Recurrent Neural Network based Bit Error Rate Prediction for Narrowband Fading Channel

Gowrishankar, Ramesh Babu H.S., and Satyanarayana P.S. (India)


Narrowband, Fading, BER, Nonlinear and Recurrent neural network.


This paper focuses on prediction of Bit Error Rate (BER) in a time varying flat and slow fading channel of narrow band wireless network. Here the time varying fading channel is modeled as nonlinear and temporal system, Neuro-computing systems are the best system to predict and analyze the behaviors of such nonlinear and temporal system. In this context BER prediction of two different neural network is investigated namely Recurrent Radial Basis Function network (RRBFN) and Echo state network (ESN) for k step prediction of BER. The predicted values are validated against simulation model and the results are promising.

Important Links:

Go Back