%0 Electronic Article
%A Long Shi
%+ School of Electrical Engineering, Southwest Jiaotong University, Chengdu 610031, People's Republic of China
%A Haiquan Zhao
%+ School of Electrical Engineering, Southwest Jiaotong University, Chengdu 610031, People's Republic of China
%K distributed network
%K a posterior estimation error minimization
%K fast convergence rate
%K high steady-state misalignment
%K low steady-state misalignment
%K variable step-size distributed incremental normalised LMS algorithm
%K least mean square algorithm
%K DINLMS algorithm
%X A variable step-size distributed incremental normalised least mean square (DINLMS) algorithm is proposed, in which the time-varying step-size of each node in the distributed network is obtained by minimising a posterior estimation error at that node. It overcomes the drawback that fast convergence rate with high steady-state misalignment or low steady-state misalignment with slow convergence rate, which always exists in the traditional DINLMS. The simulation results show that the proposed algorithm could achieve a better performance.
%@ 0013-5194
%T Variable step-size distributed incremental normalised LMS algorithm
%B Electronics Letters
%D April 2016
%V 52
%N 7
%P 519-521
%I Institution of Engineering and Technology
%U https://digital-library.theiet.org/;jsessionid=1tet1dj3ls3dk.x-iet-live-01content/journals/10.1049/el.2015.3882
%G EN