• The Journal of the Acoustical Society of Korea
• /
• v.13 no.6
• /
• pp.83-90
• /
• 1994

In this paper, we propose a new learning algorithm, ASOFM(Adaptive Self Organizing Feature Map), to solve the defects of Kohonen's Self Organiaing Feature Map. Kohonen's algorithm is sometimes stranded on local minima for the initial weights. The proposed algorithm uses an object function which can evaluate the state of network in learning and adjusts the learning rate adaptively according to the evaluation of the object function. As a result, it is always guaranteed that the state of network is converged to the global minimum value and it has a capacity of generalized learning by adaptively. It is reduce that the learning time of our algorithm is about $30\%$ of Kohonen's.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2003.05a
• /
• pp.47-50
• /
• 2003

기계학습의 한 종류인 분류자 시스템은 간단한 문제에 대하여 실시간 처리와 온라인 학습이 가능하다. 그러나 복잡한 환경에서는 빠른 적응이 힘들다. 본 논문에서는 복잡한 환경에서 분류자 시스템의 적응 성능을 개선함으로써 실시간이 가능하도록 전체 환경을 분류하고 각기 다른 룰 셋을 이용하는 룰 클러스터링에 의한 분류자 시스템을 제안한다 환경을 상황에 따라 나눔으로써 전체 환경이 변화하였을 경우 각 상황에 따른 변화에 대해서만 추가적으로 학습함으로써 탐색 공간을 줄여 학습 시간을 감소시킨다. 제안한 시스템은 분류자 시스템 중 ZCS을 이용하여 로봇축구 시스템에 적용하여 기존의 방법과 그 성능을 비교 검토한다.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2020.11a
• /
• pp.140-142
• /
• 2020

본 논문에서는 심층적 강화학습 기반 GOP (Group of Picture) 크기를 선택하여 HEVC/H.265의 인코더를 제어하는 방법을 제안한다. 기존 방법에서는 현재 비디오 신호를 부호화 하는 과정에서 이미 부호화한 정보를 사용해야하는 부호화 의존성에 관한 문제가 있었다. 제안 방법은 강화학습 방식을 도입하여 이러한 문제를 극복하고 입력 비디오의 시간적 상관도에 따라 GOP의 크기를 적응적으로 선택하여 부호화 한다. 본 논문에서는 GOP 선택을 위한 강화학습 환경을 새롭게 정의하고 부호화 성능에 따른 보상을 부여하는 방식으로 학습을 수행한다. 제안된 적응적 GOP 선택에 따라 인코더 제어 시, 부호화 방법의 부호화 효율이 -6.07% BD-rate 향상된 실험 결과를 보이며 본 방법의 우수성을 입증한다.

• Journal of Korean Home Economics Education Association
• /
• v.19 no.3
• /
• pp.169-183
• /
• 2007

The purpose of this study is to examine the effects of self-esteem, relationships with parents and peer relationships on adolescents' school adjustment. Total of 900 middle school students residing in Guri, Geonggi-Do participated in the survey and the data collected from 874 students (557 male and 317 female students) were analyzed for this study. The followings summarize results of the study. First, the findings suggested that there is no significant difference between female and male students in school adjustment. Secondly, the study revealed that there is no difference between female and male students in self-esteem and relationship with parents. Thirdly, this study provided clear evidence that students with high self-esteem and close relationship with parents and schoolmates adapt to school life better than those with low self-esteem and distant relationship with parents and schoolmates. Fourthly, students with high self-esteem and close relationship with parents and schoolmates displayed higher adaptability to school life, and as for male students, close relationship with schoolmates was the most prominent factor which helps them adapt to school life better while female students' adaptability to school lifewas mainly affected by relationship with parents.

• Journal of the Korea Convergence Society
• /
• v.10 no.1
• /
• pp.299-305
• /
• 2019

The purpose of study was to investigate the effects of career decision efficacy, learning Flow, and academic achievement on department adaptation of dental hygiene students. The subjects of the study are self-administered surveys of 200 students who indicated their intention to participate. 181 questionnaires were analyzed using SPSS 18.0. The results of this study show that career decision efficacy, learning flow, academic achievement affect to major satisfaction, major confidences, major attachment. The results of this study show that career decision efficacy, academic achievement affect to major vision. Some dental hygienists students need support systems such as learning methods and educational environment that can improve academic achievement and learning commitment in order to help students adapt to their department. In addition, education and career support for career decision efficacy should be continuously maintained.

• Journal of KIISE:Software and Applications
• /
• v.35 no.1
• /
• pp.33-40
• /
• 2008

In this paper, we propose a method to enhance adaptability in a dialogue system using the reinforcement learning that reduces response errors by trials and error-search similar to a human dialogue process. The adaptive dialogue strategy means that the dialogue system improves users' satisfaction and dialogue efficiency by loaming users' dialogue styles. To apply the reinforcement learning to the dialogue system, we use a main-dialogue span and sub-dialogue spans as the mathematic application units, and evaluate system usability by using features; success or failure, completion time, and error rate in sub-dialogue and the satisfaction in main-dialogue. In addition, we classify users' groups into beginners and experts to increase users' convenience in training steps. Then, we apply reinforcement learning policies according to users' groups. In the experiments, we evaluated the performance of the proposed method on the individual reinforcement learning policy and group's reinforcement learning policy.

