A Nonquadratic Algorithm Based on the Extended Recursive Least-Squares Algorithm

In adaptiveg filters, several recursive algorithms have been used to track state-space model vectors in nonstationary environments. So far, kernel recursive algorithms showed the best results in this regard. With this letter, we aim to propose an algorithm based on a nonlinear function of the error,...

Full description

Saved in:
Bibliographic Details
Published in:IEEE signal processing letters 2018-10, Vol.25 (10), p.1535-1539
Main Authors: Amaral, Luis Fernando Coelho, Lopes, Marcus Vinicius, Barros, Allan Kardec
Format: Article
Language:English
Subjects:
Algorithms
Autoregressive processes
Computer simulation
Extended recursive least-squares (EX-RLS) algorithm
Kernel
Least squares
Mathematical analysis
Mathematical model
nonquadratic function
Nonstationary environments
Prediction algorithms
Rayleigh channels
Recursive algorithms
recursive filter adaptive
Signal processing algorithms
State space models
State vectors
Stochastic processes
System identification
Tracking
tracking performance
Vectors (mathematics)
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:In adaptiveg filters, several recursive algorithms have been used to track state-space model vectors in nonstationary environments. So far, kernel recursive algorithms showed the best results in this regard. With this letter, we aim to propose an algorithm based on a nonlinear function of the error, motivated by the extended recursive least-squares algorithm. Simulations were performed on the problem of tracking a nonlinear Rayleigh fading multipath channel and on a system identification. The results showed that the proposed algorithm can overcome the extended kernel version ones.
ISSN:1070-9908
1558-2361
DOI:10.1109/LSP.2018.2864609