Nonlinear blind equalization schemes using complex-valued multilayer feedforward neural networks

Among the useful blind equalization algorithms, stochastic-gradient iterative equalization schemes are based on minimizing a nonconvex and nonlinear cost function. However, as they use a linear FIR filter with a convex decision region, their residual estimation error is high. In the paper, four nonl...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on neural networks Vol. 9; no. 6; pp. 1442 - 1455
Main Authors: YOU, C, HONG, D
Format: Journal Article
Language:English
Published: New York, NY IEEE 01.11.1998
Institute of Electrical and Electronics Engineers
Subjects:
Applied sciences
Blind equalizers
Constellation diagram
Cost function
Electric, optical and optoelectronic circuits
Electronics
Estimation error
Exact sciences and technology
Finite impulse response filter
Iterative algorithms
Multilayer perceptrons
Neural networks
Nonlinear filters
Quadrature amplitude modulation
Random variables
Theoretical study. Circuits analysis and design
Blind
Backpropagation algorithm
Perceptron
Algorithm complexity
Multiple layer
Activation
Quadrature modulation
Neural network
Feedforward
Equalization
Experimental study
ISSN:1045-9227
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Among the useful blind equalization algorithms, stochastic-gradient iterative equalization schemes are based on minimizing a nonconvex and nonlinear cost function. However, as they use a linear FIR filter with a convex decision region, their residual estimation error is high. In the paper, four nonlinear blind equalization schemes that employ a complex-valued multilayer perceptron instead of the linear filter are proposed and their learning algorithms are derived. After the important properties that a suitable complex-valued activation function must possess are discussed, a new complex-valued activation function is developed for the proposed schemes to deal with QAM signals of any constellation sizes. It has been further proven that by the nonlinear transformation of the proposed function, the correlation coefficient between the real and imaginary parts of input data decreases when they are jointly Gaussian random variables. Last, the effectiveness of the proposed schemes is verified in terms of initial convergence speed and MSE in the steady state. In particular, even without carrier phase tracking procedure, the proposed schemes correct an arbitrary phase rotation caused by channel distortion.
Bibliography:ObjectType-Article-2
SourceType-Scholarly Journals-1
ObjectType-Feature-1
content type line 23
ObjectType-Article-1
ObjectType-Feature-2
ISSN:1045-9227
DOI:10.1109/72.728394