Variable Step-Size Partial Rank Adaptive Filter Algorithm Based on Unifidd Framework

Employing a recently introduced framework within which a large number of classical aud modern adaptive filter algorithms can be viewed as pecial cases, we have developed a generic variable step-size adaptive filter. Variable Step-Size normalized least Inean square (VSSNLMS) and VSS Affine Projection Algoritlrrns (VSSAPA) are particular examples of adaptive algorithnrs covered by this generic adaptive filter. In this papel we introduce the new VSS Paftial Rank (VSSPR) adaptive filter algorithm based on the generic VSS adaptive filter. The proposed algorithr.n has faster convelgence rate and lower steady state mean square error compare with PRA.

کلیدواژه ها:

Adaptive filter ، variable step-size ، Partial Rank A I gorithm (PRA) ، Un ifi ed Frarnework.