Abstract
Neural network (NN) based channel estimation method has been proposed for identifying the parameters of a nonlinear time varying satellite channel. A multipath time-varying Ricean-fading channel has been considered in the analysis for a down link scenario. To study the flexibility and performance of the proposed method, the channel in question has been varied over a reasonable range of Doppler frequencies, and the estimation for each case has been made by employing 16-quadrature amplitude modulation (16-QAM) technique. Both back propagation (BP) and natural gradient (NG) algorithms have been studied for the channel identification technique. Finally, a NN maximum likelihood sequence estimator (NN-MLSE) based receiver has been studied for the addressed system. Simulation results show that the NN-MLSE receiver performs close to that of the ideal (the channel is perfectly known) MLSE receiver in terms of symbol error rate (SER).
Original language | English |
---|---|
Article number | 1556868 |
Pages (from-to) | 17-27 |
Number of pages | 11 |
Journal | GANIT: Journal of Bangladesh Mathematical Society |
Volume | 25 |
DOIs | |
Publication status | Published - 2005 |
Event | Canadian Conference on Electrical and Computer Engineering 2005 - Saskatoon, SK, Canada Duration: May 1 2005 → May 4 2005 |
Keywords
- MLSE
- Neural networks
- Parameter identification
- QAM
- Satellite channel
ASJC Scopus subject areas
- Electrical and Electronic Engineering
- Hardware and Architecture