GFDM TRANSCEIVER BASED ON ANN CHANNEL ESTIMATION

Generalized frequency division multiplexing (GFDM) is one of the candidate waveforms beyond 5G for wireless communication. Channel estimation challenging in transmission because inherent interference. It based on a pilot signal that uses Least Square (LS) and Normalized Mean (NLMS) to perform estimation. This paper used Artificial Neural Network (ANN) as channel method, considered novel process GFDM transceiver. The ANN depends data set generated from LS estimation, which considers proposed method optimized backpropagation neural network. algorithm fitness function estimate channel. Levenberg-Marquardt (LM), Bayesian Regularization (BR), Scaled Conjugate Gradient (SCG) training methods by using Matlab toolbox BR gives best performance than other at 22 neurons hidden layers, 20dB give BER = 0.0369 enhanced over 0.08.