`Stop-and-go' decision-directed blind adaptive equalization using the complex-valued multilayer perceptron

Cheolwoo You, Daesik Hong

Research output: Contribution to journalConference article

Abstract

In this paper, a `stop-and-go' decision-directed blind equalization scheme is newly proposed. This scheme uses the structure of complex-valued multilayer feedforward neural networks, instead of the linear transversal filters that are usually used in conventional LMS-type blind equalization schemes. A complex-valued activation function composed of two real functions is used. Each real activation function has multi-saturated output region in order to deal with QAM signals of any constellation sizes. Also, the complex backpropagation algorithm is modified for the proposed scheme. Computer simulation are performed to compare the proposed scheme with the conventional `stop-and-go' algorithm in terms of convergence speed, MSE value in the steady state, and constellation of QAM signals after the initial convergence. Simulation results demonstrate the effectiveness of the proposed scheme.

Original languageEnglish
Pages (from-to)3289-3292
Number of pages4
JournalICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
Volume4
Publication statusPublished - 1997 Jan 1

Fingerprint

self organizing systems
Multilayer neural networks
Blind equalization
quadrature amplitude modulation
constellations
Quadrature amplitude modulation
Chemical activation
activation
Transversal filters
linear filters
Backpropagation algorithms
Feedforward neural networks
computerized simulation
output
Computer simulation
simulation

All Science Journal Classification (ASJC) codes

  • Signal Processing
  • Electrical and Electronic Engineering
  • Acoustics and Ultrasonics

Cite this

@article{f74cc20f50c5417ab23b6436d942f625,
title = "`Stop-and-go' decision-directed blind adaptive equalization using the complex-valued multilayer perceptron",
abstract = "In this paper, a `stop-and-go' decision-directed blind equalization scheme is newly proposed. This scheme uses the structure of complex-valued multilayer feedforward neural networks, instead of the linear transversal filters that are usually used in conventional LMS-type blind equalization schemes. A complex-valued activation function composed of two real functions is used. Each real activation function has multi-saturated output region in order to deal with QAM signals of any constellation sizes. Also, the complex backpropagation algorithm is modified for the proposed scheme. Computer simulation are performed to compare the proposed scheme with the conventional `stop-and-go' algorithm in terms of convergence speed, MSE value in the steady state, and constellation of QAM signals after the initial convergence. Simulation results demonstrate the effectiveness of the proposed scheme.",
author = "Cheolwoo You and Daesik Hong",
year = "1997",
month = "1",
day = "1",
language = "English",
volume = "4",
pages = "3289--3292",
journal = "Proceedings - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing",
issn = "0736-7791",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - JOUR

T1 - `Stop-and-go' decision-directed blind adaptive equalization using the complex-valued multilayer perceptron

AU - You, Cheolwoo

AU - Hong, Daesik

PY - 1997/1/1

Y1 - 1997/1/1

N2 - In this paper, a `stop-and-go' decision-directed blind equalization scheme is newly proposed. This scheme uses the structure of complex-valued multilayer feedforward neural networks, instead of the linear transversal filters that are usually used in conventional LMS-type blind equalization schemes. A complex-valued activation function composed of two real functions is used. Each real activation function has multi-saturated output region in order to deal with QAM signals of any constellation sizes. Also, the complex backpropagation algorithm is modified for the proposed scheme. Computer simulation are performed to compare the proposed scheme with the conventional `stop-and-go' algorithm in terms of convergence speed, MSE value in the steady state, and constellation of QAM signals after the initial convergence. Simulation results demonstrate the effectiveness of the proposed scheme.

AB - In this paper, a `stop-and-go' decision-directed blind equalization scheme is newly proposed. This scheme uses the structure of complex-valued multilayer feedforward neural networks, instead of the linear transversal filters that are usually used in conventional LMS-type blind equalization schemes. A complex-valued activation function composed of two real functions is used. Each real activation function has multi-saturated output region in order to deal with QAM signals of any constellation sizes. Also, the complex backpropagation algorithm is modified for the proposed scheme. Computer simulation are performed to compare the proposed scheme with the conventional `stop-and-go' algorithm in terms of convergence speed, MSE value in the steady state, and constellation of QAM signals after the initial convergence. Simulation results demonstrate the effectiveness of the proposed scheme.

UR - http://www.scopus.com/inward/record.url?scp=0030682329&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0030682329&partnerID=8YFLogxK

M3 - Conference article

AN - SCOPUS:0030682329

VL - 4

SP - 3289

EP - 3292

JO - Proceedings - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing

JF - Proceedings - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing

SN - 0736-7791

ER -