Blind identification of single-input multiple-output pole-zero systems

In this paper, we present a technique for the blind identification of single-input multiple-output (SIMO) pole-zero (PZ) systems using only the second-order statistics of the system output data. We utilize the structure of the SIMO system and the commutative property of the convolution operation to provide a simple approach for solving the above problem. In this method, we first estimate the products of all permutations of a numerator and a denominator polynomial from two different channels. The individual numerator and denominator polynomials for each channel are then extracted from the above estimates. Once the channel parameters have been found, an estimate of the input sequence can be obtained. The system input is treated as an unknown deterministic sequence, and hence, restrictive i.i.d. assumptions on the input sequence are not required. The performance of the method is promising, even with short records of data.