Forums

LMS Equalization

Started by Helmi Kurniawan February 26, 2003
Hi all,

Anybody of you know how to use the matlab script provided in the book
DSP using matlab. The script is about LMS equalizer algorithm and as
follows:

function [h,y] = lms(x,d,delta,N)
% LMS Algorithm for Coefficient Adjustment
% ----
% [h,y] = lms(x,d,delta,N)
% h = estimated FIR filter
% y = output array y(n)
% x = input array x(n)
% d = desired array d(n), length must be same as x
% delta = step size
% N = length of the FIR filter
%
M = length(x); y = zeros(1,M);
h = zeros(1,N);
for n = N:M
x1= x(n:-1:n-N+1);
y = h * x1.';
error = d(n) - y(n);
h = h + delta*(error)*x1;
end

If i send the input array x =[1.03+1.002i 2.03+3i 2.06+3.32i
2.008+2.98i]

and let say the desired array is [1+i 2+3i 2+3i 3+3i]

and i used delta = 0.02 and N=4 how come the output only one and it
seems the error become larger, and hence it does not reduce the error.

Please explain about this and preferably with the example.

Thanks

Best regards,
Kurniawan



Here is an example,

x=randn(1,100);
y=filter([1 2 3 4],1,x);
[h,o]=lms(x,y,0.1,4);

I got h = [1.0004 1.9998 2.9996 3.9996]

I didnt try complex values.
In your code replace line y = h * x1.';
with y(n) = h * x1.';

Navan --- "Helmi Kurniawan <>"
<> wrote:
> Hi all,
>
> Anybody of you know how to use the matlab script
> provided in the book
> DSP using matlab. The script is about LMS equalizer
> algorithm and as
> follows:
>
> function [h,y] = lms(x,d,delta,N)
> % LMS Algorithm for Coefficient Adjustment
> % ----
> % [h,y] = lms(x,d,delta,N)
> % h = estimated FIR filter
> % y = output array y(n)
> % x = input array x(n)
> % d = desired array d(n), length must be same as
> x
> % delta = step size
> % N = length of the FIR filter
> %
> M = length(x); y = zeros(1,M);
> h = zeros(1,N);
> for n = N:M
> x1= x(n:-1:n-N+1);
> y = h * x1.';
> error = d(n) - y(n);
> h = h + delta*(error)*x1;
> end
>
> If i send the input array x =[1.03+1.002i 2.03+3i
> 2.06+3.32i
> 2.008+2.98i]
>
> and let say the desired array is [1+i 2+3i 2+3i
> 3+3i]
>
> and i used delta = 0.02 and N=4 how come the output
> only one and it
> seems the error become larger, and hence it does not
> reduce the error.
>
> Please explain about this and preferably with the
> example.
>
> Thanks
>
> Best regards,
> Kurniawan


__________________________________________________