Release Time:2019-03-12  Hits:

Indexed by: Conference Paper

Date of Publication: 2004-08-31

Included Journals: Scopus、CPCI-S、EI

Volume: 1

Page Number: 392-395

Key Words: adaptive filter; RLS; linear prediction

Abstract: In this paper, a new computationally efficient algorithm for recursive least-squares (RLS) algorithm called Reduced Order RLS. it is also called as Partial Updating RLS (PU-RLS), algorithm is introduced. The basic idea of UP-RLS algorithm is that a high order filter function is decomposed into two low order simple functions, and then update the sub filter coefficients partially which result in less computation. This kind of adaptive algorithm shows much more enhanced computational efficiency compared to the earlier works such as Split RLS algorithm but with better performance than Split RLS algorithm based on simulation results.