We consider the problem of giving an approximate Markovian representation for multivariate Gaussian processes. The result is a generalization of the Lindquist-Picci algorithm to derive a minimal stochastic realization from a nonminimal one. The properties of the invariant subspaces of a state space are exploited to produce an approximate model
On the multivariable approximate stochastic realization problem
A Gombani
1991
Abstract
We consider the problem of giving an approximate Markovian representation for multivariate Gaussian processes. The result is a generalization of the Lindquist-Picci algorithm to derive a minimal stochastic realization from a nonminimal one. The properties of the invariant subspaces of a state space are exploited to produce an approximate modelFile in questo prodotto:
Non ci sono file associati a questo prodotto.
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
