e_lda_a.m

具有图形操作界面的支持向量机多类分类实验系统.全部用Matlab实现,可以实现多种分类识别. 这是本人的毕业设计的附属程序

%addpath G:\Matlab_EXP\stprtool
%addpath G:\Matlab_EXP\stprtool\data

% Generate data
distrib.Mean = [[5;4] [4;5]]; % mean vectors
distrib.Cov(:,:,1) = [1 0.9; 0.9 1]; % 1st covariance
distrib.Cov(:,:,2) = [1 0.9; 0.9 1]; % 2nd covariance
distrib.Prior = [0.5 0.5]; % Gaussian weights
data = gmmsamp(distrib,250); % sample data
 subplot(3,3,1);title('原始分布');
 h1=ppatterns(data);
 legend([h1],'Training set');

lda_model = lda(data,1); % train LDA
lda_rec = pcarec(data.X,lda_model);
lda_data = linproj(data,lda_model);
 subplot(3,3,2);title('IDA_分布');
 h2=ppatterns(lda_data);
 legend([h2],'IDA set');



pca_model = pca(data.X,1); % train PCA
pca_rec = pcarec(data.X,pca_model);
pca_data = linproj( data,pca_model);

 subplot(3,3,3);title('PCA_分布');
 h5=ppatterns(pca_data);
 legend([h5],'PCA set');
 
%h3 = plot(lda_rec(1,:),lda_rec(2,:),'r');
%h4 = plot(pca_rec(1,:),pca_rec(2,:),'b');
%legend([h3 h4],'LDA direction','PCA direction');

subplot(3,3,4);title('LDA分布');
ppatterns(lda_data);
pgauss(mlcgmm(lda_data));

subplot(3,3,5); title('PCA'); 
ppatterns(pca_data);
pgauss(mlcgmm(pca_data));