62 research outputs found
Frequency domain identification of autoregressive models in the presence of additive noise
No full textThis paper describes a new approach for identifying autoregressive models from a finite number of measurements,
in presence of additive and uncorrelated white noise. As a major novelty, the proposed approach deals with
frequency domain data. In particular, two different frequency domain algorithms are proposed.
The first algorithm is based on some theoretical results concerning the so-called dynamic Frisch Scheme.
The second algorithm maps the AR identification problem into a quadratic eigenvalue problem.
Both methods resemble in many aspects some other identification algorithms, originally
developed in the time domain. The features of the proposed methods are compared each other
and with those of other time domain algorithms by means of Monte Carlo simulations
Frequency domain EIV identification combining the Frisch scheme and Yule-Walker equations
No full textThe paper proposes a new frequency domain method for identifying linear dynamic errors-in-variables (EIV) models. The noise-free input is an arbitrary signal, not necessarily periodic and the input and output noises are additive and uncorrelated white processes. The method combines, in a frequency domain context, the characteristics of the Frisch scheme and the properties of the Yule-Walker equations. The features of the method are illustrated by means of numerical examples
Errors in Variables Identification using maximum likelihood estimation in the Frequency Domain
No full textThis report deals with the identification of errors–in–variables (EIV) models
corrupted by additive and uncorrelated white Gaussian noises when the noise–free
input is an arbitrary signal, not required to be periodic. In particular, a frequency
domain maximum likelihood (ML) estimator is proposed and analyzed in some
detail. As some other EIV estimators, this method assumes that the ratio of the
noise variances is known. The estimation problem is formulated in the frequency
domain. It is shown that the parameter estimates are consistent. An explicit algorithm
for computing the asymptotic covariance matrix of the parameter estimates
is derived. The possibility to effectively use lowpass filtered data by using only
part of the frequency domain is discussed, analyzed and illustrated
When Are Errors-in-Variables Aspects Important to Consider in System Identification?
No full textWhen recorded signals are corrupted by noise on both input and output sides, standard identification methods give biased parameter estimates, due to the presence of input noise. This paper discusses in what situations such a bias is large and, consequently, when errors-in-variables identification methods should preferably be used
Comparison of three Frisch methods for errors-in-variables identification
No full textThe errors–in–variables framework concerns static or dynamic systems whose input and output variables are affected by additive noise. Several estimation methods have been proposed for identifying dynamic errors–in–variables models. One of the more promising approaches is the so–called Frisch scheme. This paper decribes three different estimation criteria within the Frisch context and compares their estimation accuracy on the basis of the asymptotic covariance matrices of the estimates. Some numerical examples support well the theoretical results
Errors-in-variables identification using a Generalized Instrumental Variable Estimation method
No full textAccuracy Analysis of the Frisch Scheme for Identifying Errors-in-Variables Systems
No full textSeveral estimation methods have been proposedfor identifying errors-in-variables systems, where both input andoutput measurements are corrupted by noise. One of the promisingapproaches is the so-called Frisch scheme. This paper providesan accuracy analysis of the Frisch scheme applied to system iden-tification. The estimates of the system parameters and the noisevariances are shown to be asymptotically Gaussian distributed.An explicit expression for the covariance matrix of the asymptoticdistribution is given as well. Numerical simulations support thetheoretical results. A comparison with the Cramér–Rao lowerbound is also given in the examples, and it is shown that the Frischscheme gives a performance close to the Cramér–Rao bound forlarge signal-to-noise ratios (SNRs).</p
- …
