• 한국수자원학회논문집
• /
• 제52권12호
• /
• pp.963-973
• /
• 2019

본 연구는 도시침수 위험기준이 산정되지 않은 지역의 예·경보 기준을 예측하기 위해 유역특성 자료와 피해이력 기반으로 산정된 한계강우량을 활용하여 도시침수 위험기준을 추정하는 모델을 검토하였다. 위험기준 추정모델은 머신러닝 알고리즘의 하나인 Support Vector Machine을 이용하여 설계하였으며, 학습자료는 지역별 한계강우량과 유역특성으로 구성하였다. 학습자료는 정규화 한 후 SVM 알고리즘에 적용하였으며, SVM에 적용시 Leave-One-Out과 K-fold 교차검증 알고리즘을 이용하여 절대평균오차와 표준편차를 계산한 후 모델의 성능을 평가하였다. Leave-One-Out의 경우 표준편차가 작은 모델이 최적모델로 선정되었으며, K-fold의 경우 fold의 개수가 적은 모델이 선정되었다. 선정된 모델의 지속시간별 평균 정확도는 80% 이상으로 나타나 침수 위험기준 추정을 위해 SVM을 활용가능 할 것으로 판단된다.

• 한국광학회:학술대회논문집
• /
• 한국광학회 1991년도 제6회 파동 및 레이저 학술발표회 Prodeedings of 6th Conference on Waves and Lasers
• /
• pp.23-28
• /
• 1991

A single-layer neural network with 4$\times$4 input neurons and 4 output neurons is optically implemented. Holographic lenslet arrays are used for the e optical interconnection topology, a liquid crystal light valve(LCLV) is used for controlling optical interconection weights. Using a Perceptron learning rule, it classifics input patterns into 4 different categories. It is shown that the performance of the adaptive neural network depends on the learning rate, the correlation of input patterns, and the nonlinear characteristic properties of the liquid crystal light valve.

• 한국수학교육학회지시리즈C:초등수학교육
• /
• 제2권1호
• /
• pp.15-26
• /
• 1998

Teachers beliefs for the mathematics can have a powerful impact on how children go about learning mathematics, and theirs mathematical beliefs and abilities. In this study, \circled1 to divided teacher's mathematical beliefs into three - absolutism, progressive absolutism, constructivism - and to search into a theoretical characteristic, \circled2 to analyze and criticize the problems of the behaviorism and to investigate a point of basic view of the constructivism on mathematics education, \circled3 to suggest teacher's a role in mathematics learning be based on the constructivism perspective .

• 한국지능시스템학회논문지
• /
• 제18권5호
• /
• pp.712-717
• /
• 2008

군집 로봇시스템에서 개개의 로봇은 스스로 주위의 환경과 자신의 상태를 스스로 판단하여 행동하고, 필요에 따라서는 다른 로봇과 협조를 통하여 어떤 주어진 일을 수행할 수 있어야 한다. 따라서 개개의 로봇은 동적으로 변화하는 환경에 잘 적응할 수 있는 학습과 진화능력을 갖는 것이 필수적이다. 본 논문에서는 구조적 위험 최소화를 기반으로 한 SVM을 이용 한 강화학습과 분산유전알고리즘을 이용한 새로운 자율이동로봇의 행동학습 및 진화방법을 제안한다. 또한 개개의 로봇이 통신을 통하여 염색체를 교환하는 분산유전알고리즘은 각기 다른 환경에서 학습한 우수한 염색체로부터 자신의 능력을 향상시킨다. 특히 본 논문에서는 진화의 성능을 향상시키기 위하여 SVM을 기반으로 한 강화학습의 특성을 이용한 선택 교배 방법을 채택하였다.

• 대한임베디드공학회논문지
• /
• 제14권6호
• /
• pp.287-294
• /
• 2019

With the automation of production lines in the manufacturing industry, the importance of real-time fault diagnosis of facility is increasing. In this paper, we propose a fault diagnosis algorithm of LM (Linear Motion)-guide based on deep learning using vibration signals. Generally, in order to guarantee the performance of the deep learning, it is necessary to have a sufficient amount of data, but in a manufacturing industry, it is often difficult to obtain enough data due to physical and time constraints. To solve this problem, we propose a convolutional neural networks (CNN) model based on transfer learning. In addition, the spectrogram image is input to the CNN to reflect the frequency characteristic of the vibration signals with time. The performance of fault diagnosis according to various load condition and transfer learning method was compared and evaluated by experiments. The results showed that the proposed algorithm exhibited an excellent performance.

