this method and the key parameter of the learning process is significant change of reward value. A successful application to mobile robot navigation is reported too.

• 로봇학회논문지
• /
• 제16권1호
• /
• pp.35-40
• /
• 2021

As the robot industry develops, industrial automation uses industrial robots in many parts of the manufacturing industry. However, rigidity-based conventional robots have a disadvantage in that they are challenging to use in environments where they grab fragile objects or interact with people because of their high rigidity. Therefore, researches on soft robot have been actively conducted. The soft robot can hold or manipulate fragile objects by using its compliance and has high safety even in an atypical environment with human interaction. However, these advantages are difficult to use in dynamic situations and control by the material's nonlinear behavior. However, for the soft robot to be used in the industry, control is essential. Therefore, in this paper, real-time PD control is applied, and the behavior of the soft actuator is analyzed by providing various waveforms as inputs. Also, Iterative learning control (ILC) is applied to reduce errors and select an ILC type suitable for soft actuators.

• 한국신뢰성학회지:신뢰성응용연구
• /
• 제18권1호
• /
• pp.20-32
• /
• 2018

Purpose: The purpose of this study is to set up an anomaly detection criteria for sensor data coming from a motorcycle. Methods: Five sensor values for accelerator pedal, engine rpm, transmission rpm, gear and speed are obtained every 0.02 second from a motorcycle. Exploratory data analysis is used to find any pattern in the data. Traditional process control methods such as X control chart and time series models are fitted to find any anomaly behavior in the data. Finally unsupervised learning algorithm such as k-means clustering is used to find any anomaly spot in the sensor data. Results: According to exploratory data analysis, the distribution of accelerator pedal sensor values is very much skewed to the left. The motorcycle seemed to have been driven in a city at speed less than 45 kilometers per hour. Traditional process control charts such as X control chart fail due to severe autocorrelation in each sensor data. However, ARIMA model found three abnormal points where they are beyond 2 sigma limits in the control chart. We applied a copula based Markov chain to perform statistical process control for correlated observations. Copula based Markov model found anomaly behavior in the similar places as ARIMA model. In an unsupervised learning algorithm, large sensor values get subdivided into two, three, and four disjoint regions. So extreme sensor values are the ones that need to be tracked down for any sign of anomaly behavior in the sensor values. Conclusion: Exploratory data analysis is useful to find any pattern in the sensor data. Process control chart using ARIMA and Joe's copula based Markov model also give warnings near similar places in the data. Unsupervised learning algorithm shows us that the extreme sensor values are the ones that need to be tracked down for any sign of anomaly behavior.

• 디지털산업정보학회논문지
• /
• 제13권3호
• /
• pp.149-165
• /
• 2017

This study is to discover and substantiate the casual relation between Learning Organization and Organizational Citizenship Behavior, with Supervisor Trust used as moderating variable. Learning Organization and Organization Citizenship Behavior are used, respectively, as independent and dependent variable, Supervisor Trust as moderating variable. The data for this study was collected from 340 public officials who participated in the training program. Data collection tools were used to collect structured questionnaire questionnaires, and dissemination and retrieval of questionnaires were carried out over 6 weeks from February 6 to March 10, 2017. Of the questionnaire distributed, the questionnaire was finally recovered from the questionnaire, with a recall rate of 91.8 %, showing a very high rate of recall. The result showed that Learning Organization is a significant factor for Organization Citizenship Behavior and also that Supervisor Trust plays a role in the control of the relationship between Learning Organization and Organization Citizenship Behavior; thus, in order for Public Organizations to achieve advanced competitiveness, vitalizations of Learning Organization is important.

• 한국산학기술학회논문지
• /
• 제15권3호
• /
• pp.1396-1403
• /
• 2014

이 연구는 학습역량 관련 지식, 창의성, 동기로 구성된 Hope프로그램이 대학생의 창의성, 문제해결, 학습동기, 학습행동에 미치는 영향을 규명하고자 시도되었다. 연구대상자들은 총 49명이었으며 Hope프로그램은 8월 26일부터 9월 13일까지 3주 동안 14시간에 걸쳐 운영되었다. 사전 사후 검사를 거쳐 실험집단과 대조집단에게 창의성, 문제해결, 학습동기, 학습행동을 검사하였다. 사전검사에서 두 집단의 동질성이 확보되지 않아, 실험 후 공분산분석(ANCOVA)을 실시하였으며, 그 결과 Hope프로그램을 실시한 실험집단과 대조집단은 창의성, 문제해결, 학습동기, 학습행동 점수에서 유의한 차이를 나타내었다(p<.05).

• Journal of Ginseng Research
• /
• 제18권1호
• /
• pp.39-43
• /
• 1994

This study was performed to investigate the effect of ginseng saponin from Korean red ginseng on the learning and memory. Total (50, 100 mg/kg, bw) and panaxadiol saponin (15, 30 mg/kg, bw) treated groups did not show the difference of the time score and the number of error in comparison with control group. Panaxatriol saponin (15, 30 mg/kg, bw) significantly decreased both the time score and the number of error in water maze test. These results indicate that panaxatriol saponin from Korean red ginseng may improve the learning ability of rat in water multiple T-maze.

