Efficiently calculate exponentially weighted moving averages of matrix?

Hi, I've seen movmean function to calculate the moving average, but is there any function to compute the exponentially weighted moving average of a matrix of values? I would like to compute it considering a window moving over rows.

Thank you for your help.

Answer 1

[Bill Tubbs]

I find the easiest way is to use a discrete filter. But the input data is in columns here not rows:

x = [0 1 1 1 1; 0 0 1 1 1]';  % input signals in columns
a = 0.4;  % smoothing factor (0 to 1);
% y(k) = a / (1 - (1-a)*q^-1) * x(k)
y = filter(a,[1 a-1], x)

y =

0 0

0.4000 0

0.6400 0.4000

0.7840 0.6400

0.8704 0.7840