It is demonstrated that the cross-spectral metric is optimal in the sense that it maximizes mutual information between the observed and desired processes and is capable of outperforming the more complex eigendecomposition-based methods.
Abstract:
The Wiener filter is analyzed for stationary complex Gaussian signals from an information theoretic point of view. A dual-port analysis of the Wiener filter leads to a decomposition based on orthogonal projections and results in a new multistage method for implementing the Wiener filter using a nested chain of scalar Wiener filters. This new representation of the Wiener filter provides the capability to perform an information-theoretic analysis of previous, basis-dependent, reduced-rank Wiener filters. This analysis demonstrates that the cross-spectral metric is optimal in the sense that it maximizes mutual information between the observed and desired processes. A new reduced-rank Wiener filter is developed based on this new structure which evolves a basis using successive projections of the desired signal onto orthogonal, lower dimensional subspaces. The performance is evaluated using a comparative computer analysis model and it is demonstrated that the low-complexity multistage reduced-rank Wiener filter is capable of outperforming the more complex eigendecomposition-based methods.
TL;DR: A tutorial on random matrices is provided which provides an overview of the theory and brings together in one source the most significant results recently obtained.
TL;DR: This paper considers the design of the analog and digital beamforming coefficients, for the case of narrowband signals, and proposes the optimal analog beamformer to minimize the mean squared error between the desired user and its receiver estimate.
TL;DR: The clutter space and its rank in the MIMO radar are explored and by using the geometry of the problem rather than data, the clutter subspace can be represented using prolate spheroidal wave functions (PSWF) and a new STAP algorithm is proposed.
TL;DR: A class of adaptive reduced-rank interference suppression algorithms is presented based on the multistage Wiener filter (MSWF), which can achieve near full-rank performance with a filter rank much less than the dimension of the signal subspace.
TL;DR: An iterative least squares (LS) procedure to jointly optimize the interpolation, decimation and filtering tasks for reduced-rank adaptive filtering for interference suppression in code-division multiple-access (CDMA) systems is described.
TL;DR: This final installment of the paper considers the case where the signals or the messages or both are continuously variable, in contrast with the discrete nature assumed until now.
TL;DR: The author examines the role of entropy, inequality, and randomness in the design of codes and the construction of codes in the rapidly changing environment.
TL;DR: In this paper, the authors propose a recursive least square adaptive filter (RLF) based on the Kalman filter, which is used as the unifying base for RLS Filters.
TL;DR: In this article, the distribution of the Mean Vector and the Covariance Matrix and the Generalized T2-Statistic is analyzed. But the distribution is not shown to be independent of sets of Variates.
Q1. What are the contributions in "A multistage representation of the wiener filter based on orthogonal projections" ?
A dual-port analysis of the Wiener filter leads to a decomposition based on orthogonal projections and results in a new multistage method for implementing the Wiener filter using a nested chain of scalar Wiener filters. This new representation of the Wiener filter provides the capability to perform an information-theoretic analysis of previous, basis-dependent, reduced-rank Wiener filters. This analysis demonstrates that the recently introduced cross-spectral metric is optimal in the sense that it maximizes mutual information between the observed and desired processes. A new reduced-rank Wiener filter is developed based on this new structure which evolves a basis using successive projections of the desired signal onto orthogonal, lower dimensional subspaces.
Q2. What is the optimal linear filter for a stationary process?
The optimal linear filter, which minimizes the mean-square error between the desired signal and its estimate,(4)is the classical Wiener filter(5)for complex stationary processes.
Q3. What is the final justification for the reduced-rank multistage Wiener filter?
A final justification for the reduced-rank multistage Wiener filter is that the covariance matrix of the process tends tobecome white as the filter structure increases in stages.
Q4. What is the error covariance matrix associated with the error process in (51)?
The error covariance matrix , which is associated with the error process in (51), is a diagonal matrix given by(57)where the operator , with a vector operand, represents a diagonal matrix whose only nonzero elements are along the main diagonal and provided by the corresponding element of the operand.
Q5. How can the Wiener filter be constructed?
In particular, it is demonstrated that the unconstrained Wiener filter can always be constructed via a chain of constrained Wiener filters.
Q6. What is the definition of a cross-spectral metric?
This cross-spectral metric is recognized in [31] to be a vector which has components that are the weighted squared magnitudes of the direction cosines between each basis vector and the cross-correlation vector for the two aforementioned correlated random processes.
Q7. How many jammers are there in this example?
For this example the number of jammers is five, which corresponds to the effective rank of the signal subspace for that covariance matrix.
Q8. What is the simplest way to represent the error-synthesis filterbank?
It is demonstrated also that the error-synthesis filterbank can be interpreted as an implementation of a Gram–Schmidt orthogonalization process.
Q9. What is the smallest degree of freedom to estimate a scalar random process?
This method utilizes a measure, termed the cross-spectral metric, to determine the smallestnumber of degrees of freedom to linearly estimate with little loss a scalar random process from a set of correlated complex random processes.