Adaptive IIR filtering based on balanced-realization

Due to low parameter sensitivity for balanced realizations, balanced structure becomes a good candidate for an statespace adaptive infinite impluse response (IIR) filter. Here, using coefficients of the transfer function as the adaptive filtering parameters, a balanced adaptive IIR filtering algorithm is proposed for output-error minimization. The algorithm in the internally balanced realization guarantees that the adaptive IIR filter always minimizes the ratio of maximum-to-minimum eigenvalue of the Grammian matrices at the each iteration. Simulation results are provided to corroborate the proposed algorithm.