Nonlinear blind equalization schemes using complex-valued multilayer feedforward neural networks
Authors:
- Daesik HongDHDaesik Hong
- 1 January 1998
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Networks
- Vol. 9 (6) , 1442-1455
Abstract
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 this 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.Keywords
This publication has 24 references indexed in Scilit:
- Effect of nonlinear transformations on correlation between weighted sums in multilayer perceptronsIEEE Transactions on Neural Networks, 1994
- Parallel, self-organizing, hierarchical neural networks. IIIEEE Transactions on Industrial Electronics, 1993
- On the whereabouts of local minima for blind adaptive equalizersIEEE Transactions on Circuits and Systems II: Analog and Digital Signal Processing, 1992
- On the approximate realization of continuous mappings by neural networksNeural Networks, 1989
- Mapping abilities of three-layer neural networks1989
- Capabilities of three-layered perceptrons1988
- Convergence analysis of self-adaptive equalizersIEEE Transactions on Information Theory, 1984
- Nonlinear Equalization of Digital Satellite ChannelsIEEE Journal on Selected Areas in Communications, 1983
- Performance advantage of complex LMS for controlling narrow-band adaptive arraysIEEE Transactions on Acoustics, Speech, and Signal Processing, 1981
- Modeling and Performance Evaluation of Nonlinear Satellite Links-A Volterra Series ApproachIEEE Transactions on Aerospace and Electronic Systems, 1979