• 한국수학교육학회지시리즈E:수학교육논문집
• /
• 제23권2호
• /
• pp.175-196
• /
• 2009

본 연구는 수학교과의 수준별 교수-학습 자료의 이론적 뒷받침에 관련된 문헌연구로, Ziv의 교수학적 자료에 제시된 하수준과 중수준에 해당하는 교수-학습 자료들을 수학문제의 내적구조라는 관점에서 분석하여, 하수준 문제들의 특징들, 중수준 문제들의 특징들을 조사하였다.

• 한국공간구조학회논문집
• /
• 제20권2호
• /
• pp.51-58
• /
• 2020

Recently, deep learning that is the most popular and effective class of machine learning algorithms is widely applied to various industrial areas. A number of research on various topics about structural engineering was performed by using artificial neural networks, such as structural design optimization, vibration control and system identification etc. When nonlinear semi-active structural control devices are applied to building structure, a lot of computational effort is required to predict dynamic structural responses of finite element method (FEM) model for development of control algorithm. To solve this problem, an artificial neural network model was developed in this study. Among various deep learning algorithms, a recurrent neural network (RNN) was used to make the time history response prediction model. An RNN can retain state from one iteration to the next by using its own output as input for the next step. An eleven-story building structure with semi-active tuned mass damper (TMD) was used as an example structure. The semi-active TMD was composed of magnetorheological damper. Five historical earthquakes and five artificial ground motions were used as ground excitations for training of an RNN model. Another artificial ground motion that was not used for training was used for verification of the developed RNN model. Parametric studies on various hyper-parameters including number of hidden layers, sequence length, number of LSTM cells, etc. After appropriate training iteration of the RNN model with proper hyper-parameters, the RNN model for prediction of seismic responses of the building structure with semi-active TMD was developed. The developed RNN model can effectively provide very accurate seismic responses compared to the FEM model.

• 한국정보통신학회:학술대회논문집
• /
• 한국정보통신학회 2018년도 춘계학술대회
• /
• pp.466-467
• /
• 2018

최근 이미지 인식, 영상 인식, 음성 인식, 자연어 처리 등 다양한 분야에 인공지능이 적용되면서 딥러닝(Deep learning) 기술에 관한 관심이 높아지고 있다. 딥러닝 중에서도 가장 대표적인 알고리즘으로 이미지 인식 및 분류에 강점이 있고 각 분야에 많이 쓰이고 있는 CNN(Convolutional Neural Network)에 대한 많은 연구가 진행되고 있다. 본 논문에서는 일반적인 CNN 구조를 변형한 새로운 네트워크 구조를 제안하고자 한다. 일반적인 CNN 구조는 convolution layer, pooling layer, fully-connected layer로 구성된다. 그러므로 본 연구에서는 일반적인 CNN 구조 내부에 FC를 첨가한 새로운 네트워크를 구성하고자 한다. 이러한 변형은 컨볼루션된 이미지에 신경회로망이 갖는 장점인 일반화 기능을 포함시켜 정확도를 올리고자 한다.

• 한국전자통신학회논문지
• /
• 제17권3호
• /
• pp.483-490
• /
• 2022

말라리아는 기생충에 의해 발생하는 질병으로 전 세계에 퍼져있다. 말라리아 셀을 인식하는데 일반적으로 두꺼운 혈흔과 얇은 혈흔 검사 방법이 사용되지만 이러한 방법은 많은 수작업 계산이 필요하여 효율성과 정확성이 매우 낮을 뿐만 아니라 빈민국에는 병리학자가 부족하여 말라리아 치명율이 높다. 본 논문에서는 특징 추출기, 잔류 구조와 완전 연결층으로 구성되고, 전이 학습을 이용한 말라리아셀 이미지를 인식하는 모델을 제안한다. VGG-19 모델의 사전 학습된 파라미터가 사용될 때 일부 컨볼루션층의 파라미터는 고정되고, 모델의 데이터에 맞추기 위하여 미세조정이 사용된다. 그리고 제안된 모델과 비교하기 위하여 잔류 구조가 없는 말라리아셀 인식 모델을 구현한다. 실험 결과 잔류 구조를 사용한 모델이 잔류 구조가 없는 모델에 비하여 성능이 우수 하였으며, 최신 논문과 비교하여 가장 높은 97.33%의 정확도를 보여주었다.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2005년도 ICCAS
• /
• pp.941-946
• /
• 2005

In this paper an active random noise control using adaptive learning rate neural networks is presented. The adaptive learning rate strategy increases the learning rate by a small constant if the current partial derivative of the objective function with respect to the weight and the exponential average of the previous derivatives have the same sign, otherwise the learning rate is decreased by a proportion of its value. The use of an adaptive learning rate attempts to keep the learning step size as large as possible without leading to oscillation. It is expected that a cost function minimize rapidly and training time is decreased. Numerical simulations and experiments of active random noise control with the transfer function of the error path will be performed, to validate the convergence properties of the adaptive learning rate Neural Networks. Control results show that adaptive learning rate Neural Networks control structure can outperform linear controllers and conventional neural network controller for the active random noise control.

