Adaptive IIR identification of stochastic systems with noisy input-output data

This paper is concerned with adaptive IIR filtering for linear systems with noisy input and output measurements. A new and numerically efficient proce dure for estimating the variances of the white input and output noises is e stablished so that the adaptive IIR filter based on the bias-eliminated lea st-squares algorithm can be efficiently implemented. This new adaptive IIR filter can achieve a substantial reduction in the computational effort, and meantime it can retain almost the same parameter estimation accuracy. Numerical results that illustrate the attractive properties of the new adap tive IIR filter are presented.