Stabilization of smoothness priors deterministic regression TVAR models

Author

Juntunen, M. ; Kaipio, Jari P.

Author_Institution

Elektrobit Ltd., Kuopio, Finland

Volume

1

fYear

2000

fDate

2000

Firstpage

568

Abstract

A method for the stabilization of time-varying autoregressive models is proposed. The method is based on the smoothness priors regularized prediction equations with nonlinear stability constraints. The problem is solved iteratively with a Gauss-Newton type algorithm in which the original constrained problem is approximated with a sequence of unconstrained problems by using appropriate penalty functions. The performance of the algorithm is studied with a simulation

Keywords

Newton method; autoregressive processes; numerical stability; parameter estimation; prediction theory; signal processing; time-varying systems; EEG analysis; Gauss-Newton type algorithm; constrained problem; iterative method; nonlinear stability constraint; penalty functions; performance; smoothness priors deterministic regression TVAR models; smoothness priors regularized prediction equations; stabilization; time-varying autoregressive models; unconstrained problems; Brain modeling; Electroencephalography; Iterative algorithms; Least squares methods; Narrowband; Newton method; Nonlinear equations; Predictive models; Stability; Stochastic processes;

fLanguage

English

Publisher

ieee

Conference_Titel

Acoustics, Speech, and Signal Processing, 2000. ICASSP '00. Proceedings. 2000 IEEE International Conference on

Conference_Location

Istanbul

ISSN

1520-6149

Print_ISBN

0-7803-6293-4

Type

conf

DOI

10.1109/ICASSP.2000.862045

Filename

862045