• Journal of Information Technology Applications and Management
• /
• 제15권3호
• /
• pp.261-273
• /
• 2008

The starting point of knowledge generation and management is the enhancement of learning capability and capacity of organizational members. Organizational change for learning environment should be aligned with the change of organizational strategy, structure and processes. The study employed action learning methodology to constitute learning organization processes. The treatment effect to institute learning organization has been successful thanks to the members' zeal and consensus to change the processes. However, not every learning team has been so successful. Some cases complained time consuming where others expect to be helpful for their incentives. The researchers concluded that the most important point for success of the learning organization project should be the support of top management.

• 디지털융복합연구
• /
• 제2권1호
• /
• pp.43-56
• /
• 2004

The emergence of distance learning through Information and Communication Technologies(ICT) requires a lot of abilities from learners, and these become main features to a successful learning. Accordingly, a self-regulated learning is one of the key abilities required by the learners, Hence this study is aimed to develop Web-Based Instruction(WBI) systems that support this self-regulated learning. The self-regulated learning not only provides significant positive learning effects, but also appropriates to apply on the WBI because it has learning-structure of specified instruction process and each process requires separated spaces. Therefore, in this study, a model of self-regulated learning system on the web is developed.

• 교육녹색환경연구
• /
• 제3권1호
• /
• pp.15-23
• /
• 2003

Focusing on both the form of open classroom and that of independent one which have been most planned and being built, this study was designed to see if the educational environment of their inner space, structure, and facilities gives a proper support to classroom activities during the various classes based on open education. Selecting representative teaching methods in elementary school, such as open simultaneous learning, learning through a medium, learning in the corner, subject learning, team teaching and learning hardening basics, this study surveyed problems and improvements using literature works, questionnaires, observing, and interviews. Through the study on learning space for open education, it has been known that the form of independent classroom fits into one classroom learning and open classroom into small group learning and individual learning, and that the form of open classroom connecting open space with a classroom are more desirable when there is change from large to small group.

• 한국멀티미디어학회논문지
• /
• 제24권7호
• /
• pp.868-879
• /
• 2021

PCB (Printed Circuit Board) inspection using a deep learning model requires a large amount of data and storage. When the amount of stored data increases, problems such as learning time and insufficient storage space occur. In this study, the existing object detection model is changed to a continual learning model to enable the recognition and classification of PCB components that are constantly increasing. By changing the structure of the object detection model to a knowledge distillation model, we propose a method that allows knowledge distillation of information on existing classified parts while simultaneously learning information on new components. In classification scenario, the transfer learning model result is 75.9%, and the continual learning model proposed in this study shows 90.7%.

• 한국정보과학회논문지:컴퓨팅의 실제 및 레터
• /
• 제15권12호
• /
• pp.983-987
• /
• 2009

유아들의 언어습득에 있어서 중요한 점 하나는 학습자에 대한 언어환경의 노출이다. 유아가 접하는 언어환경은 부모와 같은 인간뿐만 아니라 각종 미디어와 같은 인공적 환경도 포함되며, 유아는 이러한 방대한 언어환경을 탐색하면서 언어를 학습한다. 본 연구는 대용량의 언어 데이터 노출이 영향을 미치는 유아언어학습을 유연하고 적절하게 모사하는 인지적 기제에 따른 기계학습 방식을 제안한다. 유아의 초기 언어학습은 문장수준의 학습과 생성 같은 행동들이 수반되는데, 이는 언어 코퍼스에 대한 노출만으로 모사가 가능하다. 모사의 핵심은 언어 하이퍼망 구조를 가진 기억기반 학습모델이다. 언어 하이퍼망은 언어구성 요소들 간의 상위차원 관계 표상을 가능케 함으로써 새로운 데이터 스트림에 대해 유사구조의 적용과 이용을 도모하여 발달적이고 점진적인 학습을 모사한다. 본 연구에서는 11 개의 유아용 비디오로부터 추출한 문장 32744개를 언어 하이퍼망을 통한 점진적 학습을 수행하여 문장을 생성해 유아의 점진적, 발달적 학습을 모사하였다.