Find Coefficients of an equation

1 visualización (últimos 30 días)
Learning
Learning el 18 de Feb. de 2024
Respondida: Star Strider el 18 de Feb. de 2024
Hi, I have a table containing 3 columns of data. I also have an equation with 4 unknown coefficients. How do I fit/solve the equation using the table data to obtain the unknown coefficients using Matlab?
Thanks!
  2 comentarios
Torsten
Torsten el 18 de Feb. de 2024
Why three columns and not two ? Do you have two independent variables in your equation:
column3 = f(column1,column2)
?
Learning
Learning el 18 de Feb. de 2024
Thanks for responding. Yes I have 2 independent variables.

Iniciar sesión para comentar.

Respuesta aceptada

Star Strider
Star Strider el 18 de Feb. de 2024
Using two independent variables is relatively straightforward. You need to concatenate them, then refer to them individually inside the objective function.
Data = randn(10,3);
objfcn = @(b, xy) b(1).*exp(-((xy(:,1)-b(2)).^2+(xy(:,2)-b(3)).^2)*b(4));
xy = Data(:,[1 2]);
[B,resnrm] = fminsearch(@(b)norm(Data(:,3) - objfcn(b,xy)), rand(4,1))
Exiting: Maximum number of function evaluations has been exceeded - increase MaxFunEvals option. Current function value: 2.628093
B = 4×1
-2.9726 1.7228 0.1193 9.6214
resnrm = 2.6281
N = 25;
x = linspace(min(Data(:,1)), max(Data(:,1)), N);
y = linspace(min(Data(:,2)), max(Data(:,2)), N);
[X,Y] = ndgrid(x,y);
fitfcn = @(b,X,Y) b(1).*exp(-((X-b(2)).^2+(Y-b(3)).^2)*b(4));
Z = fitfcn(B,X,Y);
figure
scatter3(Data(:,1), Data(:,2), Data(:,3), 'filled')
hold on
surf(X, Y, Z, 'FaceAlpha',0.5)
hold off
colormap(turbo)
This is a random example.
.

Más respuestas (0)

Categorías

Más información sobre Linear and Nonlinear Regression en Help Center y File Exchange.

Productos


Versión

R2023b

Community Treasure Hunt

Find the treasures in MATLAB Central and discover how the community can help you!

Start Hunting!

Translated by