A Compact Pi Network for Reducing Bit Error Rate in Dispersive FIR Channel Noise Model

Abstract

During signal transmission, the combined effect of the transmitter filter, the transmission medium, and additive white Gaussian noise (AWGN) are included in the channel which distort and add noise to the signal. This causes the well defined signal constellation to spread causing errors in bit detection. A compact pi neural network with minimum number of nodes is proposed. The replacement of summation at each node by multiplication results in more powerful mapping. The resultant pi network is tested on six different channels. Keywords—Additive white Gaussian noise, digital communication system, multiplicative neuron, Pi neural network. I. INTRODUCTION HE most basic elements of a communication system is a source of signal, a channel which introduces distortion as well as noise and a receiver with a means of detecting errors caused by noise. As higher-level modulation becomes more desirable to cope with the need for high-speed data transmission, nonlinear distortion becomes a major factor, which limits the performance of communication systems. Additive Gaussian noise can disturb the digitally modulated signal during transmission. Additive superimposed noise normally has a constant power density and a Gaussian amplitude distribution throughout the bandwidth of a channel. The source in the communication system model generates a 4- QAM complex valued symbol set. The combined effect of the transmitter filter, the transmission medium, and additive white Gaussian noise (AWGN) are included in the channel. A widely used channel model is a finite impulse response (FIR) model whose output at time instant k is given by (1):