yang.asv

粒子群算法

%function [ output_args ] = Untitled1( input_args )
%UNTITLED1 Summary of this function goes here
%  Detailed explanation goes here



%H1=xlsread('tading.xls',1,'A1:H123');
H1=xlsread('test.xls',1,'A1:J64');
%  [b,a]= butter(5,0.5);
%  H1=filtfilt(b,a,H);
  data=H1;
  data=(data-ones(size(data,1),1)*min(data))./(ones(size(data,1),1)*(max(data)-min(data)));
 H1=data;
 
 
 A1=H1(1:40,1:8);
 B1=H1(1:40,9);
 C1=H1(41:60,1:8);
 D1=H1(41:60,9);
%  A1=H1(1:80,1:7);
%  B1=H1(1:80,8);
%  C1=H1(81:120,1:7);
%  D1=H1(81:120,8); 

%       data=A;
%       data1=A;
%       data=(data-ones(size(data,1),1)*min(data))./(ones(size(data,1),1)*(max(data)-min(data)));
%       A1=data ;
% 
%       %  MOData=sqrt(sum(A.^2));
%       % A1=A./MOData(ones(n,1),:);
%       data2=B;
%       data=B;
%       data=(data-ones(size(data,1),1)*min(data))./(ones(size(data,1),1)*(max(data)-min(data)));
%       B1=data ;
% 
%       data=C;
%       data=(data-ones(size(data,1),1)*min(data1))./(ones(size(data,1),1)*(max(data1)-min(data1)));
%       C1=data;
%       %   MOData=sqrt(sum(C.^2));
%       %  C1=C./MOData(ones(p,1),:);
% 
%       data=D;
%       data=(data-ones(size(data,1),1)*min(data2))./(ones(size(data,1),1)*(max(data2)-min(data2)));
%       D1=data ;
    





     % max_ev =14;  %选择主元个数 tading
       max_ev =8;  %选择主元个数
      rbf_var = 1.4;  %髙斯函数的参数
      cov_size=40;     %样本个数
      for i=1:cov_size,    %得到K
          for j=i:cov_size,
              K(i,j) = exp(-norm(A1(i,:)-A1(j,:))^2/rbf_var);
              K(j,i) = K(i,j);
          end
      end
      unit = ones(cov_size, cov_size)/cov_size;
      % centering in feature space!
      K_n = K - unit*K - K*unit + unit*K*unit;

      [evecs,evals] = eig(K_n);
     % A2=evecs;
      evals = real(diag(evals));
      for i=1:cov_size,
          evecs(:,i) = evecs(:,i)/(sqrt(evals(i)));   
      end
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
      test_num=40;

      unit_test = ones(test_num,cov_size)/cov_size;
      K_test = zeros(test_num,cov_size);
      for i=1:test_num,
          for j=1:cov_size,
              K_test(i,j) = exp(-norm(A1(i,:)-A1(j,:))^2/rbf_var);
          end
      end
      K_test_n = K_test - unit_test*K - K_test*unit + unit_test*K*unit;
      test_features = zeros(test_num, max_ev);
      test_features = K_test_n * evecs(:,1:max_ev);
      A2=test_features;


%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
      test_num=20;
      unit_test = ones(test_num,cov_size)/cov_size;
      K_test = zeros(test_num,cov_size);
      for i=1:test_num,
          for j=1:cov_size,
              K_test(i,j) = exp(-norm(C1(i,:)-A1(j,:))^2/rbf_var);
          end
      end
      K_test_n = K_test - unit_test*K - K_test*unit + unit_test*K*unit;
      test_features = zeros(test_num, max_ev);
      test_features = K_test_n * evecs(:,1:max_ev);
      C2=test_features;


      model = svmtrain(B1, A2, '-s 3 -t 2 -g 0.09 -c 30 -p 0.01');
      [y, accuracy] = svmpredict(D1, C2, model);

      


  
 
 X=abs(D1-y);
 error=sqrt(sum(X.^2)/test_num)
% Y=ones(size(X,1),1)*mean(X);
 %error=sqrt(sum((X-Y).^2)/test_num)
 
 T=[1:1:20]';
 V=[1,20,-0.5,1.5];

 plot(T,D1,'r--','LineWidth',2 );
 axis(V);
 hold on
 plot(T,y,'b','linewidth',2);
 axis(V);