Performance analysis of a RLS-based MLP-DFE in time-invariant and time-varying channels

Kashif Mahmood; Abdelmalek Zidouri; Azzedine Zerguine

doi:10.1016/j.dsp.2007.04.006

Performance analysis of a RLS-based MLP-DFE in time-invariant and time-varying channels

Kashif Mahmood, Abdelmalek Zidouri, Azzedine Zerguine^*

^*Corresponding author for this work

Research output: Contribution to journal › Article › peer-review

13 Scopus citations

Abstract

In this work, a recently derived recursive least-square (RLS) algorithm to train multi layer perceptron (MLP) is used in an MLP-based decision feedback equalizer (DFE) instead of the back propagation (BP) algorithm. Its performance is investigated and compared to those of MLP-DFE based on the BP algorithm and the simple DFE based on the least-mean square (LMS) algorithm. The results show improved performance obtained by the new structure in both time-invariant and time-varying channels. As will be detailed in this work, the newly proposed structure is a compromise between complexity and performance.

Original language	English
Pages (from-to)	307-320
Number of pages	14
Journal	Digital Signal Processing: A Review Journal
Volume	18
Issue number	3
DOIs	https://doi.org/10.1016/j.dsp.2007.04.006
State	Published - May 2008

Bibliographical note

Funding Information:
The authors would like to acknowledge the support of KFUPM.

Keywords

Decision feedback equalizer (DFE)
Least-mean square (LMS)
Multi layer perceptron (MLP)
Recursive least-square (RLS)

ASJC Scopus subject areas

Signal Processing
Computer Vision and Pattern Recognition
Statistics, Probability and Uncertainty
Computational Theory and Mathematics
Electrical and Electronic Engineering
Artificial Intelligence
Applied Mathematics

Access to Document

10.1016/j.dsp.2007.04.006

Cite this

@article{79e6970b5e0f4023873b0bc2c6f3b0c2,

title = "Performance analysis of a RLS-based MLP-DFE in time-invariant and time-varying channels",

abstract = "In this work, a recently derived recursive least-square (RLS) algorithm to train multi layer perceptron (MLP) is used in an MLP-based decision feedback equalizer (DFE) instead of the back propagation (BP) algorithm. Its performance is investigated and compared to those of MLP-DFE based on the BP algorithm and the simple DFE based on the least-mean square (LMS) algorithm. The results show improved performance obtained by the new structure in both time-invariant and time-varying channels. As will be detailed in this work, the newly proposed structure is a compromise between complexity and performance.",

keywords = "Decision feedback equalizer (DFE), Least-mean square (LMS), Multi layer perceptron (MLP), Recursive least-square (RLS)",

author = "Kashif Mahmood and Abdelmalek Zidouri and Azzedine Zerguine",

note = "Funding Information: The authors would like to acknowledge the support of KFUPM.",

year = "2008",

month = may,

doi = "10.1016/j.dsp.2007.04.006",

language = "English",

volume = "18",

pages = "307--320",

journal = "Digital Signal Processing: A Review Journal",

issn = "1051-2004",

publisher = "Elsevier Inc.",

number = "3",

}

TY - JOUR

T1 - Performance analysis of a RLS-based MLP-DFE in time-invariant and time-varying channels

AU - Mahmood, Kashif

AU - Zidouri, Abdelmalek

AU - Zerguine, Azzedine

N1 - Funding Information: The authors would like to acknowledge the support of KFUPM.

PY - 2008/5

Y1 - 2008/5

N2 - In this work, a recently derived recursive least-square (RLS) algorithm to train multi layer perceptron (MLP) is used in an MLP-based decision feedback equalizer (DFE) instead of the back propagation (BP) algorithm. Its performance is investigated and compared to those of MLP-DFE based on the BP algorithm and the simple DFE based on the least-mean square (LMS) algorithm. The results show improved performance obtained by the new structure in both time-invariant and time-varying channels. As will be detailed in this work, the newly proposed structure is a compromise between complexity and performance.

AB - In this work, a recently derived recursive least-square (RLS) algorithm to train multi layer perceptron (MLP) is used in an MLP-based decision feedback equalizer (DFE) instead of the back propagation (BP) algorithm. Its performance is investigated and compared to those of MLP-DFE based on the BP algorithm and the simple DFE based on the least-mean square (LMS) algorithm. The results show improved performance obtained by the new structure in both time-invariant and time-varying channels. As will be detailed in this work, the newly proposed structure is a compromise between complexity and performance.

KW - Decision feedback equalizer (DFE)

KW - Least-mean square (LMS)

KW - Multi layer perceptron (MLP)

KW - Recursive least-square (RLS)

UR - http://www.scopus.com/inward/record.url?scp=42949161478&partnerID=8YFLogxK

U2 - 10.1016/j.dsp.2007.04.006

DO - 10.1016/j.dsp.2007.04.006

M3 - Article

AN - SCOPUS:42949161478

SN - 1051-2004

VL - 18

SP - 307

EP - 320

JO - Digital Signal Processing: A Review Journal

JF - Digital Signal Processing: A Review Journal

IS - 3

ER -

Performance analysis of a RLS-based MLP-DFE in time-invariant and time-varying channels

Abstract

Bibliographical note

Keywords

ASJC Scopus subject areas

Access to Document

Fingerprint

Cite this