wh_test.m

模拟退火程序:这部分代码是模式识别中结合模拟退火法的特征提取

0.303579915	0.557184815	-0.184752009	-0.131292473	-0.067370569	-0.062517091	0.01559215	0.034151763	-0.000029067	0.026575867	-0.000298681	0.009168611	;
0.30512901	0.578658155	-0.135637257	-0.199274092	-0.086412654	-0.066250143	0.040422397	0.017646563	0.037407363	0.003180789	0.008150494	-0.00302745	;



];

X(6,:,:)=[0.308456516	0.548699085	-0.188978063	-0.151401475	-0.05557065	-0.07151002	0.029697358	0.035295551	0.011350417	0.029611753	-0.000172193	0.004511909	;
0.303781897	0.572784321	-0.175900454	-0.15982919	-0.079770148	-0.062447534	0.031683803	0.021984255	0.018414898	0.022320333	0.00683321	0.000134725	;
0.313261341	0.556251172	-0.14013791	-0.212952853	-0.067862578	-0.078719935	0.047927774	0.027589061	0.049566641	0.005202673	0.008211293	-0.008349136	;
0.284908315	0.568808886	-0.131568384	-0.202095468	-0.076652587	-0.061235653	0.04478053	0.013812483	0.045367555	0.013242968	0.006149054	-0.005525492	;
0.287084687	0.575892201	-0.140922732	-0.198646949	-0.083573006	-0.064195266	0.044711147	0.017367295	0.046159505	0.01549979	0.006369112	-0.00575415	;
0.281049285	0.546456464	-0.140081671	-0.169099004	-0.056917687	-0.064495243	0.031842614	0.028793156	0.033243438	0.006694227	0.003922365	-0.0014173	;
0.383983213	0.548002583	-0.184058917	-0.275652385	-0.055645106	-0.103768595	0.073157602	0.033261197	0.069590444	0.017032398	0.010147945	-0.016082914	;
0.374519138	0.553724906	-0.190707924	-0.25493662	-0.061983979	-0.099767206	0.060571049	0.043637263	0.062121946	0.019263263	0.006255307	-0.012719783	;
0.355640049	0.543936317	-0.243642438	-0.202911814	-0.052304478	-0.097469392	0.043774927	0.059282718	0.042924694	0.058490116	-0.010574806	0.002811307	;
0.359162844	0.547757095	-0.211255408	-0.212579729	-0.056999616	-0.096230084	0.053912169	0.041651046	0.041713275	0.034392907	0.000339032	-0.001886479	;
0.37073123	0.565897482	-0.215098083	-0.229607878	-0.074524486	-0.099571865	0.057529297	0.042465989	0.052048413	0.033339256	0.001823458	-0.005058141	;
0.400155396	0.549113312	-0.238149121	-0.249824441	-0.063563098	-0.101323625	0.049738291	0.049822996	0.065991272	0.03957486	0.004851617	-0.006410054	;
0.338221576	0.576300872	-0.188435064	-0.225054272	-0.087096194	-0.084162971	0.053139915	0.032710663	0.06557034	0.022029086	0.008510094	-0.011759612	;
0.350176366	0.563933031	-0.20363074	-0.230582781	-0.071850125	-0.093315092	0.055982655	0.040994853	0.059798675	0.034395192	0.002484973	-0.008412053	;
0.555473345	0.37083975	-0.240262683	-0.223004053	-0.097697719	-0.064257521	0.044624972	0.058484884	0.048509062	0.054528699	-0.007336872	0.000070482	;
0.374892418	0.544474087	-0.256459686	-0.214016897	-0.051435968	-0.101975964	0.046138477	0.060299388	0.041929186	0.062916871	-0.009850469	0.003043985	;
0.373539707	0.550129301	-0.199687214	-0.239908892	-0.061132904	-0.092641448	0.058865606	0.032099332	0.058361548	0.021800715	0.01064277	-0.012094524	;
0.365476534	0.543556545	-0.227296181	-0.21830308	-0.052827831	-0.099557678	0.055808394	0.046384472	0.044403476	0.048257135	-0.003494629	-0.002444588	;
0.375529756	0.544625419	-0.257572321	-0.214453327	-0.051800869	-0.101087428	0.045643802	0.060581287	0.041922208	0.064314221	-0.01057276	0.002827199	;
0.411438142	0.553999796	-0.227747657	-0.280450597	-0.069643537	-0.108752036	0.064789817	0.052056019	0.088674407	0.027432307	0.00872837	-0.020550431	;
0.398129002	0.557652407	-0.208170683	-0.276174732	-0.066935544	-0.10756104	0.073927027	0.041315971	0.060877116	0.03761378	0.001159061	-0.011863093	;
0.336487548	0.549179705	-0.22248214	-0.197190513	-0.057758971	-0.094604488	0.048226009	0.049055308	0.043444006	0.049415616	-0.002144146	-0.001648939	;
0.337802247	0.564347324	-0.218009438	-0.207178505	-0.074593061	-0.088635877	0.049467306	0.040646739	0.039328062	0.060355439	-0.004740133	0.001194481	;
0.355938167	0.575604047	-0.211722199	-0.239591565	-0.083117461	-0.09686185	0.057876637	0.047561386	0.06111299	0.043718077	-0.002123816	-0.008430425	;
0.37477778	0.560157551	-0.213976915	-0.247519687	-0.069665546	-0.098426945	0.055614655	0.04330301	0.064873199	0.03405877	0.004070168	-0.007295272	;
0.334903972	0.552946636	-0.212306554	-0.1914372	-0.064619539	-0.085960555	0.050583161	0.040093687	0.033374037	0.05042884	-0.00518336	-0.002856815	;
0.327272099	0.551333354	-0.185449303	-0.224684349	-0.060500063	-0.085737278	0.05303093	0.034436475	0.057150916	0.037599907	0.002888804	-0.007362706	;
0.348667887	0.549653961	-0.213215023	-0.221129093	-0.058311993	-0.100194115	0.053738556	0.045334916	0.048043265	0.04886101	0.000125173	-0.00160962	;
0.340675713	0.542173342	-0.167051213	-0.245998032	-0.050804746	-0.091025502	0.059499738	0.034942587	0.05955035	0.023414168	0.003756096	-0.009157437	;
0.303151042	0.560101131	-0.140777648	-0.203372669	-0.068370781	-0.069807385	0.048251684	0.018807546	0.032208137	0.018505477	0.003736952	-0.002440018	;
0.305409415	0.574160144	-0.152002982	-0.197408617	-0.079876054	-0.071389919	0.044190719	0.02896688	0.038857323	0.012856645	0.003509259	-0.007282798	;
0.33629833	0.584954854	-0.186508636	-0.214087632	-0.092964464	-0.08965557	0.058738941	0.038395445	0.045567546	0.028607399	0.000947341	-0.010310975	;
0.298917412	0.527207473	-0.157706757	-0.17685105	-0.036602563	-0.067412606	0.032019216	0.028431043	0.034558027	0.012087569	0.005821723	-0.000480218	;
0.297499863	0.543506549	-0.122193058	-0.203849508	-0.050257985	-0.07160026	0.047020521	0.02617755	0.04567158	-0.009484969	0.007574721	-0.010071673	;
0.283962213	0.537110356	-0.108000866	-0.199877438	-0.045228459	-0.064636766	0.04552588	0.016758938	0.046094482	-0.012408711	0.010864205	-0.010168727	;
0.296797944	0.567841432	-0.149398819	-0.191120593	-0.076513251	-0.063202009	0.038780812	0.024686343	0.042258255	0.01246435	0.006109127	-0.008713156	;
0.32174269	0.550792658	-0.202172837	-0.153583005	-0.062116247	-0.079010374	0.032125458	0.045063227	0.015017716	0.033790809	-0.003950211	0.002288772	;
];
[Species_Sum,Sample_Sum,Parameter_Sum_All]=size(X);
% %--------------------------------------------------------------------------参数初始化
% Species_Sum=6;%类别总数
% Sample_Sum=37;%每一类中样本的个数，注每一类的样本数必须相等
% Parameter_Sum_All=12;
% %--------------------------------------------------------------------------
Probability=1/Species_Sum;%概率,因为每类中样本数相等,所以概率也相同

