Blind Beamforming Algorithm Based on Improved Complex Value Independent Component Analysis

In this paper, we propose an improved complex value independent component analysis (ICA) algorithm and apply it to beamforming. The main idea is to use a new cubic convergence Newton method to improve the complex value ICA algorithm, and design a fixed-point blind beamformer based on the improved complex value ICA algorithm. Simulation results show that our method is faster convergence than complex value ICA algorithm with the same error, and the beam of blind beamformer is very close to the optimal beam, which suppose the direction of arrival signal has been known.