clc
clear
%数据处理
data=xlsread('data.xlsx');
for j=1:72
DATA_train_input(j,:)=data(:,j:j+4);
DATA_train_output(j,:)=data(j+5);
end
for j=73:92
DATA_test_input(j-72,:)=data(:,j:j+4);
DATA_test_output(j-72,:)=data(j+5);
end
save DATA_train_input DATA_train_input;
save DATA_train_output DATA_train_output;
save DATA_test_input DATA_test_input;
save DATA_test_output DATA_test_output;
%% 测试结果
%% I. 清空环境变量
clear all
clc
%% II. 训练集/测试集产生
%%
% 1. 导入数据
load DATA_train_input;
load DATA_train_output;
load DATA_test_input;
load DATA_test_output;
%%
P_train = DATA_train_input';
T_train = DATA_train_output';
% % 测试集
P_test = DATA_test_input';
T_test = DATA_test_output';
N = size(P_test,2);
%% III. 数据归一化
[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);
%% IV. BP神经网络创建、训练及仿真测试
%%
% 1. 创建网络
net = newff(p_train,t_train,20);%创建15个隐含层节点的BP网络
%%
% 2. 设置训练参数
net.trainParam.epochs = 100;
net.trainParam.goal = 1e-5;
net.trainParam.lr = 0.01;
%%
% 3. 训练网络
net = train(net,p_train,t_train);
%%
% 4. 仿真测试
t_sim = sim(net,p_test);
%%
% 5. 数据反归一化
T_sim = mapminmax('reverse',t_sim,ps_output);
%% V. 性能评价
%%
% 1. 相对误差error
error = abs(T_sim - T_test)./T_test;
%%
% 2. 决定系数R^2
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));
%%
% 3. 结果对比
result = [T_test' T_sim' error'];
%% VI. 绘图
figure
plot(1:N,T_test,'b:*',1:N,T_sim,'r-o')
legend('真实值','预测值')
xlabel('预测样本')
ylabel('测试值')
string = {'预测结果对比';['R^2=' num2str(R2)]};
title(string)