• Journal of Korea Multimedia Society
• /
• v.5 no.1
• /
• pp.59-67
• /
• 2002

In this paper, I discuss the problems of developing web based adaptive hypermedia for education using extensible Markup Language(XML). Adaptive hypermedia systems are capable of altering the Presentation of the contents of the hypermedia on the basis of a dynamic understanding of the individual student. The student profile is contained in a student model, while the knowledge about the domain can be represented in the form of a concept based domain model. Accordingly, I define two different markup languages using XML. The one structures the domain model and the another describes the student model. These language can be easily extended and authored, with the result of obtaining a simple methodology for data structuring in the field of web based educational adaptive hypermedia.

• Journal of IKEEE
• /
• v.24 no.4
• /
• pp.998-1003
• /
• 2020

In this paper, an emotion training method using emotional adaptation is proposed to improve the performance of the existing emotion recognition system. For emotion adaptation, an emotion speech model was created from a speech model without emotion using a small number of training emotion voices and emotion adaptation methods. This method showed superior performance even when using a smaller number of emotional voices than the existing method. Since it is not easy to obtain enough emotional voices for training, it is very practical to use a small number of emotional voices in real situations. In the experimental results using a Korean database containing four emotions, the proposed method using emotional adaptation showed better performance than the existing method.

• Proceedings of the Korean Information Science Society Conference
• /
• 2001.10b
• /
• pp.55-57
• /
• 2001

강화학습은 한 에이전트가 자신이 놓여진 환경으로부터의 보상을 최대화할 수 있는 최적의 행동 전략을 학습하는 것이다. 따라서 강화학습은 입력(상태)과 출력(행동)의 쌍으로 명확한 훈련 예들이 제공되는 교사 학습과는 다르다. 특히 Q-학습과 같은 비 모델 기반(model-free)의 강화학습은 사전에 환경에 대한 별다른 모델을 설정하거나 학습할 필요가 없으며 다양한 상태와 행동들을 충분히 자주 경험할 수만 있으면 최적의 행동전략에 도달할 수 있어 다양한 응용분야에 적용되고 있다. 하지만 실제 응용분야에서 Q-학습과 같은 강화학습이 겪는 최대의 문제는 큰 상태 공간을 갖는 문제의 경우에는 적절한 시간 내에 각 상태와 행동들에 대한 최적의 Q값에 수렴할 수 없어 효과를 거두기 어렵다는 점이다. 이런 문제점을 고려하여 본 논문에서는 로봇 축구 시뮬레이션 환경에서 각 선수 에이전트의 동적 위치 결정을 위해 효과적인 새로운 Q-학습 방법을 제안한다. 이 방법은 원래 문제의 상태공간을 몇 개의 작은 모듈들로 나누고 이들의 개별적인 Q-학습 결과를 단순히 결합하는 종래의 모듈화 Q-학습(Modular Q-Learning)을 개선하여, 보상에 끼친 각 모듈의 기여도에 따라 모듈들의 학습결과를 적응적으로 결합하는 방법이다. 이와 같은 적응적 중재에 기초한 모듈화 Q-학습법(Adaptive Mediation based Modular Q-Learning, AMMQL)은 종래의 모듈화 Q-학습법의 장점과 마찬가지로 큰 상태공간의 문제를 해결할 수 있을 뿐 아니라 보다 동적인 환경변화에 유연하게 적응하여 새로운 행동 전략을 학습할 수 있다는 장점을 추가로 가질 수 있다. 이러한 특성을 지닌 AMMQL 학습법은 로봇축구와 같이 끊임없이 실시간적으로 변화가 일어나는 다중 에이전트 환경에서 특히 높은 효과를 볼 수 있다. 본 논문에서는 AMMQL 학습방법의 개념을 소개하고, 로봇축구 에이전트의 동적 위치 결정을 위한 학습에 어떻게 이 학습방법을 적용할 수 있는지 세부 설계를 제시한다.

• Journal of Korea Multimedia Society
• /
• v.12 no.5
• /
• pp.757-766
• /
• 2009

This study presents an adaptive hypermedia learning system which can provide individual learning environment using a learner behavioral model. This system proposes a LBML which can manage learners' learning behavioral information by tracking down such information real-time. The system consists of a collecting system of learning behavioral information and an adaptive learning support system. The collecting system of learning behavioral information uses Web 2.0 technologies and collects learners' learning behavioral information real-time based on a SCORM CMI data model. The collected information is stored as LBML instances of individual learners based on a LBML schema. With the adaptive learning support system, a rule-based learning supporting module and an interactive learning supporting module are developed by analysing LBML instances.