Paper Info
Title
Complex-valued Gaussian signal processing: Optimality of MSE, incorporation of full statistics, and a unified view
Abstract
In this paper, we study the performance of mean square error (MSE) and Gaussian entropy criteria for linear and widely linear complex filtering. The MSE criterion cannot exploit the full second-order statistics of the error signal. To this end, we propose a new Gaussian entropy criterion to exploit the full second-order statistics of the error signal, and compare the performance of the two criteria in linear and widely linear filters. We show that the minimum Gaussian entropy estimator is also the best linear unbiased estimator (BLUE).
Year
DOI
Venue
2011
10.1109/CISS.2011.5766121
CISS
Keywords
Field
DocType
signal processing,second-order statistics,mean square error (mse),noncircularity,mean square error,blue,gaussian entropy criteria,gaussian entropy,gaussian signal processing,higher order statistics,best linear unbiased estimator,gaussian processes,minimum gaussian entropy estimator,widely linear complex filtering,entropy,best linear unbiased estimator (blue),mean square error methods,minimization,entropy estimation,indexing terms
Best linear unbiased prediction,Mathematical optimization,Linear filter,Higher-order statistics,Mean squared error,Gaussian,Gaussian process,Statistics,Gaussian function,Mathematics,Estimator
Conference
ISBN
Citations 
PageRank 
978-1-4244-9847-5
3
0.43
References 
Authors
5
2
Name
Order
Citations
PageRank
Xi-Lin Li154734.85
Tülay Adali21690126.40