I. Kollar, Frequency Domain System Identification Toolbox.The MathWorks Inc., 1994. 769  Home/Search Document Details and Download
Summary Related Articles Check |
This paper is cited in the following contexts:
The RPM Toolbox: A System for Fitting Linear Models to Frequency.. - Pfeffer (1993) (1 citation) (Correct)
....the system, most control design techniques require the use of some form of parametric model. Techniques to identify models from frequency response data are manifold (examples include [5, 6] or [7] which has a good overview) Another MATLAB based identification toolbox is being developed by Kollar [8]. These techniques are generally referred to as complex curve fitting algorithms, and the RPM framework toolbox is such a system. Complex curve fitting algorithms can be classified according to the type of systems they can be applied to, the form of model they use, and the type of cost ....
I. Kollar, R. Pintelon, and J. Schoukens. Frequency domain system identification toolbox for matlab. In Proceedings of the 9th IFAC/IFORS Symposium on Identification and System Parameter Estimation, pages 1243--46, Oxford, England, July 1991. Pergamon Press. (Conf. in Budapest) .
Variance of Fourier Coefficients Calculated from.. - Laszlo Balogh Istvan (2002) (1 citation) Self-citation (Kollar) (Correct)
....calculated Fourier coefficients. Keywords parameter estimation, variance reduction, overlapped segments, frequency domain system identification, Fourier coefficient, variance analysis. I. INTRODUCTION The widely accepted way of preprocessing data for frequency domain system identification is [1] to measure the steady state response and the input signal of a system using periodic excitation, slice up the input and output signals into periods, calculate the Fourier coefficients of each period at the excited frequencies, perform averaging and variance analysis over the calculated Fourier ....
I. Kollar, Frequency Domain System Identification Toolbox for Matlab, The MathWorks, Inc., Natick, MA, 1994, current version: http://elecwww.vub.ac.be/fdident/.
Generalization of a Total Least Squares Problem in Frequency.. - Balogh, Kollar (2001) Self-citation (Kollar) (Correct)
....properties of the new method in practice. Keywords system identification, total least squares, generalized eigenvalues, TLS, frequency domain, initial value setting I. INTRODUCTION Parametric system identification usually concludes in the estimation of unknown parameters in a model ( 1] 2] [3]) The estimation of the parameters can be done in many different ways. For the sake of short computing time and numerical simplicity, our goal is usually to cast the problem in the form of a set of linear equations. Because of the distortions and noises in the measurement process, we consider an ....
....likelihood (ML) cost function is a possible candidate for this. Maximum likelihood (ML) estimation is the best we can do in many cases if identification of a system is required. Unfortunately, in frequency domain system identification the maximum likelihood method leads a nonlinear problem ([3], 2] Therefore, we cannot apply efficient numerical algorithms such as WTLS. Nevertheless the maximum likelihood has good statistically properties (see [3] 1] To obtain the ML cost function from (5) the matrix W has to be the following: W 2 ML (j k ; p) N(j k ; p)CU (j k )N H (j ....
[Article contains additional citation context not shown here]
Istvan Kollar, Frequency Domain System Identification Toolbox, Gamax, 2001, http://elecwww.vub.ac.be/fdident/.
Generalization of a Total Least Squares Problem in Frequency.. - Istvan Self-citation (Kollar) (Correct)
....properties of the new method in practice. Keywords system identification, total least squares, generalized eigenvalues, TLS, frequency domain, initial value setting I. INTRODUCTION Parametric system identification usually concludes in the estimation of unknown parameters in a model ( 1] 2] [3]) The estimation of the parameters can be done in many different ways. For the sake of short computing time and numerical simplicity, our goal is usually to cast the problem in the form of a set of linear equations. Because of the distortions and noises in the measurement process, we consider an ....
....likelihood (ML) cost function is a possible candidate for this. Maximum likelihood (ML) estimation is the best we can do in many cases if identification of a system is required. Unfortunately, in frequency domain system identification the maximum likelihood method leads a nonlinear problem ([3], 2] Therefore, we cannot apply efficient numerical algorithms such as WTLS. Nevertheless the maximum likelihood has good statistically properties (see [3] 1] To obtain the ML cost function from (5) the matrix has to be the following: Y ML dv 0 O dv d ....
[Article contains additional citation context not shown here]
Istvan Kollar, Frequency Domain System Identification Toolbox, Gamax, 2001, http://elecwww.vub.ac.be/fdident/.
Parametric and Nonparametric Identification and.. - Tavakoli, Taghirad, .. (2003) (Correct)
No context found.
I. Kollar, Frequency Domain System Identification Toolbox.The MathWorks Inc., 1994. 769
Online articles have much greater impact More about CiteSeer.IST Add search form to your site Submit documents Feedback
CiteSeer.IST - Copyright Penn State and NEC