• 제어로봇시스템학회:학술대회논문집
• /
• 1986.10a
• /
• pp.90-94
• /
• 1986

This paper describes expansion of the state space pole assignment self-tuning control of SISO systems with system noise and abservation noise to that of MIMO systems. Resursive Prediction Error method is used for both parameter and state estimation in the block controllable canonical form. This simplifies the state feedback law by eliminating the online computation of transformation matrix.

• 제어로봇시스템학회:학술대회논문집
• /
• 1986.10a
• /
• pp.367-369
• /
• 1986

Guaranteed cost control is a method applicable to a class of systems with uncertain parameters that guarantees an upper bound of the cost functional. This paper is concerned with a matrix decomposition technique used to yield a reasonable upper bound of the cost functional for a finite-time LQ regulator problem. The uncertain linear systems dealt with in this paper are described by a set of state equations of single-input phase-variable canonical form which contain unknown but bounded uncertain parameters.

• Journal of the Korean Data and Information Science Society
• /
• v.19 no.4
• /
• pp.1327-1334
• /
• 2008

Mixed effect binomial regression models are widely used for analysis of correlated count data in which the response is the result of a series of one of two possible disjoint outcomes. In this paper, we consider kernel extensions with nonparametric fixed effects and parametric random effects. The estimation is through the penalized likelihood method based on kernel trick, and our focus is on the efficient computation and the effective hyperparameter selection. For the selection of hyperparameters, cross-validation techniques are employed. Examples illustrating usage and features of the proposed method are provided.

• The Transactions of the Korean Institute of Electrical Engineers D
• /
• v.53 no.6
• /
• pp.395-401
• /
• 2004

By using an adaptive algorithm, together with an additional dynamic system, this paper proposes a new approach to design of a state observer for a class of uncertain systems. We enlarge the class of linear systems from the canonical form of [1] by proposing an adaptive observer that allows unknown parameters to affect those unmeasured states. The result is based on a recent result which presents a design algorithm for an additional system to replace output derivative measurements with the additional dynamics. A numerical example illustrates the design procedure of the state observer.

• Bulletin of the Korean Chemical Society
• /
• v.8 no.1
• /
• pp.19-26
• /
• 1987

A statistical thermodynamical treatment for polymer adsorption from solution is presented. The canonical partition function for the polymer solution in the presence of a surface or an impermeable interface is formulated on the basis of usual quasi-crystalline lattice model, Bragg-Williams approximation of random mixing, and Pak's simple treatment of liquid. The present theory gives the surface excess ${\Gamma}_{exc}$ and the surface coverage ${\phi}^s_2$ of the polymer as a function of the chain length x, the Flory-Huggins parameter x, the adsorption energy parameter $x_s$, and polymer concentration $v_2$. Present theory is also applicable to the calculation of interfacial tension of polymer solution against water. For the idealized flexible polymer, interfacial tensions according to our theory fit good to the experimental data to the agreeable degrees.

• ETRI Journal
• /
• v.42 no.6
• /
• pp.922-931
• /
• 2020

A hierarchical iterative algorithm for the canonical polyadic decomposition (CPD) of tensors is proposed by improving the traditional conjugate gradient least squares (CGLS) method. Methods based on algebraic operations are investigated with the objective of estimating the direction of arrival (DoA) and polarization parameters of signals impinging on an array with electromagnetic (EM) vector-sensors. The proposed algorithm adopts a hierarchical iterative strategy, which enables the algorithm to obtain a fast recovery for the highly collinear factor matrix. Moreover, considering the same accuracy threshold, the proposed algorithm can achieve faster convergence compared with the alternating least squares (ALS) algorithm wherein the highly collinear factor matrix is absent. The results reveal that the proposed algorithm can achieve better performance under the condition of fewer snapshots, compared with the ALS-based algorithm and the algorithm based on generalized eigenvalue decomposition (GEVD). Furthermore, with regard to an array with a small number of sensors, the observed advantage in estimating the DoA and polarization parameters of the signal is notable.

• Communications for Statistical Applications and Methods
• /
• v.15 no.6
• /
• pp.1003-1011
• /
• 2008

Mixed-effect Poisson regression models are widely used for analysis of correlated count data such as those found in longitudinal studies. In this paper, we consider kernel extensions with semiparametric fixed effects and parametric random effects. The estimation is through the penalized likelihood method based on kernel trick and our focus is on the efficient computation and the effective hyperparameter selection. For the selection of hyperparameters, cross-validation techniques are employed. Examples illustrating usage and features of the proposed method are provided.

• Journal of the Korean Institute of Telematics and Electronics
• /
• v.23 no.4
• /
• pp.450-454
• /
• 1986

In this paper a complexity reduction method in a linear system is studied. The poles to be retained are selected by the dominancy and the values of residues at respective poles. The reduced order model is obtained by the aggregation method, and the aggregation matrix is determined by the eigenvectors of a controllable canonical form. We consider the markov parameter and the time-moment at the same time, thereby getting rid of the steady-state errors. The input-output matrices are obtained using a chained aggregation matrix, and application of this method is illustrated by example.

• Journal of KSNVE
• /
• v.9 no.1
• /
• pp.196-205
• /
• 1999

The existence. bifurcation. and the orbital stability of periodic motions, which is called nonlinear normal mode, in a nonlinear dual mass Hamiltonian system. which has 6th order homogeneous polynomial as a nonlinear term. are studied in this paper. By direct integration of the equations of motion. Poincare Map. which is a mapping of a phase trajectory onto 2 dimensional surface in 4 dimensional phase space. is obtained. And via the Birkhoff-Gustavson canonical transformation, the analytic expression of the invariant curves in the Poincare Map is derived for small value of energy. It is found that the nonlinear system. which is considered in this paper. has 2 or 4 nonlinear normal modes depending on the value of nonlinear parameter. The Poincare Map clearly shows that the bifurcation modes are stable while the mode from which they bifurcated out changes from stable to unstable.

• The Bulletin of The Korean Astronomical Society
• /
• v.37 no.1
• /
• pp.48.1-48.1
• /
• 2012

We present the ultraviolet (UV) color-color relation of early-type galaxies (ETGs) in the nearby universe (0.05 < z < 0.12) to investigate the properties of hot stellar populations responsible for the UV excess (UVX). The initial sample of ETGs is selected by the spectroscopic redshift and the morphology parameter from the SDSS DR 7, and then cross-matched with the GALEX far-UV (FUV) and near-UV (NUV) GR6 data. The cross-matched ETG sample is further classified by their emission line characteristics in the optical spectra into quiescent, star-forming, and active galactic nucleus categories. Contaminations from early-type spiral galaxies, mergers, and morphologically disturbed galaxies are removed by visual inspection. By drawing the FUV-NUV (as a measure of UV spectral shape) versus FUV-r (as a measure of UVX strength) diagram for the final sample of -3700 quiescent ETGs, we find that the "old and dead" ETGs consist of a well-defined sequence in UV colors, the "UV red sequence," so that the stronger UVX galaxies should have a harder UV spectral shape systematically. However, the observed UV spectral slope is too steep to be reproduced by the canonical stellar population models in which the UV flux is mainly controlled by age or metallicity parameters. Moreover, 2 mag of color spreads both in FUV-NUV and FUV-r appear to be ubiquitous among any subsets in distance or luminosity. This implies that the UVX in ETGs could be driven by yet another parameter which might be even more influential than age or metallicity.