The Wiener filter for locally stationary stochastic processes is rarely locally stationary

Title: The Wiener filter for locally stationary stochastic processes is rarely locally stationary
Creator: Wahlberg, Patrik; Schreier, Peter J.
Relation: 17th European Signal Processing Conference (EUSIPCO 2009). EUSIPCO 2009: 17th European Signal Processing Conference (Glasgow, Scotland 24-28 August, 2009) p. 2465-2469
Relation: http://www.eusipco2009.org/Papers-g.html
Publisher: EURASIP
Resource Type: conference paper
Date: 2009
Description: The Wiener filter (i.e., linear minimum mean squared error filter) for wide-sense stationary stochastic processes is translation-invariant, i.e., its impulse response, like the covariance function, is only a function of the time-shift. We investigate whether there is a generalization of this result to continuous-time stochastic processes that are locally stationary in Silverman’s sense: Is the optimal filter for locally stationary processes locally stationary itself? The answer is surprisingly negative: Even though the optimal filter can be locally stationary in special cases, it rarely is, even when the covariance functions have Gaussian shape.
Subject: Wiener filter; stationary stochastic processes; locally stationary
Identifier: uon:9020
Identifier: http://hdl.handle.net/1959.13/919908
Reviewed

		Thumbnail	File	Description	Size	Format