Neural network-based techniques for efficient detection of variable-bit-rate signals in MC-CDMA systems working over LEO satellite networks

  • Authors:

  • Claudio Sacchi;Gianluca Gera;Carlo S. Regazzoni

  • Affiliations:

  • Department of Information and Communication Technology (DIT), University of Trento, Multimedia Communications and Networking Labs, Via Sommarive 14, I-38050 Trento, Italy;Department of Biophysical and Electronic Engineering (DIBE), CNIT-DIBE, University of Genoa, Signal Processing and Telecommunications Group (SP&T), Via Opera Pia 11/A, I-16145 Genoa, Italy;Department of Biophysical and Electronic Engineering (DIBE), CNIT-DIBE, University of Genoa, Signal Processing and Telecommunications Group (SP&T), Via Opera Pia 11/A, I-16145 Genoa, Italy

  • Venue:
  • Signal Processing
  • Year:
  • 2005

Quantified Score

Hi-index 0.09

Visualization

Abstract

For a few years, multicarrier modulations have been proposed as valuable alternatives with respect to state-of-the-art single carrier ones due to their resilience against interference and channel distortion effects. In particular, many studies are arising about multicarrier-CDMA (MC-CDMA) techniques that provide improved robustness and flexibility with respect to single-carrier spread-spectrum techniques. Satellite communications considered the employment of MC-CDMA for multimedia transmission very recently, especially for what concerns the delivery of variable-bit-rate services over low-earth-orbit (LEO) satellite networks. To this aim, the problems to be faced are mainly related to the development of efficient methodologies for satellite channel estimation, equalization and multi-user detection, in order to exploit in an optimal way the natural diversity inherent to MC-CDMA. In this paper we compare two different neural-network-based approaches for efficient reception of MC-CDMA signals in the case of asynchronous, multi-user, and variable-bit-rate transmission over LEO satellite channels. The first approach introduces neural networks for supporting receiver decision. The second more sophisticated approach exploits neural networks for joint channel estimation and symbol detection. Simulation results will be presented that demonstrate the improved effectiveness of the proposed methodologies, with respect to state-of-the-art MC-CDMA detection techniques, both in terms of reduced BER and in terms of low computational complexity.