New beamforming method based on radial- basis function neural network processing in SαSG distribution noise environments

The under-determined problem of the blind source separation (BSS) for chaotic signals is intractable. A BSS algorithm is proposed and realized in this paper, which is also applied into a secret communication scheme. Both theoretical analysis and numerical simulations demonstrate that the proposed method is of higher security and precision for recovered source signals even when channel noise is very high.