Recursive least-squares backpropagation algorithm for stop-and-go decision-directed blind equalization

Shafayat Abrar; Azzedine Zerguine; Maamar Bettayeb

doi:10.1109/TNN.2002.804282

Recursive least-squares backpropagation algorithm for stop-and-go decision-directed blind equalization

Shafayat Abrar^*, Azzedine Zerguine, Maamar Bettayeb

^*Corresponding author for this work

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

13 Scopus citations

Abstract

Stop-and-go decision-directed (S & G-DD) equalization is the most primitive blind equalization (BE) method for the cancelling of intersymbol-interference in data communication systems. Recently, this scheme has been applied to complex-valued multilayer feedforward neural network, giving robust results with a lower mean-square error at the expense of slow convergence. To overcome this problem, in this work, a fast converging recursive least squares (RLS)-based complex-valued backpropagation learning algorithm is derived for S & G-DD blind equalization. Simulation results show the effectiveness of the proposed algorithm in terms of initial convergence.

Original language	English
Pages (from-to)	1472-1481
Number of pages	10
Journal	IEEE Transactions on Neural Networks
Volume	13
Issue number	6
DOIs	https://doi.org/10.1109/TNN.2002.804282
State	Published - Nov 2002

Bibliographical note

Funding Information:
The authors acknowledge the support of KFUPM. The authors like to thank the anonymous reviewers for their constructive suggestions which has helped improve the paper.

Keywords

Complex-valued backpropagation algorithm
Recursive least squares (RLS) algorithm
Stop-and-go decision-directed (S & G-DD) blind equalization (BE) algorithm

ASJC Scopus subject areas

Software
Computer Science Applications
Computer Networks and Communications
Artificial Intelligence

Access to Document

10.1109/TNN.2002.804282

Cite this

@article{4ac0f5d274f64aabbe569bd3bfb7ec04,

title = "Recursive least-squares backpropagation algorithm for stop-and-go decision-directed blind equalization",

abstract = "Stop-and-go decision-directed (S \& G-DD) equalization is the most primitive blind equalization (BE) method for the cancelling of intersymbol-interference in data communication systems. Recently, this scheme has been applied to complex-valued multilayer feedforward neural network, giving robust results with a lower mean-square error at the expense of slow convergence. To overcome this problem, in this work, a fast converging recursive least squares (RLS)-based complex-valued backpropagation learning algorithm is derived for S \& G-DD blind equalization. Simulation results show the effectiveness of the proposed algorithm in terms of initial convergence.",

keywords = "Complex-valued backpropagation algorithm, Recursive least squares (RLS) algorithm, Stop-and-go decision-directed (S \& G-DD) blind equalization (BE) algorithm",

author = "Shafayat Abrar and Azzedine Zerguine and Maamar Bettayeb",

note = "Funding Information: The authors acknowledge the support of KFUPM. The authors like to thank the anonymous reviewers for their constructive suggestions which has helped improve the paper.",

year = "2002",

month = nov,

doi = "10.1109/TNN.2002.804282",

language = "English",

volume = "13",

pages = "1472--1481",

journal = "IEEE Transactions on Neural Networks",

issn = "1045-9227",

number = "6",

}

TY - JOUR

T1 - Recursive least-squares backpropagation algorithm for stop-and-go decision-directed blind equalization

AU - Abrar, Shafayat

AU - Zerguine, Azzedine

AU - Bettayeb, Maamar

N1 - Funding Information: The authors acknowledge the support of KFUPM. The authors like to thank the anonymous reviewers for their constructive suggestions which has helped improve the paper.

PY - 2002/11

Y1 - 2002/11

N2 - Stop-and-go decision-directed (S & G-DD) equalization is the most primitive blind equalization (BE) method for the cancelling of intersymbol-interference in data communication systems. Recently, this scheme has been applied to complex-valued multilayer feedforward neural network, giving robust results with a lower mean-square error at the expense of slow convergence. To overcome this problem, in this work, a fast converging recursive least squares (RLS)-based complex-valued backpropagation learning algorithm is derived for S & G-DD blind equalization. Simulation results show the effectiveness of the proposed algorithm in terms of initial convergence.

AB - Stop-and-go decision-directed (S & G-DD) equalization is the most primitive blind equalization (BE) method for the cancelling of intersymbol-interference in data communication systems. Recently, this scheme has been applied to complex-valued multilayer feedforward neural network, giving robust results with a lower mean-square error at the expense of slow convergence. To overcome this problem, in this work, a fast converging recursive least squares (RLS)-based complex-valued backpropagation learning algorithm is derived for S & G-DD blind equalization. Simulation results show the effectiveness of the proposed algorithm in terms of initial convergence.

KW - Complex-valued backpropagation algorithm

KW - Recursive least squares (RLS) algorithm

KW - Stop-and-go decision-directed (S & G-DD) blind equalization (BE) algorithm

UR - https://www.scopus.com/pages/publications/0036859419

U2 - 10.1109/TNN.2002.804282

DO - 10.1109/TNN.2002.804282

M3 - Article

AN - SCOPUS:0036859419

SN - 1045-9227

VL - 13

SP - 1472

EP - 1481

JO - IEEE Transactions on Neural Networks

JF - IEEE Transactions on Neural Networks

IS - 6

ER -

Recursive least-squares backpropagation algorithm for stop-and-go decision-directed blind equalization

Abstract

Bibliographical note

Keywords

ASJC Scopus subject areas

Access to Document

Fingerprint

Cite this