• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2003.09a
• /
• pp.300-303
• /
• 2003

An Algorithm based on direct implementation of variable structure systems theory approach is proposed for on-line training of multilayer perceptrons. Network structures which have multiple inputs, single output and one hidden layer are considered and the weights are assumed to have capabilities for continuous time adaptation. The zero level set of the network learning error is regarded as a sliding surface in the learning parameters space. A sliding mode trajectory can be brought on and reached in finite time on such a sliding manifold. Results from simulated on-line identification task for a two-link planar manipulator dynamics are also presented.

• Journal of the Korean Operations Research and Management Science Society
• /
• v.25 no.3
• /
• pp.1-15
• /
• 2000

In this paper, we propose a practical cut generation method based on the Chvatal-Gomory procedure for the (0, 1)-Knapsack problem with a variable capacity. For a given set N of n items each of which has a positive integral weight and a facility of positive integral capacity, a feasible solution of the problem is defined as a subset S of N along with the number of facilities that can satisfy the sum of weights of all the items in S. We first derive a class of valid inequalities for the problem using Chvatal-Gomory procedure, then analyze the associated separation problem. Based on the results, we develop an affective cut generation method. We then analyze the theoretical strength of the inequalities which can be generated by the proposed cut generation method. Preliminary computational results are also presented which show the effectiveness of the proposed cut generation method.

• Journal of Power System Engineering
• /
• v.18 no.3
• /
• pp.36-41
• /
• 2014

The structure of a variable liquid column oscillator(a VLCO) is analogous to that of the tuned liquid column damper used to suppress oscillatory motion in large structures like tall buildings and cargo ships. The VLCO is a system absorbing high kinetic energy of accelerated motions of the multiple floating bodies in the effect of air springs occurred by installation of inner air chambers. Thus, VLCO can improve the efficiency of energy than wave energy converters of the activating object type made in Pelamis Company. In this research, the experiment was performed in two models of same draft. The one is that weights were filled, and the other is that water was filled. The numerical results were estimated by assuming that do not exist internal flow, and the results were compared with the results of experiments.

• The Transactions of the Korean Institute of Power Electronics
• /
• v.2 no.1
• /
• pp.39-45
• /
• 1997

In this paper, a high speed motor drive system using an indirect adaptive neural network controller is proposed. In the variable high speed motor drives, the speed response can be deteriorated by long settling time and high overshoot. To obtain a good dynamical performance, an adaptive feedforward controller consisted of Neural Network Controller(NNC) and Neural Network Emulator(NNE) is applied. The NNE is used to identify the parameters and characteristics of high speed motor. To train the controller, the weights are dynamically adjusted using the back propagation algorithm. Computer simulation and implementation of the proposed system is described.

• The Korean Journal of Applied Statistics
• /
• v.30 no.6
• /
• pp.993-1004
• /
• 2017

A stratified sampling method is generally used with a sample selected using the same sample weight in each stratum in order to improve the accuracy of the sampling survey estimation. However, the weight should be adjusted to reflect the response rate if the response rate is affected by the value of the variable of interest. It may be also more effective to adjust the weights by subdividing the stratum rather than using the same weight if the variable of interest has a linear relationship with the continuous auxiliary variables. In this study, we propose a method to increase the accuracy of estimation using an informative sampling design technique when the response rate is an exponential function of the variable of interest and the variable of interest has a linear relationship with the auxiliary variable. Simulation results show the superiority of the proposed method.

