Blind Sources Separation Algorithm Based on Adaptive Givens Rotations

Blind Source Separation (BSS) problems generally can be simplified as an optimization model with orthogonal constraints. Addressing it, natural gradient algorithms are often used. But this kind of algorithm converges relatively slowly and the separation accuracy is sensitive to step size parameter. An adaptive Givens rotations algorithm is proposed in this paper in order to make faster convergence and do not need any more step size parameters. Simulations show that the proposed algorithm is a robust and promising method in BSS comparing with the other similar problems.