貝葉斯分類器的matlab實(shí)現(xiàn)

1、貝葉斯分類器的matlab實(shí)現(xiàn)貝葉斯分類原理：1) 在已知P(Wi)，P(X|Wi)(i=1,2)及給出待識(shí)別的X的情況下，根據(jù)貝葉斯公式計(jì)算出后驗(yàn)概率P(Wi|X) ;2) 根據(jù)1)中計(jì)算的后驗(yàn)概率值，找到最大的后驗(yàn)概率，則樣本X屬于該類舉例：解決方案：但對(duì)于兩類來(lái)說，因?yàn)榉帜赶嗤?，所以可采取如下分類?biāo)準(zhǔn)：%By Shelley from NCUT，April 14th 2011%Email:just_for_%此程序利用貝葉斯分類算法，首先對(duì)兩類樣本進(jìn)行訓(xùn)練，%進(jìn)而可在屏幕上任意取點(diǎn)，程序可輸出屬于第一類，還是第二類%clear;close all%讀入兩類訓(xùn)練樣本數(shù)

2、據(jù)load data%求兩類訓(xùn)練樣本的均值和方差u1=mean(Sample1);u2=mean(Sample2);sigm1=cov(Sample1);sigm2=cov(Sample2);%計(jì)算兩個(gè)樣本的密度函數(shù)并顯示x=-20:0.5:40;y= -20:0.5:20;X,Y = meshgrid(x,y);F1 = mvnpdf(X(:),Y(:),u1,sigm1);F2 = mvnpdf(X(:),Y(:),u2,sigm2);P1=reshape(F1,size(X);P2=reshape(F2,size(X);figure(2)surf(X,Y,P1)hold onsurf(X

3、,Y,P2)shading interpcolorbartitle(條件概率密度函數(shù)曲線);%以下為測(cè)試部分%利用ginput隨機(jī)選取屏幕上的點(diǎn)（可連續(xù)取10個(gè)點(diǎn)）%程序可根據(jù)點(diǎn)的位置自動(dòng)地顯示出屬于那個(gè)類%pw1=0.4;pw2=0.6;figure(1)plot(Sample1(:,1),Sample1(:,2),r.)hold onplot(Sample2(:,1),Sample2(:,2),b.)for i=1:10u,v=ginput(1);plot(u,v,m*);P1=pw1*mvnpdf(u,v,u1,sigm1);P2=pw2*mvnpdf(u,v,u2,sigm2);hol

4、d allif(P1P2)disp(it belong to the first class);elsedisp(it belong to the second class);end;end%結(jié)果示意：兩個(gè)樣本的密度函數(shù)曲線：測(cè)試結(jié)果：命令窗口中顯示：it belong to the first classit belong to the second classit belong to the second classit belong to the first classit belong to the first classit belong to the first classit belong to the first classit belong to the first classit belong to the first classit belong to the first class分析可知在