MATLAB神经网络30个案例分析源代码[Demo]chapter12.pdf

SVM SVM 1 2 Matlab30 3 /vbuy.html 4 Matlab30 5 by liyang[faruto] @ faruto's Studio~ Email:faruto@163.com QQ:516667408 /faruto http://www.mfun.la Contents SVM SVM close all; clear; clc; format compact; % wine,classnumber = 3,wine:178*13,wine_labes:178*1 load chapter12_wine.mat; % figure subplot(3,5,1); hold on for run = 1:178 plot(run,wine_labels(run)); end title('class','FontSize',10); for run = 2:14 subplot(3,5,run); hold on; str = [ 'attrib ',num2str(run-1)]; for i = 1:178 plot(i,wine(i,run-1)); end title(str, 'FontSize',10); end % % 1-30,60-95,131-153 train_wine = [wine(1:30,:);wine(60:95,:);wine(131:153,:)]; % train_wine_labels = [wine_labels(1:30);wine_labels(60:95);wine_labels(131:153)]; % 31-59,96-130,154-178 test_wine = [wine(31:59,:);wine(96:130,:);wine(154:178,:)]; % file:///D|/Mydesktop/30/MATLAB30+/chapter12/html/chapter12.html[2010/11/16 22:44:40] SVM test_wine_labels = [wine_labels(31:59);wine_labels(96:130);wine_labels(154:178)]; % ,[0,1] % mapminmaxmatlab [train_wine,pstrain] = mapminmax(train_wine'); % 01 pstrain.ymin = 0; pstrain.ymax = 1; % [0,1] [train_wine,pstrain] = mapminmax(train_wine,pstrain); % mapminmaxmatlab [test_wine,pstest] = mapminmax(test_wine'); % 01 pstest.ymin = 0; pstest.ymax = 1; % [0,1] [test_wine,pstest] = mapminmax(test_wine,pstest); % ,libsvm train_wine = train_wine'; test_wine = test_wine'; SVM model = svmtrain(train_wine_labels, train_wine, '-c 2 -g 0.02'); SVM [predict_label, accuracy] = svmpredict(test_wine_labels, test_wine, model); Accuracy = 96.6292% (86/89) (classification) file:///D|/Mydesktop/30/MATLAB30+/chapter12/html/chapter12.html[2010/11/16 22:44:40] SVM %