Blind Separation of Cyclostationary Signals

Authors:
Nhat Anh Cheviet;Mohamed Badaoui;Adel Belouchrani;Francois Guillet
Affiliations:
LASPI EA3059, University of Saint Etienne, Jean Monnet, France;LASPI EA3059, University of Saint Etienne, Jean Monnet, France;Elec. Eng. Dept., Ecole Nationale Polytechnique, Algiers, Algeria;LASPI EA3059, University of Saint Etienne, Jean Monnet, France
Venue:
ICA '09 Proceedings of the 8th International Conference on Independent Component Analysis and Signal Separation
Year:
2009

Citing 8
Cited 0

Statistical spectral analysis: a nonprobabilistic theory

Statistical spectral analysis: a nonprobabilistic theory
Cyclic higher-order statistics: input/output relations for discrete- and continuous-time MIMO linear almost-periodically time-variant systems

Signal Processing
Cyclostationarity: half a century of research

Signal Processing
Separation of instantaneous mixtures of cyclo-stationary sources

Signal Processing
Blind separation of cyclostationary sources using joint block approximate diagonalization

ICA'07 Proceedings of the 7th international conference on Independent component analysis and signal separation
A blind source separation technique using second-order statistics

IEEE Transactions on Signal Processing
On the behavior of current second and higher order blind sourceseparation methods for cyclostationary sources

IEEE Transactions on Signal Processing
Blind source-separation using second-order cyclostationarystatistics

IEEE Transactions on Signal Processing

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper, we propose a new method for the blind source separation with assuming that the source signals are cyclostationarity. The proposed method exploits the characteristics of cyclostationary signals in the Fraction-of-Time probability framework in order to simultaneously separate all sources without restricting the distribution or the number of cycle frequencies of each source. Furthermore, a new identifiability condition is also provided to show which kind of cyclostationary source can be separated by the second-order cyclostationarity statistics. Numerical simulations are presented to demonstrate the effectiveness of the proposed approach.