# MAT之NN：实现BP神经网络的回归拟合，基于近红外光谱的汽油辛烷值含量预测结果对比

+关注继续查看

## 实现代码

plot(NIR')

title('Near infrared spectrum curve—Jason niu')

temp = randperm(size(NIR,1));

P_train = NIR(temp(1:50),:)';

T_train = octane(temp(1:50),:)';

P_test = NIR(temp(51:end),:)';

T_test = octane(temp(51:end),:)';

N = size(P_test,2);

[p_train, ps_input] = mapminmax(P_train,0,1);

p_test = mapminmax('apply',P_test,ps_input);

[t_train, ps_output] = mapminmax(T_train,0,1);

net = newff(p_train,t_train,9);

net.trainParam.epochs = 1000;

net.trainParam.goal = 1e-3;

net.trainParam.lr = 0.01;

net = train(net,p_train,t_train);

t_sim = sim(net,p_test);

T_sim = mapminmax('reverse',t_sim,ps_output);

error = abs(T_sim - T_test)./T_test;

R2 = (N * sum(T_sim .* T_test) - sum(T_sim) * sum(T_test))^2 / ((N * sum((T_sim).^2) - (sum(T_sim))^2) * (N * sum((T_test).^2) - (sum(T_test))^2));

result = [T_test' T_sim' error']

figure

plot(1:N,T_test,'b:*',1:N,T_sim,'r-o')

legend('Real value','predicted value')

xlabel('Prediction sample')

ylabel('Octane numbe')

string = {'Comparison of the prediction results of the octane number in the test set—Jason niu';['R^2=' num2str(R2)]};

title(string)

4029 0
Android官方开发文档Training系列课程中文版：连接无线设备之通过P2P搜索网络服务

800 0

5715 0

83 0
AI 开年翻车事件：训练神经网络除 bug ，结果它把整个库删了……

268 0

2902 0
+关注

1701

0

《SaaS模式云原生数据仓库应用场景实践》

《看见新力量：二》电子书