An iterative blind cyclostationary beamforming algorithm
Ke-Lin Du, M.N.S. Swamy · 2003
The cross-correlation neural network proposed in Diamantaras and Kung (1994) is an efficient iterative method for singular value decomposition. In this paper, we propose an iterative blind cyclostationary beamforming algorithm, which is inspired by the cross-correlation neural model. It can be used to extract signals with cyclostationarity. The new algorithm is a gradient decent-based method. It is fast, simple, and easy to implement. Simulation shows that it can provide good performance as long as the learning rate is suitably selected.