Regression prediction | MATLAB implements MPA-BiGRU marine predator algorithm optimization of two-way gated cyclic unit multi-input single-output regression prediction (multiple indicators, multi-graph)

Regression prediction | MATLAB implements MPA-BiGRU marine predator algorithm optimization of two-way gated cyclic unit multi-input single-output regression prediction (multiple indicators, multi-graph)

List of effects

basic introduction

MPA-BiGRU Ocean Predator Algorithm Optimizes Bidirectional Gated Recurrent Unit Data Multivariate regression/time series forecasting can directly run Matlab language 1.
Multivariate single-output model can also be replaced by time series single-column input forecasting. Evaluation indicators include: R2, MAE, RMSE and MAPE, etc. There are many graphs, including iterative curve graphs and forecast effect graphs, which can fully meet your needs~ 2. The
marine predator algorithm is an optimization algorithm proposed in recent years, with strong optimization capabilities , has the characteristics of fast convergence speed, etc., few people use it, and it can also be replaced by optimization algorithms such as NGO and GOA.
3. It is normal for the optimization algorithm to optimize the deep learning model to run slowly, please wait patiently~
4. The attached test data can directly replace the data and you can use it to directly run the main one-click output graph, suitable for novices~

programming

• Complete source code and data acquisition method: private message reply PSO-SDAE particle swarm optimization stacking denoising autoencoder multi-input single-output regression prediction (multi-indicator, multi-map) .

%%  清空环境变量
warning off             % 关闭报警信息
close all               % 关闭开启的图窗
clear                   % 清空变量
clc                     % 清空命令行

%%  导入数据
res = xlsread('data.xlsx');

%%  划分训练集和测试集
temp = randperm(103);

P_train = res(temp(1: 80), 1: 7)';
T_train = res(temp(1: 80), 8)';
M = size(P_train, 2);

P_test = res(temp(81: end), 1: 7)';
T_test = res(temp(81: end), 8)';
N = size(P_test, 2);

%%  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);
t_test = mapminmax('apply', T_test, ps_output);



%%  仿真测试
t_sim1 = sim(net, p_train);
t_sim2 = sim(net, p_test);

%%  数据反归一化
T_sim1 = mapminmax('reverse', t_sim1, ps_output);
T_sim2 = mapminmax('reverse', t_sim2, ps_output);

%%  均方根误差
error1 = sqrt(sum((T_sim1 - T_train).^2) ./ M);
error2 = sqrt(sum((T_sim2 - T_test ).^2) ./ N);



%%  相关指标计算
% 决定系数 R2
R1 = 1 - norm(T_train - T_sim1)^2 / norm(T_train - mean(T_train))^2;
R2 = 1 - norm(T_test -  T_sim2)^2 / norm(T_test -  mean(T_test ))^2;

disp(['训练集数据的R2为：', num2str(R1)])
disp(['测试集数据的R2为：', num2str(R2)])

% 平均绝对误差 MAE
mae1 = sum(abs(T_sim1 - T_train)) ./ M ;
mae2 = sum(abs(T_sim2 - T_test )) ./ N ;

disp(['训练集数据的MAE为：', num2str(mae1)])
disp(['测试集数据的MAE为：', num2str(mae2)])

% 平均相对误差 MBE
mbe1 = sum(T_sim1 - T_train) ./ M ;
mbe2 = sum(T_sim2 - T_test ) ./ N ;

disp(['训练集数据的MBE为：', num2str(mbe1)])
disp(['测试集数据的MBE为：', num2str(mbe2)])

References

[1] https://blog.csdn.net/kjm13182345320/article/details/129215161
[2] https://blog.csdn.net/kjm13182345320/article/details/128105718