Sliding window order-recursive least-squares algorithms

Order-recursive least-squares (ORLS) algorithms employing a sliding window (SW) are presented. The authors demonstrate that standard architectures that are well known for growing memory ORLS estimation, e.g., triangular array, lattice, and multichannel lattice, also apply to sliding window ORLS esti...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on signal processing 1994-08, Vol.42 (8), p.1961-1972
Main Authors: Zhao, K., Fuyun Ling, Lev-Ari, H., Proakis, J.G.
Format: Article
Language:English
Subjects:
Applied sciences
Architecture
Covariance matrix
Digital signal processing
Equations
Exact sciences and technology
Feedforward systems
Information, signal and communications theory
Lattices
Miscellaneous
Resonance light scattering
Signal generators
Signal processing
Signal processing algorithms
Telecommunications and information theory
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Order-recursive least-squares (ORLS) algorithms employing a sliding window (SW) are presented. The authors demonstrate that standard architectures that are well known for growing memory ORLS estimation, e.g., triangular array, lattice, and multichannel lattice, also apply to sliding window ORLS estimation. A specific SW-ORLS algorithm is the combination of two independent attributes: its global architecture and its local cell implementation. Various forms of local cell implementation based on efficient time-recursions of time-varying coefficients are discussed. In particular, the authors show that time and order updates of any order-recursive sliding window least-squares algorithm can be realized solely in terms of 3/spl times/3 hyperbolic Householder transformations (HHT). Finally, the authors present two HHT-based algorithms: the HHT triangular array algorithm and the HHT lattice algorithm.< >
ISSN:1053-587X
1941-0476
DOI:10.1109/78.301835