i want to solve nonlinear regression problem. input variable 'x' is two element. also output variable 'T' = two element.
but An error has occurred in matlab.
how can i solve it.
help me.....
here is my code.
clear all close all clc;
x(1,:) = 0:1:100; x(2,:) = 100:1:200; v = [4 8 5 3 ]; mdl = @(b,t)( b(1)*t.^3 + b(2)*t.^2 + b(3)*t + b(4)); T = mdl(v,x); S = mdl(v,x) + 10000*randn(1,101); beta0 = [0 0 0 0]; beta = nlinfit(x,S,mdl,beta0); %beta %result = mdl(beta,x);
figure(1) grid on hold on
plot(S','ro') %plot(result)6

 Réponse acceptée

Prajit T R
Prajit T R le 19 Mar 2018

0 votes

Hi Kim
The second argument to the nlinfit function only accepts a vector. So it would be better to fit 'x' element-wise. I have modified your code to illustrate the same. I am not sure if this is what you're looking for, but this might help:
x(1,:) = 0:1:100;
x(2,:) = 100:1:200;
v = [4 8 5 3 ];
mdl = @(b,t)( b(1)*t.^3 + b(2)*t.^2 + b(3)*t + b(4));
T = mdl(v,x);
S = mdl(v,x) + 10000*randn(1,101);
beta0 = [0 0 0 0];
size(x)
size(S)
beta1 = nlinfit(x(1,:),S(1,:),mdl,beta0);
beta2 = nlinfit(x(2,:),S(2,:),mdl,beta0);
result = mdl([beta1 beta2],x);
figure(1)
grid on
hold on
plot(S','ro')
figure
plot(result)
Cheers

Plus de réponses (0)

Community Treasure Hunt

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

Start Hunting!