svm using matlab | Matlab Projects.....

svm using matlab

svm using matlab

2 comments:

Unknown said...: can I please get the svm dual for non-linearly separable cases in matlab?
email- sharmi.banerji@gmail.com
Thanks so much; February 28, 2013 at 11:35 AM
Unknown said...: Hi Sir,

Can you please help me with the plotting of results with the Kernel SVM code-
clc;
close all;
clear all;
N1=50;
N2=50;
C=1;
m1=[1 1];
m2=[4 4];
c1=[1.2 0;0 1.2];
c2=[1.5 0;0 1.5];
w1=mvnrnd(m1,c1,N1);
w2=mvnrnd(m2,c2,N2);
temp = cat(1,ones(N1,3),-ones(N2,3));
temp(1:N1,1:2)=w1;
temp(N1+1:N1+N2,1:2)=-w2;
data_set=temp;
g = @(x,y) (x*y'+1).^2;
X_data = cat(1,data_set(1:N1,1:2),-data_set(N1+1:N1+N2,1:2));
y = data_set(:,3);
H = (y*y').*g(X_data,X_data);
f=-ones(N1+N2,1);
Aeq=y';
beq=0;
lb=zeros(N1+N2,1);
ub=C*ones(N1+N2,1);
lambda=quadprog(H,f,[],[],Aeq,beq,lb,ub);

lambda(floor(10000*abs(lambda))==0)=0;
s =g(X_data,X_data);
% weight vector
w = g(data_set,data_set)*(y.*lambda);
q=find(lambda>0 & lambda<C-.000001);
for i=1:N1+N2
yi=(y.*lambda)*g(data_set(i,:),data_set);
end
yi(floor(10000*abs(yi))==0)=0;
figure
surf(yi);

I want to plot the data set and the decision surface together, but i am not sure about the axes so I just used the surf function.

Thanks,
Sharmi
sharmi.banerji@gmail.com; March 14, 2013 at 9:04 AM

Post a Comment

Subscribe to: Post Comments (Atom)