nlrls2.m

《自适应滤波算法与实现》（第二版）源码

%NLRLS2 Problem 1.1.1.2.5
%
%   'ifile.mat' - input file containing:
%      I - members of ensemble
%      K - iterations
%      a1 - coefficient of input AR process
%      sigmax - standard deviation of input
%      Wo - coefficient vector of plant
%      sigman - standard deviation of measurement noise
%      epsilon - small auxiliary constant
%      lambda - forgetting factor
% 
%   'ofile.mat' - output file containing:
%      ind - sample indexes 
%      MSNE - mean-square normalized error

clear all	% clear memory
load ifile;	% read input variables
sigmav=sigmax*sqrt(1-a1^2);	
		% standard deviation of input to AR process
L=length(Wo);		% plant and filter length
N=L-1;			% plant and filter order
MSNE=zeros(K,1);	% prepare to accumulate MSNE*I

for i=1:I,		% ensemble
   X=zeros(L,1);    	% initial memory
   v=randn(K,1)*sigmav;		% input to AR process
   x=filter([1,0],[1,a1],v);	% input 
   n=randn(K,1)*sigman;		% measurement noise 
   %
   % initial parameters
   deltan=zeros(1,L);
   deltaDn=zeros(1,L);
   oldebn=zeros(1,L);
   sigma2x=epsilon;
   sigma2d=epsilon;
   for k=1:K,		% iterations
      X=[x(k)		
         X(1:N)];	% new input vector
      d=Wo'*X+n(k);	% noisy desired signal sample
      sigma2x=lambda*sigma2x+(x(k))^2;	% input signal power
      sigma1x=sqrt(sigma2x);
      sigma2d=lambda*sigma2d+d^2;	% desired signal power
      sigmad=sqrt(sigma2d);
      %
      % initialization
      ebn(1)=x(k)/sigma1x;
      efn=ebn(1);
      en=d/sigmad;
      for j=1:L,	% orders
         %
         % auxiliary parameters
         oldauxeb=sqrt(1-(oldebn(j))^2);
         auxeb=sqrt(1-(ebn(j))^2);
         auxef=sqrt(1-efn^2);
         deltan(j)=deltan(j)*oldauxeb*auxef+oldebn(j)*efn;
         auxdelta=sqrt(1-(deltan(j))^2);
         %
         % prediction errors
         ebn(j+1)=(oldebn(j)-deltan(j)*efn)/auxdelta/auxef;
         efn=(efn-deltan(j)*oldebn(j))/auxdelta/oldauxeb;
         %
         % feedforward filtering
         deltaDn(j)=deltaDn(j)*auxeb*sqrt(1-en^2)+en*ebn(j);
         auxdeltaD=sqrt(1-(deltaDn(j))^2);
         en=(en-deltaDn(j)*ebn(j))/auxeb/auxdeltaD;
      end
      MSNE(k)=MSNE(k)+en^2;	% accumulate MSNE*I
      %
      % updated parameter
      oldebn=ebn;
   end
end

ind=0:(K-1);		% sample indexes
MSNE=MSNE/I;		% calculate misadjustment
save ofile ind MSNE;	% write output variables