Conjugate gradient method for adaptive nonlinear filtering

Sreeraman Rajan, Kyung Sub Joo, Tamal Bose, Mei Qin Chen

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

The application of the Conjugate Gradient (CG) method for the identification of a new class of non-linear discrete time systems, called 'Generalized Bilinear System' is investigated. An algorithm based on the CG method is developed for adaptive generalized bilinear filtering with output error method. This algorithm outperforms the LMS and RLS methods in terms of speed of convergence. In this algorithm, the optimization is done over blocks of input and output data rather than a single pair of data. However, only one iteration and coefficient update is done for every sample of data. Some examples are given to illustrate the efficiency of the algorithm.

Original languageEnglish (US)
Title of host publicationMidwest Symposium on Circuits and Systems
EditorsMagdy A. Bayoumi, Ken W. Jenkins
PublisherIEEE
Pages1327-1330
Number of pages4
Volume2
StatePublished - 1994
Externally publishedYes
EventProceedings of the 37th Midwest Symposium on Circuits and Systems. Part 2 (of 2) - Lafayette, LA, USA
Duration: Aug 3 1994Aug 5 1994

Other

OtherProceedings of the 37th Midwest Symposium on Circuits and Systems. Part 2 (of 2)
CityLafayette, LA, USA
Period8/3/948/5/94

Fingerprint

Nonlinear filtering
Conjugate gradient method

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Electronic, Optical and Magnetic Materials

Cite this

Rajan, S., Sub Joo, K., Bose, T., & Chen, M. Q. (1994). Conjugate gradient method for adaptive nonlinear filtering. In M. A. Bayoumi, & K. W. Jenkins (Eds.), Midwest Symposium on Circuits and Systems (Vol. 2, pp. 1327-1330). IEEE.

Conjugate gradient method for adaptive nonlinear filtering. / Rajan, Sreeraman; Sub Joo, Kyung; Bose, Tamal; Chen, Mei Qin.

Midwest Symposium on Circuits and Systems. ed. / Magdy A. Bayoumi; Ken W. Jenkins. Vol. 2 IEEE, 1994. p. 1327-1330.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Rajan, S, Sub Joo, K, Bose, T & Chen, MQ 1994, Conjugate gradient method for adaptive nonlinear filtering. in MA Bayoumi & KW Jenkins (eds), Midwest Symposium on Circuits and Systems. vol. 2, IEEE, pp. 1327-1330, Proceedings of the 37th Midwest Symposium on Circuits and Systems. Part 2 (of 2), Lafayette, LA, USA, 8/3/94.
Rajan S, Sub Joo K, Bose T, Chen MQ. Conjugate gradient method for adaptive nonlinear filtering. In Bayoumi MA, Jenkins KW, editors, Midwest Symposium on Circuits and Systems. Vol. 2. IEEE. 1994. p. 1327-1330
Rajan, Sreeraman ; Sub Joo, Kyung ; Bose, Tamal ; Chen, Mei Qin. / Conjugate gradient method for adaptive nonlinear filtering. Midwest Symposium on Circuits and Systems. editor / Magdy A. Bayoumi ; Ken W. Jenkins. Vol. 2 IEEE, 1994. pp. 1327-1330
@inproceedings{23da752204ff4228a1ba1d10bc06f902,
title = "Conjugate gradient method for adaptive nonlinear filtering",
abstract = "The application of the Conjugate Gradient (CG) method for the identification of a new class of non-linear discrete time systems, called 'Generalized Bilinear System' is investigated. An algorithm based on the CG method is developed for adaptive generalized bilinear filtering with output error method. This algorithm outperforms the LMS and RLS methods in terms of speed of convergence. In this algorithm, the optimization is done over blocks of input and output data rather than a single pair of data. However, only one iteration and coefficient update is done for every sample of data. Some examples are given to illustrate the efficiency of the algorithm.",
author = "Sreeraman Rajan and {Sub Joo}, Kyung and Tamal Bose and Chen, {Mei Qin}",
year = "1994",
language = "English (US)",
volume = "2",
pages = "1327--1330",
editor = "Bayoumi, {Magdy A.} and Jenkins, {Ken W.}",
booktitle = "Midwest Symposium on Circuits and Systems",
publisher = "IEEE",

}

TY - GEN

T1 - Conjugate gradient method for adaptive nonlinear filtering

AU - Rajan, Sreeraman

AU - Sub Joo, Kyung

AU - Bose, Tamal

AU - Chen, Mei Qin

PY - 1994

Y1 - 1994

N2 - The application of the Conjugate Gradient (CG) method for the identification of a new class of non-linear discrete time systems, called 'Generalized Bilinear System' is investigated. An algorithm based on the CG method is developed for adaptive generalized bilinear filtering with output error method. This algorithm outperforms the LMS and RLS methods in terms of speed of convergence. In this algorithm, the optimization is done over blocks of input and output data rather than a single pair of data. However, only one iteration and coefficient update is done for every sample of data. Some examples are given to illustrate the efficiency of the algorithm.

AB - The application of the Conjugate Gradient (CG) method for the identification of a new class of non-linear discrete time systems, called 'Generalized Bilinear System' is investigated. An algorithm based on the CG method is developed for adaptive generalized bilinear filtering with output error method. This algorithm outperforms the LMS and RLS methods in terms of speed of convergence. In this algorithm, the optimization is done over blocks of input and output data rather than a single pair of data. However, only one iteration and coefficient update is done for every sample of data. Some examples are given to illustrate the efficiency of the algorithm.

UR - http://www.scopus.com/inward/record.url?scp=0028749337&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0028749337&partnerID=8YFLogxK

M3 - Conference contribution

VL - 2

SP - 1327

EP - 1330

BT - Midwest Symposium on Circuits and Systems

A2 - Bayoumi, Magdy A.

A2 - Jenkins, Ken W.

PB - IEEE

ER -