BP_MIV.zip_MIV SVM_MIV平均值_MIV平均影响值_miv算法_平均影响值MIV

clc clear all load tz_B1F load tz_B2F load tz_B3F load tz_B4F load tz_B3L load tz_B4L load tz_C4F load tz_C2L load tz_C3L load tz_C4L load tz_X2F load tz_X3F load tz_X4F load tz_X4L load tz_X3L load tz_ceshi_B1F; load tz_ceshi_B2F load tz_ceshi_B3F load tz_ceshi_B4F load tz_ceshi_B3L load tz_ceshi_B4L load tz_ceshi_C2L load tz_ceshi_C3L load tz_ceshi_C4L load tz_ceshi_X2F load tz_ceshi_X3F load tz_ceshi_X4F load tz_ceshi_X3L load tz_ceshi_X4L load tz_ceshi_C4F load tz_ceshi_B4F load tz_ceshi_C4L load tz_ceshi_B4L load tz_ceshi_X4F load tz_ceshi_C4F load tz_ceshi_X4L tz_B1F(:,5:6)=tz_ceshi_B1F; tz_B2F(:,5:6)=tz_ceshi_B2F; tz_B3F(:,5:6)=tz_ceshi_B3F; tz_B4F(:,5:6)=tz_ceshi_B4F; tz_B3L(:,5:6)=tz_ceshi_B3L; tz_B4L(:,5:6)=tz_ceshi_B4L; tz_C4F(:,5:6)=tz_ceshi_C4F; tz_C2L(:,5:6)=tz_ceshi_C2L; tz_C3L(:,5:6)=tz_ceshi_C3L; tz_C4L(:,5:6)=tz_ceshi_C4L; tz_X2F(:,5:6)=tz_ceshi_X2F; tz_X3F(:,5:6)=tz_ceshi_X3F; tz_X4F(:,5:6)=tz_ceshi_X4F; tz_X3L(:,5:6)=tz_ceshi_X3L; tz_X4L(:,5:6)=tz_ceshi_X4L; p=cat(2,tz_B1F,tz_B2F,tz_B3F,tz_B4F,tz_B3L,tz_B4L,tz_C4F,tz_C2L,tz_C3L,tz_C4L,tz_X2F,tz_X3F,tz_X4F,tz_X3L,tz_X4L); p_max=max(p'); p_min=min(p'); % save p_max % save p_min [c l]=size(p); for i=1:c a=p(i,:); p(i,:)=(p(i,:)-p_min(1,i))/(p_max(1,i)-p_min(1,i)); end %去第一片烟叶作为输入 p=p'; [m n]=size(p); yy_temp=p; %%x1可以表示长，x2为宽...计算特征影响值，p=[x1；x2；...]作为输出，t为样本已知分级结果 %p_increase为增加10%矩阵，p_decrease为减小 for i=1:n p=yy_temp; px=p(:,i); pa=px*1.1; p(:,i)=pa; aa=['p_increase' int2str(i) '=p']; eval(aa); end for i=1:n p=yy_temp; px=p(:,i); pa=px*0.9; p(:,i)=pa; aa=['p_decrease' int2str(i) '=p']; eval(aa); end %建立训练bp网络 load net_guiyihua_maxmin_dange net=net_guiyihua_maxmin_dange; %预测sim for i=1:n eval(['p_increase',num2str(i), '=transpose(p_increase',num2str(i),')']); end for i=1:n eval(['p_decrease',num2str(i), '=transpose(p_decrease',num2str(i),')']); end %result_in为增加后的输出，result_de是减少后的输出 for i=1:n eval(['result_in',num2str(i),'=sim(net,','p_increase',num2str(i),')']); end for i=1:n eval(['result_de',num2str(i),'=sim(net,','p_decrease',num2str(i),')']); end for i=1:n eval(['result_in',num2str(i),'=transpose(result_in',num2str(i),')']); end for i=1:n eval(['result_de',num2str(i),'=transpose(result_de',num2str(i),')']); end %n个值，分别是n个特征的影响值，符号正负表示方向，绝对值大小表示影响的相对重要性 for i=1:n IV=['result_in',num2str(i),'-result_de',num2str(i)]; eval(['MIV_',num2str(i),'=mean(',IV,')']) end