A Derivation of a General Order, Multichannel Fast Transversal, Recursive Least Squares Filter Algorithm

Abstract

This paper examines the derivation of a general order, multiple input version of the fast transversal recursive least squares filter algorithm. The new algorithm, in which the order (or number of taps) associated with each input channel is independent, is distinguished from the previously published multichannel form of the fast transversal RLS algorithm, wherein each input channel was con strained to have the same order. This additional flexibility allows assignment of filter resources to particular channels, or independent assignment to the pole/zero estimators in an ARMA system identification application. A summary of the new algorithm is given, in proper order of execution. An operations count is also provided for each equation