Unbiased identification of multivariable systems subject to colored noise

It is known that how to draw much more useful information from available sample data with a view to arriving at desired results is an important issue in system identification. A valuable new way of taking advantage of signal processing techniques to implement unbiased parameter estimation was reported by Feng and Zheng (1991). In this paper, some important extensions to their bias-eliminated least-squares method are made such that the method can be employed to perform unbiased identification of multi-input single-output systems subject to colored noise. The performance of the developed method is both analyzed theoretically and illustrated by means of some simulated examples