• 한국안전학회지
• /
• 제33권6호
• /
• pp.42-49
• /
• 2018

In this study, we have developed a prediction model for expansion and contraction behaviors of expansion joint in Gwangan Bridge using machine learning techniques and bridge monitoring data. In the development of the prediction model, two famous machine learning techniques, multiple regression analysis (MRA) and artificial neural network (ANN), were employed. Structural monitoring data obtained from bridge monitoring system of Gwangan Bridge were used to train and validate the developed models. From the results, it was found that the expansion and contraction behaviors predicted by the developed models are matched well with actual expansion and contraction behaviors of Gwangan Bridge. Therefore, it can be concluded that both MRA and ANN models can be used to predict the expansion and contraction behaviors of Gwangan Bridge without actual measurements of those behaviors.

• International Journal of Control, Automation, and Systems
• /
• 제1권1호
• /
• pp.142-148
• /
• 2003

Reinforcement learning is considered as an important tool for robotic learning in unknown/uncertain environments. In this paper, we propose an evaluation function expressed in a vector form to realize multi-dimensional reinforcement learning. The novel feature of the proposed method is that learning one behavior induces parallel learning of other behaviors though the objectives of each behavior are different. In brief, all behaviors watch other behaviors from a critical point of view. Therefore, in the proposed method, there is cross-criticism and parallel learning that make the multi-dimensional learning process more efficient. By ap-plying the proposed learning method, we carried out multi-dimensional evaluation (reward) and multi-dimensional learning simultaneously in one trial. A special neural network (Q-net), in which the weights and the output are represented by vectors, is proposed to realize a critic net-work for Q-learning. The proposed learning method is applied for behavior planning of mobile robots.

• Educational Technology International
• /
• 제11권2호
• /
• pp.43-75
• /
• 2010

The purpose of this study is to identify patterns of learner behaviors, conflicting and facilitating factors during collaborative work in an online learning community(OLC). This study further seeks to investigate the difference of learner behaviors between high- and low-performing groups, and conflicting and facilitating factors. The online postings from four groups(19 students) in the spring semester(study 1) and six groups(24 students) in the fall semester(study 2) were analyzed. A coding scheme was generated based on constant comparison using the qualitative data analysis tool, NVivo. The analysis identified 7 categories of learner behaviors in both studies. Among the seven categories, information seeking and co-construction were most frequently observed in both studies. One evident difference between the high- and low-performing groups was that the high-performing groups revealed more incidents of learner behaviors in both studies. In addition, six categories of conflicting factors and five categories of facilitating factors were emerged in both studies. The inefficiency of work category was one of the most frequently observed categories in both studies. Interestingly, the high-performing groups showed more incidents of conflicting factors than the low-performing groups. This study revealed two different types of conflicting factors and there is a need for different moderating strategies depending on its type. Based on the results of the study, effective design strategies for an OLC to facilitate active learning were suggested.

• 지식경영연구
• /
• 제3권1호
• /
• pp.1-18
• /
• 2002

Many organizations implement knowledge management initiates by developing knowledge management systems. This study aims at investigating knowledge sharing behaviors in a knowledge management system and identifying factors affecting such behaviors. To do this, we defined knowledge sharing behaviors in a knowledge management system as registration and view of knowledge at a system. Based on this definition, we established a research model by identifying seven factors affecting both behaviors as independent variables: Learning orientation, Pressure to share knowledge, Top management support, Reward for knowledge sharing, Level of experience in IT, System quality, and Knowledge quality. The 14 hypotheses derived from a research model were tested by a correlation analysis and a multiple regression analysis with data from 165 respondents of the 21 organizations which implemented knowledge management initiatives. As results, both of knowledge registration and knowledge review were strongly affected by the learning-orientedness of an organization. Finally, we discussed results and limitations of this study.

• 컴퓨터교육학회논문지
• /
• 제9권2호
• /
• pp.27-36
• /
• 2006

본 연구는 e-Learning 협력학습 기술 개발 지원을 위한 기반 연구로서, e-Learning 에서의 협력학습을 위한 기본모형 개발과 협력학습 활동에서 발생하는 학습자들의 학습행위요소를 세부적으로 분석 제시하는 것을 연구의 목적으로 하였다. 연구의 목적을 달성하기 위하여 면대면 교실수업에서 이루어져 온 다양한 협동학습 모형들을 분석하였으며, 면대면과 온라인 환경에서 협력학습 및 커뮤니케이션 활동을 강조하는 문제중심학습, 프로젝트 학습, 탐구학습, 토론학습 등 교수모형에 기초한 주요 학습모형들의 절차와 단계, 학습활동 등도 분석하였다. 연구 결과 e-Learning에서의 협력학습을 위한 일반 모형과 세부 학습행위요소들, 그리고 시스템적 지원기능들이 제시되었으며, 추후 연구를 위한 과제가 제안되었다.

