Title :
Maximum Likelihood, Weighted Kalman And Subspace Linear Prediction Algorithms For System Identification
Author :
Rua, Y. ; Sarkar, T.K.
Author_Institution :
Syracuse University
fDate :
Oct. 31 1988-Nov. 2 1988
Abstract :
For the problem of estimating parameters of a linear system from its input and output sequences, we present iterative quadratic maximum likelihood (IQML), iterative quadratic weighted Kalman (IQWK), and noniterative subspace linear prediction (SLP) algorithms. The SLP algorithms are based on a novel subspace deconvolution of the output. In particular, a double total-least-squares (D-TLS) SLP algorithm is provided.
Keywords :
Contracts; Covariance matrix; Deconvolution; Iterative algorithms; Iterative methods; Kalman filters; Least squares approximation; Maximum likelihood estimation; Parameter estimation; Prediction algorithms;
Conference_Titel :
Signals, Systems and Computers, 1988. Twenty-Second Asilomar Conference on
Conference_Location :
Pacific Grove, CA, USA
DOI :
10.1109/ACSSC.1988.754643
