Title :
An on-line least-squares parameter estimator with finite convergence time
Author_Institution :
Fac. de Ingenieria, Univ. Nacional Autonoma de Mexico, Mexico
fDate :
7/1/1988 12:00:00 AM
Abstract :
An online parameter-estimation algorithm is presented which has the following features: (1) it reduces to the linear least-squares (LS) estimator after a set of regression vectors that span the full dimension of the parameter space has been processed, and (2) when the regression model is linear in the parameters, the parameter and prediction errors converge to zero in finite time. Both continuous- and discrete-time versions of the algorithm are given
Keywords :
convergence of numerical methods; least squares approximations; parameter estimation; continuous time; discrete-time versions; finite convergence time; linear least-squares; on-line least-squares parameter estimator; parameter space; prediction errors; regression model; regression vectors; Circuits; Convergence; Digital modulation; Equations; Notice of Violation; Parameter estimation; Signal processing; Signal processing algorithms; Speech processing; Time measurement;
Journal_Title :
Proceedings of the IEEE
