bp.rar_BP_BP模型

clc clear p=[168.9393 66.1307 1.7167 10.8 137.5832 41.5875 ;169.2184 12.9668 2.5751 27 275.2258 185.3612 ;56611.5 25738.9782 238.6 6188.1735 38070 8701 ;0.095 0.013 -0.0437 -0.0159 0.0134 0.1178 ;60 10 20 6.3 46 14.06 ];%输入数据 t=[1 1 1 1 1 1];%输出数据 [na,mina,maxa]=premnmx(p); Pr=[min(p(1,:)),max(p(1,:)); min(p(2,:)),max(p(2,:)); min(p(3,:)),max(p(3,:)); min(p(4,:)),max(p(4,:)); min(p(5,:)),max(p(5,:)); ]; net=newff(Pr,[6,1],{ 'tansig', 'purelin' },'trainlm');%网络创建 net=init(net); net.trainParam.lr = 0.05; net.trainParam.mc = 0.95; net.trainParam.epochs = 5000; net.trainParam.goal = 0.0001; net= train(net, p,t); p2n=tramnmx(p,mina,maxa); pp = sim(net,p2n);%正常输入 E=abs(t-pp) tt=abs(1-pp) M=sse(E) N=mse(E) figure(1) plot(1:6,t, '-o',1:6, pp, '-*'); title('o为真实值，*为评测值') xlabel('历届世博'); ylabel('经济影响力'); pp figure(2) plot(E)