Blind Adaptive Equalization of MIMO Systems: New Recursive Algorithms and Convergence Analysis

An adaptive (recursive in time) filtering method is proposed for blind deconvolution of multiple-input multiple-output (MIMO) channels modeled by an autoregressive moving average (ARMA) process. This method consists of two recursive schemes. The adaptive blind identification algorithm estimates the MIMO system impulse response. These estimates are then used in an adaptive Wiener-type filter to extract the instantaneous mixture of input sources. Such a mixture is further processed by a blind source separation algorithm to obtain the individual sources. Only second-order (SOS) statistics are used, and precise knowledge of the system order is not required as long as it is overmodeled. We also present an algorithm for the case of time-varying parameters. It is proved that the developed algorithms are globally convergent with probability one.