• 인터넷정보학회논문지
• /
• 제9권6호
• /
• pp.127-139
• /
• 2008

UMPC(Ultra Mobile Personal Computer)와 같은 최첨단 모바일 PC는 이동용이성과 실시간 의사소통 가능성 등의 특징과 동료학생과의 대화, 학습 자료의 자유로운 송부 및 공유 등과 같은 학습활동이 요구되는 학습 환경에서 그 가치를 크게 인정받고 있다. 본 연구에서는 초등학교 5학년 과학시간에 한국학술정보원(KERIS)에서 제시한 u-러닝통합탐구모형을 중심으로 UMPC를 활용하는 수업을 전개하고, 학습 활동전개과정에서 의미 있는 요소를 찾아내어 UMPC가 u-러닝에서 의미 있는 역할을 하고 있는지 알아보고자 하였다. 본 연구결과에서 UMPC의 역할은 수업전개에서 학습활동과 관계가 될 수 있는 요소로 활용되지만 학습활동 중에 교사와 지속적인 피드백이 있어야만 UMPC가 학습활동의 역할을 담당할 수 있었다.

• 제어로봇시스템학회논문지
• /
• 제3권6호
• /
• pp.555-562
• /
• 1997

With only the classical PID controller applied to control of a DC motor, good (target) performance characteristic of the controller can be obtained if all the model parameters of DC motor and operating conditions such as external load torque, disturbance, etc. are known exactly. However, in case when some of system parameters or operating conditions are uncertain or unknown, the fixed PID controller does not guarantee good performance, which is assumed with precisely known system parameters and operating conditions. In view of this and the robustness enhancement of DC motor control system, we propose a PID learning controller which consists of a set of learning rules for PID gain tuning and learning of an auxiliary input. The proposed PID learning controller is shown to drive the state of uncertain DC motor system with unknown system parameters and external load torque to the desired one world wide asymptotically. Computer simulation and experimental results are given to demonstrate the effectiveness of the proposed PID learning controller, thereby showing its superiority to the conventional fixed PID controller.

• 전기학회논문지
• /
• 제56권7호
• /
• pp.1315-1320
• /
• 2007

In this paper, we introduce a new fuzzy model called fuzzy combined polynomial neural networks, which are based on the representative fuzzy model named polynomial fuzzy model. In the design procedure of the proposed fuzzy model, the coefficients on consequent parts are estimated by using not general least square estimation algorithm that is a sort of global learning algorithm but weighted least square estimation algorithm, a sort of local learning algorithm. We are able to adopt various type of structures as the consequent part of fuzzy model when using a local learning algorithm. Among various structures, we select Polynomial Neural Networks which have nonlinear characteristic and the final result of which is a complex mathematical polynomial. The approximation ability of the proposed model can be improved using Polynomial Neural Networks as the consequent part.

• 한국주거학회논문집
• /
• 제9권3호
• /
• pp.25-32
• /
• 1998

This study has carried out two steps. Firstly, the questionnaire was carried out in order to extract visual interference factors in the TV learning spaces. Secondly, on the basis of the questionnaire, it has been carried out two experiments in the TV learning space. In the experiment I, the preferable luminance of the characters and the preferable luminance ratios between the characters and backgrounds on the TV screen are extracted. In the experiment II, the preferable luminance distributions on the TV screen and its surrounding surfaces is found out. The data made in this study is expected to utilize in the lighting design on the TV learning spaces as guides.

• Journal of Mechanical Science and Technology
• /
• 제19권spc1호
• /
• pp.357-363
• /
• 2005

The non-minimum phase characteristic of a flexible manipulator makes tracking control of its tip difficult. The level of the tip tracking performance of a flexible manipulator is significantly affected by the characteristics of the tip reference trajectory as well as the characteristics of the flexible manipulator system. This paper addresses the question of how to best specify a reference trajectory for the tip of a flexible manipulator to follow in order to achieve the objectives of reducing : tip tracking error, residual tip vibration, and the required actuation effort at the manipulator joint. A novel method of tip-based learning controller for the flexible manipulator system is proposed in the paper, where a model of the flexible manipulator system with a command shaping filter is used to generate a smooth and realizable tip reference trajectory for a tip-based learning controller.