Convergence properties of affine projection and normalized data reusing methods

Robert A. Soni, Kyle A. Gallivan, W. Kenneth Jenkins

Research output: Contribution to journalArticle

3 Citations (Scopus)

Abstract

The coloring of input sequences can significantly reduce the effective convergence rate of normalized least mean squares (LMS) adaptive filtering algorithms. Recently, there has been significant interest in affine projection adaptive filtering algorithms. These algorithms offer improved performance over traditional normalized LMS algorithms. They can achieve the performance of recursive least squares techniques at a lower computational cost. Unfortunately, these algorithms can greatly amplify measurement noise leading to higher overall misadjustment and poor tracking abilities. In this paper, the new forms of data reusing developed by the authors will be shown to be able to approximate the convergence performance of the affine projection methods without the large misadjustment. In addition, a comprehensive analysis of the steady-state statistical convergence properties of a broad class of data-reusing algorithms will be presented.

Original languageEnglish (US)
Pages (from-to)1166-1170
Number of pages5
JournalConference Record of the Asilomar Conference on Signals, Systems and Computers
Volume2
StatePublished - 1998

Fingerprint

Adaptive filtering
Coloring
Costs

All Science Journal Classification (ASJC) codes

  • Hardware and Architecture
  • Signal Processing
  • Electrical and Electronic Engineering

Cite this

@article{063853bb978c49b783f23ce10eb037bc,
title = "Convergence properties of affine projection and normalized data reusing methods",
abstract = "The coloring of input sequences can significantly reduce the effective convergence rate of normalized least mean squares (LMS) adaptive filtering algorithms. Recently, there has been significant interest in affine projection adaptive filtering algorithms. These algorithms offer improved performance over traditional normalized LMS algorithms. They can achieve the performance of recursive least squares techniques at a lower computational cost. Unfortunately, these algorithms can greatly amplify measurement noise leading to higher overall misadjustment and poor tracking abilities. In this paper, the new forms of data reusing developed by the authors will be shown to be able to approximate the convergence performance of the affine projection methods without the large misadjustment. In addition, a comprehensive analysis of the steady-state statistical convergence properties of a broad class of data-reusing algorithms will be presented.",
author = "Soni, {Robert A.} and Gallivan, {Kyle A.} and Jenkins, {W. Kenneth}",
year = "1998",
language = "English (US)",
volume = "2",
pages = "1166--1170",
journal = "Conference Record of the Asilomar Conference on Signals, Systems and Computers",
issn = "1058-6393",
publisher = "IEEE Computer Society",

}

Convergence properties of affine projection and normalized data reusing methods. / Soni, Robert A.; Gallivan, Kyle A.; Jenkins, W. Kenneth.

In: Conference Record of the Asilomar Conference on Signals, Systems and Computers, Vol. 2, 1998, p. 1166-1170.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Convergence properties of affine projection and normalized data reusing methods

AU - Soni, Robert A.

AU - Gallivan, Kyle A.

AU - Jenkins, W. Kenneth

PY - 1998

Y1 - 1998

N2 - The coloring of input sequences can significantly reduce the effective convergence rate of normalized least mean squares (LMS) adaptive filtering algorithms. Recently, there has been significant interest in affine projection adaptive filtering algorithms. These algorithms offer improved performance over traditional normalized LMS algorithms. They can achieve the performance of recursive least squares techniques at a lower computational cost. Unfortunately, these algorithms can greatly amplify measurement noise leading to higher overall misadjustment and poor tracking abilities. In this paper, the new forms of data reusing developed by the authors will be shown to be able to approximate the convergence performance of the affine projection methods without the large misadjustment. In addition, a comprehensive analysis of the steady-state statistical convergence properties of a broad class of data-reusing algorithms will be presented.

AB - The coloring of input sequences can significantly reduce the effective convergence rate of normalized least mean squares (LMS) adaptive filtering algorithms. Recently, there has been significant interest in affine projection adaptive filtering algorithms. These algorithms offer improved performance over traditional normalized LMS algorithms. They can achieve the performance of recursive least squares techniques at a lower computational cost. Unfortunately, these algorithms can greatly amplify measurement noise leading to higher overall misadjustment and poor tracking abilities. In this paper, the new forms of data reusing developed by the authors will be shown to be able to approximate the convergence performance of the affine projection methods without the large misadjustment. In addition, a comprehensive analysis of the steady-state statistical convergence properties of a broad class of data-reusing algorithms will be presented.

UR - http://www.scopus.com/inward/record.url?scp=0032256410&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0032256410&partnerID=8YFLogxK

M3 - Article

AN - SCOPUS:0032256410

VL - 2

SP - 1166

EP - 1170

JO - Conference Record of the Asilomar Conference on Signals, Systems and Computers

JF - Conference Record of the Asilomar Conference on Signals, Systems and Computers

SN - 1058-6393

ER -