Open AccessNon‐parametric variable step‐size diffusion LMS algorithm over adaptive networks
Author(s) -
Han Hongyu,
Zhang Sheng,
Liang Hongbin
Publication year - 2017
Publication title -
electronics letters
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.375
H-Index - 146
ISSN - 1350-911X
DOI - 10.1049/el.2016.3828
Subject(s) - least mean squares filter , algorithm , parametric statistics , variable (mathematics) , convergence (economics) , rate of convergence , a priori and a posteriori , adaptive filter , diffusion , noise (video) , mathematics , adaptive algorithm , node (physics) , computer science , statistics , telecommunications , artificial intelligence , engineering , mathematical analysis , channel (broadcasting) , philosophy , physics , structural engineering , epistemology , economics , image (mathematics) , thermodynamics , economic growth
To address the conflicting requirement of fast convergence rate and low misadjustment, a new non‐parametric variable step‐size diffusion least mean squares (LMS) (NPVSSDifLMS) algorithm is presented. The non‐parametric variable step‐size scheme is obtained to cancel the influence of noise signals in the intermediate posteriori errors at every node. Simulation results show that this NPVSSDifLMS algorithm outperforms the DifLMS and VSSDifLMS algorithms.