# How to fit curve using for loop?

조회 수: 19(최근 30일)
Ass 2021년 10월 4일
댓글: Mathieu NOE 2021년 10월 25일
I have a 15 number of signals with data point 64 in each. I want to use loop to fit all the signals with fittype 'gauss2' and plot all the curves with thier fitting. I have written like this but it is showing eroor. Kindly suggest me to resolve this. Thank you.
figure;
for i1=1:64
for j1=1:15
recon1_f(j1)=fit(t(i1),recon_amp2_1(:,j1),'gauss2');
h2{i}=plot(recon1_f(j1),t,recon_amp2_1(:,j1));
ylim([0 0.05]);
end
end
##### 댓글 수: 1표시숨기기 없음
Mathieu NOE 2021년 10월 4일
hi
maybe you should share some data so we can test the code
tx

댓글을 달려면 로그인하십시오.

### 채택된 답변

Mathieu NOE 2021년 10월 4일
hello again
in the mean time I created this example (only 5 loops) on dummy data
NB you only need one for loop and not two as in your code
hope it helps
clearvars
clc
% dummy data
x1 = [0:1:20];
y1 = [0,0.004,0.008,0.024,0.054,0.112,0.33,0.508,0.712,0.926,1,0.874,0.602,0.404,0.252,0.146,0.074,0.036,0.018,0.004,0];
for ci = 1:5
% modify x and y range (dummy data generation)
x = x1*ci;
y = y1*ci^2 + 0.1*rand(size(y1));
% curve fit using fminsearch
f = @(a,b,c,x) a.*exp(-(x-b).^2 / c.^2);
obj_fun = @(params) norm(f(params(1), params(2), params(3),x)-y);
sol = fminsearch(obj_fun, [max(y),max(x)/2,max(x)/6]);
a_sol = sol(1);
b_sol = sol(2);
c_sol = sol(3);
xx = linspace(min(x),max(x),300);
y_fit = f(a_sol, b_sol,c_sol, xx);
yy = interp1(x,y, xx);
Rsquared = my_Rsquared_coeff(yy,y_fit); % correlation coefficient
figure(ci)
plot(xx, y_fit, '-',x,y, 'r .', 'MarkerSize', 40)
title(['Gaussian Fit / R² = ' num2str(Rsquared) ], 'FontSize', 15)
ylabel('Intensity (arb. unit)', 'FontSize', 14)
xlabel('x(nm)', 'FontSize', 14)
eqn = " y = "+a_sol+ " * exp(-(x - " +b_sol+")² / (" +c_sol+ ")²";
legend(eqn)
end
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
function Rsquared = my_Rsquared_coeff(data,data_fit)
% R2 correlation coefficient computation
% The total sum of squares
sum_of_squares = sum((data-mean(data)).^2);
% The sum of squares of residuals, also called the residual sum of squares:
sum_of_squares_of_residuals = sum((data-data_fit).^2);
% definition of the coefficient of correlation is
Rsquared = 1 - sum_of_squares_of_residuals/sum_of_squares;
end
##### 댓글 수: 20표시숨기기 이전 댓글 수: 19
Mathieu NOE 2021년 10월 25일
hello
seems to me the index i1 is not usedin the line
c(i,:,i2)=(data(p(i),:));
so It should be
c(i,i1,i2)=(data(p(i),:));

댓글을 달려면 로그인하십시오.

### Community Treasure Hunt

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

Start Hunting!

Translated by