LSTM时间序列回归matlab实现（附代码+数据集）-Toy模板网

这篇具有很好参考价值的文章主要介绍了LSTM时间序列回归matlab实现（附代码+数据集）。希望对大家有所帮助。如果存在错误或未考虑完全的地方，请大家不吝赐教，您也可以点击"举报违法"按钮提交疑问。

原理部分

LSTM在1997年被提出，从发表时间上来看已经是个"老"方法了。和其他的神经网络一样，LSTM可用于分类、回归以及时间序列预测等。原理部分的介绍可参考这篇博客。本文主要涉及利用matlab实现LSTM。
lstm matlab程序,代码,matlab,lstm,回归,人工智能

代码部分

任务：以青霉素发酵过程仿真数据为例，利用LSTM建模预测质量变量。
青霉素发酵过程仿真过程简介：共有18个过程变量，其中15个可测变量，剩余3个一般作为质量变量。共生成30个批次数据，每批次运行时长为400小时，采样时间为1小时，其中25批次用于训练，5批次用于测试。
本文所用数据下载，基于matlab深度学习工具箱实现青霉素浓度的预测。

数据标准化

XTrain_mu = mean([XTrain{:}],2);
XTrain_sig = std([XTrain{:}],0,2);
XTest_mu = mean([XTest{:}],2);
XTest_sig = std([XTest{:}],0,2);
YTrain_mu = mean([YTrain{:}],2);
YTrain_sig = std([YTrain{:}],0,2);
YTest_mu = mean([YTest{:}],2);
YTest_sig = std([YTest{:}],0,2);

for i = 1:numel(XTrain)
    XTrain{i} = (XTrain{i} - XTrain_mu) ./ XTrain_sig ;
    YTrain{i}=(YTrain{i} - YTrain_mu) ./ YTrain_sig;
end

for i = 1:numel(XTest)
    XTest{i}=(XTest{i} - XTest_mu) ./ XTest_sig;
    YTest{i}=(YTest{i} - YTest_mu) ./ YTest_sig;
end

定义网络结构

numResponses = size(YTrain{1},1);
numHiddenUnits = 200;
numFeatures=15;%变量个数
layers = [ ...
    sequenceInputLayer(numFeatures)
    lstmLayer(numHiddenUnits,'OutputMode','sequence')
    fullyConnectedLayer(50)
    dropoutLayer(0.5)
    fullyConnectedLayer(numResponses)
    regressionLayer];
maxEpochs = 90;

设定超参数

options = trainingOptions('adam', ...
    'MaxEpochs',maxEpochs, ...
    'InitialLearnRate',0.01, ...
    'GradientThreshold',1, ...
    'Shuffle','never', ...
    'Plots','training-progress',...
    'Verbose',0);

模型训练

net = trainNetwork(XTrain,YTrain,layers,options);

回归预测

YPred = predict(net,XTest);

输出可视化

idx = randperm(numel(YPred),4);
figure
for i = 1:numel(idx)
    subplot(2,2,i)
    plot(YTest{idx(i)},'--')
    hold on
    plot(YPred{idx(i)},'.-')
    hold off
    title("Test Observation " + idx(i))
    xlabel("Time Step")
    ylabel("青霉素浓度")
    rmse = sqrt(mean((YPred{i} - YTest{i}).^2))
end
legend(["True" "Predicted"],'Location','southeast')

结果

训练过程：

回归预测：

lstm matlab程序,代码,matlab,lstm,回归,人工智能

整体代码

XTrain_mu = mean([XTrain{:}],2);
XTrain_sig = std([XTrain{:}],0,2);
XTest_mu = mean([XTest{:}],2);
XTest_sig = std([XTest{:}],0,2);
YTrain_mu = mean([YTrain{:}],2);
YTrain_sig = std([YTrain{:}],0,2);
YTest_mu = mean([YTest{:}],2);
YTest_sig = std([YTest{:}],0,2);

for i = 1:numel(XTrain)
    XTrain{i} = (XTrain{i} - XTrain_mu) ./ XTrain_sig ;
    YTrain{i}=(YTrain{i} - YTrain_mu) ./ YTrain_sig;
end

for i = 1:numel(XTest)
    XTest{i}=(XTest{i} - XTest_mu) ./ XTest_sig;
    YTest{i}=(YTest{i} - YTest_mu) ./ YTest_sig;
end
numResponses = size(YTrain{1},1);
numHiddenUnits = 200;
numFeatures=15;
layers = [ ...
    sequenceInputLayer(numFeatures)
    lstmLayer(numHiddenUnits,'OutputMode','sequence')
    fullyConnectedLayer(50)
    dropoutLayer(0.5)
    fullyConnectedLayer(numResponses)
    regressionLayer];
maxEpochs = 90;
options = trainingOptions('adam', ...
    'MaxEpochs',maxEpochs, ...
    'InitialLearnRate',0.01, ...
    'GradientThreshold',1, ...
    'Shuffle','never', ...
    'Plots','training-progress',...
    'Verbose',0);
net = trainNetwork(XTrain,YTrain,layers,options);
YPred = predict(net,XTest);
idx = randperm(numel(YPred),4);
figure
for i = 1:numel(idx)
    subplot(2,2,i)
    plot(YTest{idx(i)},'--')
    hold on
    plot(YPred{idx(i)},'.-')
    hold off
    title("Test Observation " + idx(i))
    xlabel("Time Step")
    ylabel("青霉素浓度")
    rmse = sqrt(mean((YPred{i} - YTest{i}).^2))
end
legend(["True" "Predicted"],'Location','southeast')