• The Korean Journal of Applied Statistics
• /
• v.25 no.2
• /
• pp.261-267
• /
• 2012

In constructing a credit scorecard, each characteristic variable is divided into a few attributes; subsequently, weights are assigned to those attributes in a process called coarse classification. While partitioning a characteristic variable into attributes, one should determine appropriate cutpoints for the partition. In this paper, we propose a cutpoint selection method via penalization. In addition, we compare the performances of the proposed method with classification spline machine (Koo et al., 2009) on both simulated and real credit data.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.21 no.4
• /
• pp.463-468
• /
• 2011

Context prediction methods have been developed in two ways - one is a prediction for discrete context and the other is for continuous context. As most of the prediction methods have been used with prediction algorithms in specific domains suitable to the environment and characteristics of contexts, it is difficult to conduct a prediction for a user's context which is based on various environments and characteristics. This study suggests a context prediction method available for both discrete and continuous contexts without being limited to the characteristics of a specific domain or context. For this, we conducted a context prediction based on sequence matching by generating sequences from contexts in consideration of association rules between context attributes and by applying variable weights according to each context attribute. Simulations for discrete and continuous contexts were conducted to evaluate proposed methods and the results showed that the methods produced a similar performance to existing prediction methods with a prediction accuracy of 80.12% in discrete context and 81.43% in continuous context.

• Journal of Korean Society of Forest Science
• /
• v.107 no.2
• /
• pp.184-192
• /
• 2018

In this study was implemented to develop tree stem weight prediction equation of Larix kaempferi in central region by selecting a standard site, taking into account of diameter and position of the local trees. Fifty five sample trees were selected in total. By utilizing actual data of the sample trees, 11 models were compared and analyzed in order to estimate four different kinds of weights which include fresh weight, ovendry outside bark weight, ovendry inside bark weight and merchantable weight. As to estimate its weight, the study has classified its model according to three parameters: DBH, DBH and height, and volume. The optimal model was chosen by comparing the performance of model using the fit index and standard error of estimate and residual distribution. As a result, the formula utilizing DBH (Variable 1) is $W=a+bD+cD^2$ (3) and its fit index was 90~92%. The formula for DBH and height (Variable 2) is $W=aD^bH^C$ (8) and its fit index was 97~98%. In summation, Variable 2 model showed higher fitness than Variable 1 model. Moreover, fit index of formula for total volume and merchantable volume (W=aV) showed high rate of 98~99%, as well as resulting 7.7-17.5 with SEE and 8.0-10.0 with CV(%) which lead to predominately high fitness in conclusion. This study is expected to provide information on weights for single trees and furthermore, to be used as a basic study for weight of stand unit and biomass estimation equations.

• Proceedings of the KSME Conference
• /
• 2004.11a
• /
• pp.840-845
• /
• 2004

The reliability analysis for nonnormal distributions using the three level DOE(design of experiments) method was developed by Seo and Kwak in 2002. Although this method estimates only up to the first four moments(mean, standard deviation, skewness, and kurtosis) of the system response function, the result and the type of probability distribution determined by using the Pearson system are shown very good. However the accuracy is low in case of nonlinear performance function and sometimes, the level calculated is outside of the region in which the random variable is defined. In this article we suggest a modified three level DOE method to overcome these weaknesses and to obtain optimum choice for 3 levels and weights to handle nonnormal distributions. Furthermore we extend it to finding the optimum choice for 5 levels and weights to increase the accuracy in case of nonlinear performance function. A systematic procedure for reliability analysis is then proposed by using the Pearson system.

• Journal of the Korean Institute of Illuminating and Electrical Installation Engineers
• /
• v.25 no.4
• /
• pp.45-56
• /
• 2011

This paper is proposed artificial neural network(ANN) rotor resistance estimation of induction motor drive controlled by multi-adaptive fuzzy learning controller(AFLC). A simple double layer feedforward ANN trained by the back-propagation technique is employed in the rotor resistance identification. In this estimator, double models of the state variable estimations are used; one provides the actual induction motor output states and the other gives the ANN model output states. The total error between the desired and actual state variables is then back propagated to adjust the weights of the ANN model, so that the output of this model tracks the actual output. When the training is completed, the weights of the ANN correspond to the parameters in the actual motor. The estimation and control performance of ANN and multi-AFLC is evaluated by analysis for various operating conditions. Also, this paper is proposed the analysis results to verify the effectiveness of this controller.