University of Khartoum

Rayleigh Fading Channel Equalization using Neural Networks

Rayleigh Fading Channel Equalization using Neural Networks

Show full item record

Title: Rayleigh Fading Channel Equalization using Neural Networks
Author: Elsidig, Abdelmojeb Eltaib
Abstract: Data transmission over band limited channel introduces ISI and additive white noise (AWGN) leading to signal distortion and loss of information. The objective of this research is to design a model of channel equalizer based on feed forward neural network for Rayleigh fading channel. The method to accomplish the objective was sought first by designing a communication model system with binary phase shift keying (BPSK) modulation, Rayleigh fading channel and AWGN. Then a Neural Network model was designed to work as an equalizer within the system. The system was simulated on Matlab to test the equalizer’s performance in terms of bit error rate (BER). The neural model was constructed using the toolbox provided by Matlab, and then the equalizer model was set and simulated. The result for the quality with which the equalizer compensates the distortion upon the signal was taken in terms of BER against Signal to Noise Ratio (SNR) for different values of maximum Doppler shift and number of paths. The research concluded that feed forward neural network channel equalizer with back propagation learning algorithm proved its ability to mitigate Rayleigh channel distortion. It is also found that with SNR greater than 10dB on average, the system works more efficiently on one path and four paths on a variation of max Doppler shift values ranging from 1 to 200.
URI: http://khartoumspace.uofk.edu/123456789/26104


Files in this item

Files Size Format View

This item appears in the following Collection(s)

Show full item record

Share

Search DSpace


Browse

My Account