移动app与网站建设的区别互联网整合营销推广
多维时序 | MATLAB实现CNN-BiLSTM-Attention多变量时间序列预测
目录
- 多维时序 | MATLAB实现CNN-BiLSTM-Attention多变量时间序列预测
- 预测效果
- 基本介绍
- 模型描述
- 程序设计
- 参考资料
预测效果
基本介绍
MATLAB实现CNN-BiLSTM-Attention多变量时间序列预测，CNN-BiLSTM-Attention结合注意力机制多变量时间序列预测。
模型描述
Matlab实现CNN-BiLSTM-Attention多变量时间序列预测
1.data为数据集，格式为excel，4个输入特征，1个输出特征，考虑历史特征的影响，多变量时间序列预测；
2.CNN_BiLSTM_AttentionNTS.m为主程序文件，运行即可；
3.命令窗口输出R2、MAE、MAPE、MSE和MBE，可在下载区获取数据和程序内容；
注意程序和数据放在一个文件夹，运行环境为Matlab2020b及以上。
注意程序和数据放在一个文件夹，运行环境为Matlab2020b及以上。
4.注意力机制模块：
SEBlock（Squeeze-and-Excitation Block）是一种聚焦于通道维度而提出一种新的结构单元，为模型添加了通道注意力机制，该机制通过添加各个特征通道的重要程度的权重，针对不同的任务增强或者抑制对应的通道，以此来提取有用的特征。该模块的内部操作流程如图，总体分为三步：首先是Squeeze 压缩操作，对空间维度的特征进行压缩，保持特征通道数量不变。融合全局信息即全局池化，并将每个二维特征通道转换为实数。实数计算公式如公式所示。该实数由k个通道得到的特征之和除以空间维度的值而得，空间维数为H*W。其次是Excitation激励操作，它由两层全连接层和Sigmoid函数组成。如公式所示，s为激励操作的输出，σ为激活函数sigmoid，W2和W1分别是两个完全连接层的相应参数，δ是激活函数ReLU，对特征先降维再升维。最后是Reweight操作，对之前的输入特征进行逐通道加权，完成原始特征在各通道上的重新分配。
程序设计
- 完整程序和数据获取方式1：同等价值程序兑换；
- 完整程序和数据获取方式2：私信博主获取。
layers = [% input matrix of spectrogram valuessequenceInputLayer(inputSize,"Name","sequence")sequenceFoldingLayer("Name","fold");% convolutional layersconvolution2dLayer([5 5],10,"Name","conv1","Stride",[2 1])reluLayer("Name","relu1")maxPooling2dLayer([5 5],"Name","maxpool1","Padding","same","Stride",[2 1])convolution2dLayer([5 5],10,"Name","conv2","Stride",[2 1])reluLayer("Name","relu2")maxPooling2dLayer([5 5],"Name","maxpool2","Padding","same","Stride",[2 1])convolution2dLayer([3 3],1,"Name","conv3","Padding",[1 1 1 1])reluLayer("Name","relu3")maxPooling2dLayer([2 2],"Name","maxpool3","Padding","same","Stride",[2 1]);% unfold and feed into LSTMsequenceUnfoldingLayer("Name","unfold")flattenLayer("Name","flatten")bilstmLayer(numHiddenUnits1,"Name","bilstm","OutputMode","last")dropoutLayer(0.4,"Name","dropout")fullyConnectedLayer(numClasses,"Name","fc")softmaxLayer("Name","softmax")classificationLayer("Name","classoutput");];
lgraph = layerGraph(layers);
lgraph = connectLayers(lgraph,'fold/miniBatchSize','unfold/miniBatchSize');
% Training
maxEpochs = 200;
learningRate = 0.001;
miniBatchSize = 15; % is this needed?
options = trainingOptions('sgdm', ...'ExecutionEnvironment', 'gpu', ...'GradientThreshold', 1, ... 'MaxEpochs' ,maxEpochs, ...'miniBatchSize',miniBatchSize,...'SequenceLength', 'longest', ...'Verbose', 0, ...'ValidationData', {xVal, yVal}, ...'ValidationFrequency', 30, ...'InitialLearnRate', learningRate, ...'Plots', 'training-progress',...'Shuffle', 'every-epoch');
net = trainNetwork(xTrain, yTrain, lgraph, options);
layers = [ sequenceInputLayer(12,'Normalization','none', 'MinLength', 9);convolution1dLayer(3, 16)batchNormalizationLayer()reluLayer()maxPooling1dLayer(2)convolution1dLayer(5, 32)batchNormalizationLayer()reluLayer() averagePooling1dLayer(2)lstmLayer(100, 'OutputMode', 'last')fullyConnectedLayer(9)softmaxLayer()classificationLayer()];
options = trainingOptions('adam', ...'MaxEpochs',10, ...'MiniBatchSize',27, ...'SequenceLength','longest');
% Train network
net = trainNetwork(XTrain,YTrain,layers,options);
————————————————
版权声明：本文为CSDN博主「机器学习之心」的原创文章，遵循CC 4.0 BY-SA版权协议，转载请附上原文出处链接及本声明。
参考资料
[1] http://t.csdn.cn/pCWSp
[2] https://download.csdn.net/download/kjm13182345320/87568090?spm=1001.2014.3001.5501
[3] https://blog.csdn.net/kjm13182345320/article/details/129433463?spm=1001.2014.3001.5501