• Journal of Korea Water Resources Association
• /
• v.52 no.12
• /
• pp.963-973
• /
• 2019

This study reviews a urban flooding risk criteria estimation model to predict risk criteria in areas where flood risk criteria are not precalculated by using watershed characteristic data and limit rainfall based on damage history. The risk criteria estimation model was designed using Support Vector Machine, one of the machine learning algorithms. The learning data consisted of regional limit rainfall and watershed characteristic. The learning data were applied to the SVM algorithm after normalization. We calculated the mean absolute error and standard deviation using Leave-One-Out and K-fold cross-validation algorithms and evaluated the performance of the model. In Leave-One-Out, models with small standard deviation were selected as the optimal model, and models with less folds were selected in the K-fold. The average accuracy of the selected models by rainfall duration is over 80%, suggesting that SVM can be used to estimate flooding risk criteria.

• Proceedings of the Optical Society of Korea Conference
• /
• 1991.06a
• /
• 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.

• Education of Primary School Mathematics
• /
• v.2 no.1
• /
• 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 .

• Journal of the Korean Institute of Intelligent Systems
• /
• v.18 no.5
• /
• pp.712-717
• /
• 2008

In swarm robot systems, each robot must act by itself according to the its states and environments, and if necessary, must cooperate with other robots in order to carry out a given task. Therefore it is essential that each robot has both learning and evolution ability to adapt the dynamic environments. In this paper, reinforcement learning method with SVM based on structural risk minimization and distributed genetic algorithms is proposed for behavior learning and evolution of collective autonomous mobile robots. By distributed genetic algorithm exchanging the chromosome acquired under different environments by communication each robot can improve its behavior ability. Specially, in order to improve the performance of evolution, selective crossover using the characteristic of reinforcement learning that basis of SVM is adopted in this paper.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.14 no.6
• /
• 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.

• Journal of Internet Computing and Services
• /
• v.9 no.6
• /
• pp.127-139
• /
• 2008

The value of up-to-date Mobile PC such as UMPC (Ultra Mobile Personal Computer) is recognized greatly in learning environment that busywork such as characteristic of transfer easy and real time communication possibility etc. and conversation with a colleague student, free sending of studying data and public ownership etc. is required. Wish to recognize whether is acting relevant role in u - unfold learning that inflect UMPC in integration research model, and UMPC is u searching for relevant element at studying activity unfolding process u - integration Inquiry-Based Learning that present in Korean education & research information service (KERIS) at fifth-year student science time In primary school in this research. This research result could take charge role of UMPCs' studying-activity though there is persistent feedback with teacher among studying-activity although UMPC's role is utilized on constituent that can be related with studying-activity in learning process.

• Journal of Institute of Control, Robotics and Systems
• /
• v.3 no.6
• /
• 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.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.56 no.7
• /
• 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.

• Journal of the Korean housing association
• /
• v.9 no.3
• /
• 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
• /
• v.19 no.spc1
• /
• 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.