Y=zeros(Species_Sum,Sample_Sum,Parameter_Sum);
A=Rand_Tong_yong(Parameter_Sum_All,Parameter_Sum);
for sort=1:Species_Sum
    for i=1:Parameter_Sum
        Position=A(i);
        Y(sort,:,i)=X(sort,:,Position);
    end
end%---------随机产生由四个参数(从6个中取)组成的矩阵

Std=zeros(Species_Sum,Parameter_Sum);
for sort=1:Species_Sum
    Std(sort,:)=std(Y(sort,:,:));
end

mean=zeros(Species_Sum,Parameter_Sum);%mean是类内的均值
for sort =1:Species_Sum                
    for number=1:Sample_Sum            %number是样本编号
          h(1,:)=1/Sample_Sum*Y(sort,number,:);
          mean(sort,:)=mean(sort,:)+h(1,:);    
    end
end

Mean=zeros(1,Parameter_Sum);
for sort=1:Species_Sum
    Mean= Mean+Probability*mean(sort,:);
end

Jd=zeros(Parameter_Sum);Sb=zeros(Parameter_Sum);Sw=zeros(Parameter_Sum);St1=zeros(Parameter_Sum);St2=zeros(Parameter_Sum);
for sort=1:Species_Sum
    Sw1=zeros(Parameter_Sum);
    for number=1:Sample_Sum
        hh(1,:)=Y(sort,number,:);
        St1=(hh(1,:)-mean(sort,:))'*(hh(1,:)-mean(sort,:));
        Sw1=Sw1+St1; 
    end
    St2=(mean(sort,:)-Mean)'*(mean(sort,:)-Mean);
    Sb=Sb+Probability*St2;
    Sw=Sw+Probability*(1/Sample_Sum)*Sw1;
end
% J1=trace(Sw+Sb);
% J2=trace(inv(Sw)*Sb);
% J3=log(norm(Sb)/norm(Sw));
J4=trace(Sb)/trace(Sw);
% J5=norm(Sw+Sb)/norm(Sw);
y=J4;
p=A;