Using a vector of coefficients in 'fittype'

Hi everyone,

I am trying to fit some lab data, but the number of coeffiecients is very big and I prefer to keep it as a vector. However, I cannot seem to make it work so I tried a simplified version from the manual:

function y = piecewiseLine(x,a,b,c,d,k)
    y = zeros(size(x));
    for i = 1:length(x)
        if x(i) < k
            y(i) = a + b.* x(i);
        else
            y(i) = c + d.* x(i);
        end
    end
end

Then:

x = [0.81;0.91;0.13;0.91;0.63;0.098;0.28;0.55;...
    0.96;0.96;0.16;0.97;0.96];
y = [0.17;0.12;0.16;0.0035;0.37;0.082;0.34;0.56;...
    0.15;-0.046;0.17;-0.091;-0.071];
ft = fittype(@(a, b, c, d, k, x)piecewiseLine(x,a,b,c,d,k), 'coefficients',{'a', 'b', 'c', 'd', 'k'});
f = fit( x, y, ft, 'StartPoint', [1, 0, 1, 0, 0.5] )

This works fine.

If I try to turn the coefficients into a vector:

function y = piecewiseLine(x,V)
    a=V(1);
    b=V(2);
    c=V(3);
    d=V(4);
    k=V(5);
    y = zeros(size(x));
    for i = 1:length(x)
        if x(i) < k
            y(i) = a + b.* x(i);
        else
            y(i) = c + d.* x(i);
        end
    end
end

And then do the fitting again like this:

x = [0.81;0.91;0.13;0.91;0.63;0.098;0.28;0.55;...
    0.96;0.96;0.16;0.97;0.96];
y = [0.17;0.12;0.16;0.0035;0.37;0.082;0.34;0.56;...
    0.15;-0.046;0.17;-0.091;-0.071];
ft = fittype(@(V, x)piecewiseLine(x,V), 'coefficients',{'V'});
f = fit( x, y, ft, 'StartPoint', [1, 0, 1, 0, 0.5] )

Then I get the following error:

Expression piecewiseLine(x,V) is not a valid MATLAB expression, has non-scalar coefficients, or cannot be evaluated

Is there a way to use a vector (nx1) of coefficients when fitting instead of n coefficients??

Thanks,

Andrea

Answer 1

[Sai Sri Pathuri]

The coefficients to fittype function cannot be passed as a vector. In order to get nearly same output, you can use lsqcurvefit function from Optimization Toolbox.