• 디지털콘텐츠학회 논문지
• /
• 제19권1호
• /
• pp.35-41
• /
• 2018

강화학습기반 Q-learning 알고리즘은 이산적인 상태와 액션의 조합을 사용하여, 한 번에 하나의 행위에 대한 목표를 학습하는데 유용하다. 여러 액션을 학습하기 위해서는 행위 기반 아키텍처를 적용하고 적절한 행위 조절 방법을 사용하면 로봇으로 하여금 빠르고 신뢰성 있는 액션을 가능하게 할 수 있다. Q-learning은 인기 있는 강화학습 방법으로 단순하고, 수렴성이 있고 사전 훈련 환경에 영향을 덜 받는 특성(off-policy)으로 인해 로봇 학습에 많이 사용되고 있다. 본 논문에서는 Q-learning 알고리즘을 램프 로봇에 적용하여 복수 행위(사람인식, 책상의 물체 인식)를 학습시키는데 사용하였다. Q-learning의 학습속도(learning rate)는 복수 행위 학습 단계의 로봇 성능에 영향을 줄 수 있으므로 학습속도 변경을 통해 최적의 복수 행위 학습 모델을 제시한다.

• 한국정밀공학회:학술대회논문집
• /
• 한국정밀공학회 2003년도 춘계학술대회 논문집
• /
• pp.1105-1108
• /
• 2003

Adaptation in dynamic environments gains a significant advantage by combining evolution and learning. We propose an on-line, realtime evolutionary learning mechanism to determine the structure and the synaptic weights of a neural network controller for mobile robot navigations. We support our method, based on (1+1) evolutionary strategy, which produces changes during the lifetime of an individual to increase the adaptability of the individual itself, with a set of experiments on evolutionary neural controller for physical robots behaviors.

• 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.

• Asia pacific journal of information systems
• /
• 제26권1호
• /
• pp.66-79
• /
• 2016

The availability of detailed data on customers' online behaviors and advances in big data analysis techniques enable us to predict consumer behaviors. In the past, researchers have built purchase prediction models by analyzing clickstream data; however, these clickstream-based prediction models have had several limitations. In this study, we propose a new method for purchase prediction that combines information theory with machine learning techniques. Clickstreams from 5,000 panel members and data on their purchases of electronics, fashion, and cosmetics products were analyzed. Clickstreams were summarized using the 'entropy' concept from information theory, while 'random forests' method was applied to build prediction models. The results show that prediction accuracy of this new method ranges from 0.56 to 0.83, which is a significant improvement over values for clickstream-based prediction models presented in the past. The results indicate further that consumers' information search behaviors differ significantly across product categories.

• 한국지역사회생활과학회지
• /
• 제22권4호
• /
• pp.679-688
• /
• 2011

Using data from an ongoing study of 170 children aged 4-6 years in low-income families, this study tests how mothers' parenting behaviors and teacher-child relationship influences the adjustment to child-care centers of young children. The mothers' parenting behaviors were measured by the mothers of surveyed children, while the teacher-child relationship and children's adjustment were rated by teachers. Measurements were recorded from using the Iowa Parent Behavior Inventory(Crase et al. 1987), Student-Teacher Relationship Scale(Pianta et al. 1995) and the Adjustment to Child-care Centers Scale(Lee 2004). The collected data was analyzed by hierarchical regression using the SPSS Program. Results indicate that mothers' parenting behaviors in the low-income families controlled characteristics of children and are positively associated with one area of early school adjustment, learning readiness. In other words, mothers who are more involved and demonstrate supportive parenting, have children with better learning readiness. The teacher-child relationship is strongly related to all areas of children's adjustment. The interaction effect of parenting behaviors and the teacher-child relationship on children's learning readiness is observed. These results highlight the importance of the teacher-child closeness as well as the quality of parenting behaviors during the preschool period for the low-income family in improving early school adjustment.