A fast wavelet-based blind signal separation

It is well known that, signal separation algorithms using de-correlation-based methods alone, are not sufficient for signal separation of mixed digital modulation signals. In this paper, it has been shown that it is possible to retain the simplicity of these methods and still be able to successfully separate mixed digital signals, by designing the decoupling system to maximize the output normalized kurtosis functions. Moreover, computations can be further reduced, by designing the decoupling system on the basis of minimizing the cross correlation between the wavelet packet coefficients decomposition of its outputs, at various nodes and a specific decomposition depth. Illustrative examples are given to verify these results.