Multilayer Perceptron Based Equalizer with an Improved Back Propagation Algorithm for Nonlinear Channels

Abstract

Neural network based equalizers can easily compensate channel impairments; such additive noise and inter symbol interference (ISI). The authors present a new approach to improve the training efficiency of the multilayer perceptron (MLP) based equalizer. Their improvement consists on modifying the back propagation (BP) algorithm, by adapting the activation function in addition to the other parameters of the MLP structure. The authors report on experiment results evaluating the performance of the proposed approach namely the back propagation with adaptive activation function (BPAAF) next to the BP algorithm. To further prove its effectiveness, the proposed approach is also compared beside a so known nonlinear equalizer explicitly the multilayer perceptron with decision feedback equalizer MLPDFE. The authors consider various performance measures specifically: signal resorted quality, lower steady state MSE reached and minimum bit error rate (BER) achieved, where nonlinear channel equalization problems are employed.

An Improved Recursive Least Square Algorithm For Adapting Fuzzy Channel Equalizer

“…The nonlinear part is described by (14), whereas the FIR channel is chosen to be of non-minimum phase with coefficients set to [h 1 h 2 h 3 ] = [0.3482 0.8704 0.3482]. Such FIR channels are widely used in the literature to assess the equalization task [10,12].…”

“…Burst noise, amplifiers, converters, and the modulation process can produce nonlinear distortions. Different signal processing techniques have been implemented to perform adaptive channel equalization [3][4][5][6][7][8][9][10][11]. Conventional adaptive filtering techniques [2,4] perform well on linear channels, nevertheless, they perform poorly on severe and nonlinear channels [3,[6][7][8][9][10][11].…”

“…Different signal processing techniques have been implemented to perform adaptive channel equalization [3][4][5][6][7][8][9][10][11]. Conventional adaptive filtering techniques [2,4] perform well on linear channels, nevertheless, they perform poorly on severe and nonlinear channels [3,[6][7][8][9][10][11]. A diversity of nature and human intelligence-inspired techniques for channel equalization have been proposed [3,[5][6][7][8][9][10][11][12][13][14], including artificial neural networks [5][6][7][8][9][10][11], particle swarm optimization [12], artificial bee colony [13], firefly [14], and fuzzy logic [15][16][17][18][19].…”

Current Characteristics Estimation of Si PV Modules Based on Artificial Neural Network Modeling

“…A combination of MLP and the gradient descent method results in a very effective algorithm, known as the back propagation (BP) algorithm [25,26,27,28,29]. The main idea of the gradient descent method is to make the weight of each node move into the negative direction of the loss function gradient and make the network adjust the weight value of each node by itself.…”