Recurrent neural network based bit error rate prediction for narrowband fading channel

Authors:
Gowrishankar;H. S. Ramesh Babu;P. S. Satyanarayana
Affiliations:
B.M.S. College of Engineering, Bangalore, India;B.M.S. College of Engineering, Bangalore, India;B.M.S. College of Engineering, Bangalore, India
Venue:
CSN '07 Proceedings of the Sixth IASTED International Conference on Communication Systems and Networks
Year:
2007

Citing 9
Cited 0

Modeling multipath fading channel dynamics for packet data performance analysis

Wireless Networks
Neural Networks: A Comprehensive Foundation

Neural Networks: A Comprehensive Foundation
Link Characteristics Estimation For IEEE 802.11 DCF Based WLAN

LCN '04 Proceedings of the 29th Annual IEEE International Conference on Local Computer Networks
Performance Evaluation of GAP-RBF Network in Channel Equalization

Neural Processing Letters
Fast communication: Non-linear RLS-based algorithm for pattern classification

Signal Processing
2007 Special Issue: Decoupled echo state networks with lateral inhibition

Neural Networks
Adaptive decision feedback equalization for digital satellite channels using multilayer neural networks

IEEE Journal on Selected Areas in Communications
Gradient radial basis function networks for nonlinear and nonstationary time series prediction

IEEE Transactions on Neural Networks
Power prediction in mobile communication systems using an optimal neural-network structure

IEEE Transactions on Neural Networks

Quantified Score

Hi-index	0.00

Visualization

Abstract

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.