A recursive estimation of the condition number in the RLS algorithm [adaptive signal processing applications]

The recursive least-squares (RLS) algorithm is one of the most popular adaptive algorithms in the literature. This is due to the fact that it is easily derived and exactly solves the normal equations. In this paper, we present a very efficient way to recursively estimate the condition number of the input signal covariance matrix by utilizing fast versions of the RLS algorithm. We also quantify the misalignment of the RLS algorithm with respect to the condition number.

[1]  T. Kailath,et al.  A state-space approach to adaptive RLS filtering , 1994, IEEE Signal Processing Magazine.

[2]  S. Haykin,et al.  Adaptive Filter Theory , 1986 .

[3]  Editors , 1986, Brain Research Bulletin.

[4]  S. Thomas Alexander,et al.  Adaptive Signal Processing , 1986, Texts and Monographs in Computer Science.

[5]  Jacob Benesty,et al.  Adaptive Signal Processing: Applications to Real-World Problems , 2003 .

[6]  Maurice Bellanger,et al.  Adaptive digital filters and signal analysis , 1987 .

[7]  Gene H. Golub,et al.  Matrix computations , 1983 .