• Human Ecology Research
• /
• 제53권6호
• /
• pp.641-654
• /
• 2015

This study identifies and tracks changes gender differences in adolescent users' problematic online behavior. This study used Korea Youth Panel Survey (KYPS), which has tracked respondents over 7 years, with self-control theory and social learning theory applied as a theoretical framework. The model included individual-level variables such as self-control and respondent's experience of problematic behavior (offline), as well as socialization variables such as the number close friends who engaged in problematic offline behavior, parent-child relationships, and parental monitoring. Dependent variables included problematic online behavior, unauthorized ID use (ID theft) and cyberbullying (cursing/insulting someone in a chat room or on a bulletin board). Control variables consisted of academic performance, time spent on a computer, monthly household income, and father's educational attainment. Random and fixed effects models were performed by gender. Results supported self-control theory even for the within-level analysis (fixed effects models) regardless of gender, while social learning theory was partially supported. Only peer effects were found significant (except for unauthorized ID use) among girls. Year dummy variables showed significant negative associations; however, academic performance and time spent using computers were significant in some models. Father's educational attainment and monthly household income were found insignificant, even in the random effects models. We also discuss implications and suggestions for future research and policy makers.

• International Journal of Advanced Culture Technology
• /
• 제10권2호
• /
• pp.162-173
• /
• 2022

In non-face-to-face teaching-learning, a survey was conducted on 55 students in the department of chemistry education at university A on the variables (behavioral control, instructor-learner interaction, cognitive learning) affecting learning satisfaction and academic achievement. There were relatively large positive correlations between variables. The positive correlation between them was found to be the factors that influenced learning satisfaction and academic achievement in non-face-to-face teaching-learning. The average values of non-face-to-face teaching-learning for each variable were lower than the corresponding values of face-to-face teaching-learning, respectively. As a result of the perception survey on the detailed factors of each variable, negative responses were relatively high in factors such as 'concentration of behavior' in behavioral control, 'level-considered explanation' in instructor-learner interaction, and 'knowledge understanding' in cognitive learning.

• 한국초등과학교육학회지:초등과학교육
• /
• 제33권1호
• /
• pp.69-81
• /
• 2014

This study was to find out the effects of out-of-class environmental experience learning on elementary students' environmental literacy. For this study, we developed and applied environmental education program utilizing out-of-class facilities and ecological park for the 5th-grade students. The subjects of this study were the 5th grade students of an elementary school located in Si-hung city. The study was carried out for two groups, an experiment group of 29 students and control group of 29 students. The education program using out-of-class environmental experience learning was provided to the experiment group while lecture-oriented education program was provided to the control group. The questionnaire used in this study to assess the environmental literacy of the study objects consists of 41 questions under 4 domains (knowledge, emotion, skill, behavior). After observing and analyzing the effects of out-of-class environmental experience learning on students' environmental literacy, we found that the program using the out-of-class environmental experience learning posed greater impacts than lecture-oriented program. By domains, environmental literacy in 3 domains illustrated positive improvement. In particular, skill domain illustrated much more improvement in environmental literacy. But, domain of behavior didn't illustrated improvement in environmental literacy. The result of this study signified that the out-of-class environmental experience learning has positive and effective impact on the environmental literacy. And out-of-class environmental experience learning is more suitable to improve the skill domain of the environmental literacy than lecture-oriented learning. But, it is couldn't improve the domain of behavior. Therefore, in order to improve behavior domain, the program must apply with effective evaluation and home training.

• Smart Structures and Systems
• /
• 제31권3호
• /
• pp.247-257
• /
• 2023

In structural health monitoring of large-scale structures, optimal sensor placement plays an important role because of the high cost of sensors and their supporting instruments, as well as the burden of data transmission and storage. In this study, a vibration sensor placement algorithm based on deep reinforcement learning (DRL) is proposed, which can effectively solve non-convex, high-dimensional, and discrete combinatorial sensor placement optimization problems. An objective function is constructed to estimate the quality of a specific vibration sensor placement scheme according to the modal assurance criterion (MAC). Using this objective function, a DRL-based algorithm is presented to determine the optimal vibration sensor placement scheme. Subsequently, we transform the sensor optimal placement process into a Markov decision process and employ a DRL-based optimization algorithm to maximize the objective function for optimal sensor placement. To illustrate the applicability of the proposed method, two examples are presented: a 10-story braced frame and a sea-crossing bridge model. A comparison study is also performed with a genetic algorithm and particle swarm algorithm. The proposed DRL-based algorithm can effectively solve the discrete combinatorial optimization problem for vibration sensor placements and can produce superior performance compared with the other two existing methods.