Linear neural network based blind equalization

Fang, Yong; Chow, Tommy W. S.; Ng, K.T.

doi:10.1016/s0165-1684(98)00245-x

Cited by 22 publications

(20 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Nonlinear adaptive filters based on a variety of neural network models was used successfully for system identification and noise-cancellation in a wide class of applications. An adaptive Recurrent Neural Network (RNN) based equalizer whose small size and high performance makes it suitable for high-speed communication channel equalization (Kechriotis, Zervas and Manolakos, 1994;Fang and Chow, 1999). Some novel blind equalization approach based on radial basis function (RBF) neural networks are proposed.…”

Section: Introductionmentioning

confidence: 99%

Optimized Decision Feedback Equalizer Algorithm based on Sparse Underwater Acoustic Channel

2016

Technical Journal of the Faculty of Engineering

View full text Add to dashboard Cite

A new optimized blind equalization algorithm for sparse underwater acoustic channel is proposed in this paper. The decision feedback equalizer is a common nonlinear equalizer to overcome the effect of noise in underwater acoustic communication. The decision feedback equalizer algorithm tracks the underwater acoustic channel change and utilizes the feedback information to adjust equalizer. The great calculation amount and complex structure lead the reduction of the algorithm performance. The proposed algorithmreduces the calculation amount with the help of simulated annealing algorithm based on sparse underwater acoustic channel and reaches the effectiveness. Based on the equalization model, various experimental performance analysis has proved that the convergence rate of the proposed algorithm was higher than common decision feedback equalizer algorithm.

show abstract

Section: Introductionmentioning

confidence: 99%

Optimized Decision Feedback Equalizer Algorithm based on Sparse Underwater Acoustic Channel

2016

Technical Journal of the Faculty of Engineering

View full text Add to dashboard Cite

show abstract

“…Most of the algorithms based on SOS use matrix decomposition, which first calculates channel parameters and then gives the equalized symbols. An alternative approach is the use of linear artificial neural networks (ANNs) for direct blind equalization [2]- [5], [11], [13], [14]. For the ANN the online learning is carried out with proper learning algorithms.…”

Section: Introductionmentioning

confidence: 99%

“…The output symbols are then the estimates of the original symbols multiplied by a unit norm constant. All the algorithms based on SOS make use of at least two correlation matrices of the source symbols: the correlation matrix with lag zero and the correlation matrix with lag one [1], [4], [5], [11], [18], [19]. Liu and Dong in [16] proved that a single correlation matrix can provide the equalization, but that is valid only for white sources, which are a special case of source symbols.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Blind Channel Equalization Using Second-Order Statistics: A Necessary and Sufficient Condition

Naveed¹,

Qureshi²,

Cheema³

et al. 2006

Circuits Syst Signal Process

View full text Add to dashboard Cite

In this work the blind equalization of a single-input, multiple-output channel has been carried out using second-order statistics. A sufficient and necessary condition for blind equalization based on second order statistics has been given. It has been proved that a single autocorrelation matrix of the source symbols is sufficient for blind equalization. The proposed scheme is generalized; that is, it is valid for white as well as colored source symbols. A linear artificial neural network is developed with a learning algorithm based on the new condition. The results of the new algorithm verify its validity and superior performance.

show abstract

“…The past few years have witnessed an increased interest in problems and techniques related to blind signal processing, especially blind equalization [1][2][3][4][5][6][7][8][9][10]. The classical methods of channel equalization rely on transmitting the training signal, known in advance by the receiver.…”

Section: Introductionmentioning

confidence: 99%

Feedforward neural network for blind equalization with PSK signals

Pandey

2005

Neural Comput & Applic

View full text Add to dashboard Cite

Most of the cost functions used for blind equalization are nonconvex and nonlinear functions of tap weights, when implemented using linear transversal filter structures. Therefore, a blind equalization scheme with a nonlinear structure that can form nonconvex decision regions is desirable. The efficacy of complexvalued feedforward neural networks for blind equalization of linear and nonlinear communication channels has been confirmed by many studies. In this paper we present a complex valued neural network for blind equalization with M-ary phase shift keying (PSK) signals. The complex nonlinear activation functions used in the neural network are especially defined for handling the M-ary PSK signals. The training algorithm based on constant modulus algorithm (CMA) cost function is derived. The improved performance of the proposed neural network in both, stationary and nonstationary environments, is confirmed through computer simulations.

show abstract

Linear neural network based blind equalization

Cited by 22 publications

References 19 publications

Optimized Decision Feedback Equalizer Algorithm based on Sparse Underwater Acoustic Channel

Optimized Decision Feedback Equalizer Algorithm based on Sparse Underwater Acoustic Channel

Blind Channel Equalization Using Second-Order Statistics: A Necessary and Sufficient Condition

Feedforward neural network for blind equalization with PSK signals

Contact Info

Product

Resources

About