• The Korean Journal of Applied Statistics
• /
• v.21 no.4
• /
• pp.659-664
• /
• 2008

Missing continuous covariates are pervasive in the use of generalized linear models for medical data. Multiple imputation is the most common and easy-to-do method of dealing with missing covariate data. However, there are always serious warnings in using this method. There should be concern to make imputed values more proper. In this paper, proper imputation from posterior predictive distribution is developed for implementing with arbitrary priors. We use empirical distribution of the posterior for approximating the posterior predictive distribution, to sample from it. This method is preferable in comparison with a presented imputation method of us which uses a full model to impute missing values using available software. The proposed methods are implemented on glucocorticoid data.

• Magazine of the Korean Society of Agricultural Engineers
• /
• v.41 no.4
• /
• pp.57-65
• /
• 1999

A modified gas tracer method was used to obtain reaeration coefficient from an artificial channel and a reach of Bokha stream, Ichon city. Propane was used as the tracer gas and Rhodamine-B dye as a dispersion and dulution tracer. Concentrations of propane in water sample were measured using a gas chromatograph and concentrationsof dye using UV-Spectrophotometer. To compare measured values with predicted values,commonly used 14 equations were selected . Results of this study suggested that the modified gas tracer method is a potentially useful procedure for th edetermination of reaeration cofficients. However, estimated reaeration coefficients from predictive equations were significantly different from that of this study. Therefore, when using predictive equations, careful selection of equation with consideration for hydraulic characteristics such as flow depth and average velocity, or use of newly derived predictive equation which is adequate for questioned stream would be needed.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2002.12a
• /
• pp.183-186
• /
• 2002

In this paper, a predictive control method using wavelet neural network for chaotic nonlinear systems is presented. In our method, we use the adjusting method of the parameter for the training a wavelet neural network. The control signals are directly obtained by minimizing the difference between a reference signal and the output of a wavelet neural network. To verify the efficiency of our method, we apply it to the Duffing and the Henon system, which are a representative continuous and discrete time chaotic nonlinear system respectively.

• Proceedings of the KIPE Conference
• /
• 2015.07a
• /
• pp.522-523
• /
• 2015

This paper proposes a deadbeat current controller using predictive current method for three-phase shunt active power filter (SAPF). In proposed controller, the compensating current reference which is necessary for the deadbeat control is estimated by using the predictive current method. This method can improve the accuracy of compensation and ensure the fast dynamic response of SAPF. Simulations have been carried out to demonstrate the perfomance of SAPF using proposed control method.

• Proceedings of the KIPE Conference
• /
• 2016.07a
• /
• pp.359-360
• /
• 2016

This paper presents a new predictive current control (PCC) method to achieve the coordinate control of power and current of the matrix converter under unbalanced input voltages. In order to control the power fluctuation in the input side, the flexible source current reference is generated based on the positive-negative sequence components of the input voltage. The optimal switching state to adjust source and load currents is selected by minimization the cost function which is obtained from the sum of the absolute errors between the current references and their predictive values. Simulation results are given to validate the effectiveness of the proposed PCC method.

• 제어로봇시스템학회:학술대회논문집
• /
• 1995.10a
• /
• pp.51-55
• /
• 1995

An adaptive unified predictive control (UPC) algorithm is applied to a batch polymerization reactor for poly(methyl methancrylate) (PMMA) and the effects of controller parameters are investigated. Computational studies are performed for a batch polymerization system model developed in this study. A transfer function in parametric form is estimated by recursive least squares (RLS) method, and the UPC algorithm is implemented to control the reactor temperature on the basis of this transfer function. The adaptive unified predictive controller shows a better performance than the PID controller for tracking set point changes, especially in the latter part of reaction course when gel effect becomes significant. Various performance can be acquired by selecting adequate values for parameters of the adaptive unified predictive controller; in other words, the optimal set of parameters exists for a given set of reaction conditions and control objective.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.30 no.11A
• /
• pp.1021-1026
• /
• 2005

In this paper, we present a novel predictive CDMA closed-loop power control (CLPC) method with a multi-step least squares (LS) linear predictor for time-varying fading channels. The proposed method effectively compensates multiple power control group delays and provides significant performance gains over nonpredictive CLPCs as well as conventional predictive CLPCs with one-step linear predictor.

• International Journal of Control, Automation, and Systems
• /
• v.3 no.1
• /
• pp.43-55
• /
• 2005

In this paper, a predictive control method using self-recurrent wavelet neural network (SRWNN) is proposed for chaotic systems. Since the SRWNN has a self-recurrent mother wavelet layer, it can well attract the complex nonlinear system though the SRWNN has less mother wavelet nodes than the wavelet neural network (WNN). Thus, the SRWNN is used as a model predictor for predicting the dynamic property of chaotic systems. The gradient descent method with the adaptive learning rates is applied to train the parameters of the SRWNN based predictor and controller. The adaptive learning rates are derived from the discrete Lyapunov stability theorem, which are used to guarantee the convergence of the predictive controller. Finally, the chaotic systems are provided to demonstrate the effectiveness of the proposed control strategy.

• International Journal of Control, Automation, and Systems
• /
• v.6 no.1
• /
• pp.126-134
• /
• 2008

As many systems depend on electronics, concern for fault tolerance is growing rapidly. For example, a car with its steering controlled by electronics and no mechanical linkage from steering wheel to front tires (steer-by-wire) should be fault tolerant because a failure can come without any warning and its effect is devastating. In order to make system fault tolerant, there has been a body of research mainly from aerospace field. This paper presents the structure of predictive hybrid redundancy that can remove most erroneous values. In addition, several numerical simulation results are given where the predictive hybrid redundancy outperforms wellknown average and median voters.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.60 no.7
• /
• pp.1360-1365
• /
• 2011

Electro-hydraulic servo motor is used to a lot of in the field of industrial equipment which requires one of the control functions among pressure, flow, and power output. In this paper, linear discrete reference model of the electro-hydraulic servo motor system are made for 1-step ahead predictive control. The parameters of electro-hydraulic servo motor system are estimated using the recursive least square method. 1-step ahead predictive model output of electro-hydraulic servo motor system corresponded to reference model output in spite of estimated parameters are not meet real parameters. Control performance affections are studied due to the forgetting factors variation.