Stationary points of a kurtosis maximization algorithm for blind signal separation and antenna beamforming

Blind source separation has been the subject of extensive research activiti es in recent years, In particular blind antenna beamforming is an effective signal separation technique for communication systems to combat co-channel interference. Among many potential candidate approaches, the simple consta nt modulus algorithm (CMA) has been widely studied and used in practice. CM A is designed to capture and separate signals with negative kurtosis, Howev er, when some signals have positive kurtoses, CMA is unable to capture and separate these sources, In this paper, we will show that the kurtosis maxim um algorithm (KMA) can capture signals with both the positive and negative kurtoses, Its global convergence proof is presented for noiseless systems w ith multiple signals sources and for systems with a single source and zero- kurtosis (such as Gaussian) additive noise.