Title :
Subspace angles between linear stochastic models
Author :
de Cock, Katrien ; De Moor, Bart
Author_Institution :
Dept. of Electr. Eng., Katholieke Univ., Leuven, Belgium
Abstract :
We define a notion of principal angles between two linear autoregressive (AR) models by considering the principal angles between the ranges of their infinite observability matrices. We show how a metric for these models, which is based on their cepstra, is related to the subspace angles between them. The definition of subspace angles is also extended to the linear autoregressive-moving-average (ARMA) model class
Keywords :
autoregressive processes; eigenvalues and eigenfunctions; identification; linear systems; matrix algebra; stochastic systems; ARMA model; cepstra; infinite observability matrices; linear autoregressive models; linear stochastic models; principal angles; subspace angles; Ear; Eigenvalues and eigenfunctions; Extraterrestrial measurements; Linear systems; Observability; Stochastic processes; Stochastic systems; Time measurement; Vectors; World Wide Web;
Conference_Titel :
Decision and Control, 2000. Proceedings of the 39th IEEE Conference on
Conference_Location :
Sydney, NSW
Print_ISBN :
0-7803-6638-7
DOI :
10.1109/CDC.2000.912082
