基于卷积神经网络-双向门控循环单元(CNN-BIGRU)分类预测，多特征输入二分类及多分类模型(Matlab完整源码和数据）

%% 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 %% 读取数据 res = xlsread('data.xlsx'); %% 分析数据 num_class = length(unique(res(:, end))); % 类别数（Excel最后一列放类别） num_dim = size(res, 2) - 1; % 特征维度 num_res = size(res, 1); % 样本数（每一行，是一个样本） num_size = 0.7; % 训练集占数据集的比例 res = res(randperm(num_res), :); % 打乱数据集（不打乱数据时，注释该行） flag_conusion = 1; % 标志位为1，打开混淆矩阵（要求2018版本及以上） %% 设置变量存储数据 P_train = []; P_test = []; T_train = []; T_test = []; %% 划分数据集 for i = 1 : num_class mid_res = res((res(:, end) == i), :); % 循环取出不同类别的样本 mid_size = size(mid_res, 1); % 得到不同类别样本个数 mid_tiran = round(num_size * mid_size); % 得到该类别的训练样本个数 P_train = [P_train; mid_res(1: mid_tiran, 1: end - 1)]; % 训练集输入 T_train = [T_train; mid_res(1: mid_tiran, end)]; % 训练集输出 P_test = [P_test; mid_res(mid_tiran + 1: end, 1: end - 1)]; % 测试集输入 T_test = [T_test; mid_res(mid_tiran + 1: end, end)]; % 测试集输出 end %% 数据转置 P_train = P_train'; P_test = P_test'; T_train = T_train'; T_test = T_test'; %% 得到训练集和测试样本个数 M = size(P_train, 2); 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 = categorical(T_train)'; t_test = categorical(T_test )'; %% 数据平铺 % 将数据平铺成1维数据只是一种处理方式 % 也可以平铺成2维数据，以及3维数据，需要修改对应模型结构 % 但是应该始终和输入层数据结构保持一致 P_train = double(reshape(P_train, num_dim, 1, 1, M)); P_test = double(reshape(P_test , num_dim, 1, 1, N)); %% 数据格式转换 for i = 1 : M p_train{i, 1} = P_train(:, :, 1, i); end for i = 1 : N p_test{i, 1} = P_test( :, :, 1, i); end %% 建立模型 lgraph = layerGraph(); % 建立空白网络结构 tempLayers = [ sequenceInputLayer([num_dim, 1, 1], "Name", "input") % 建立输入层，输入数据结构为[num_dim, 1, 1] sequenceFoldingLayer("Name", "seqfold")]; % 建立序列折叠层 lgraph = addLayers(lgraph, tempLayers); % 将上述网络结构加入空白结构中 tempLayers = [ convolution2dLayer([3, 1], 16, "Name", "conv_1", "Padding", "same") % 建立卷积层,卷积核大小[3, 1]，16个特征图 reluLayer("Name", "relu_1") % Relu 激活层 convolution2dLayer([3, 1], 32, "Name", "conv_2", "Padding", "same") % 建立卷积层,卷积核大小[3, 1]，32个特征图 reluLayer("Name", "relu_2")]; % Relu 激活层 lgraph = addLayers(lgraph, tempLayers); % 将上述网络结构加入空白结构中 numHiddenUnits = 64; % 隐含层神经元个数 tempLayers = [ sequenceUnfoldingLayer("Name", "sequnfold") % 建立序列反折叠层 flattenLayer("Name", "flatten1") % 网络铺平层 gruLayer( numHiddenUnits, 'OutputMode', 'sequence',"Name", "bigru1")% BiGRU层 concatenationLayer(1, 2, "Name", "cat1") gruLayer( numHiddenUnits, 'OutputMode', 'last', "Name", "bigru3") concatenationLayer(1, 2, "Name", "cat2") fullyConnectedLayer(num_class, "Name", "fc") % 全连接层 softmaxLayer("Name", "softmax") % softmax激活层 classificationLayer("Name", "classification")]; % 分类层 lgraph = addLayers(lgraph, tempLayers); % 将上述网络结构加入空白结构中 lgraph = addLayers( lgraph, [ FlipLayer("flip1") flattenLayer("Name", "flatten2") % 网络铺平层 gruLayer( numHiddenUnits, 'OutputMode', 'sequence',"Name", "bigru2" ) FlipLayer("flip2")] ); lgraph = addLayers(lgraph, [ FlipLayer("flip3") gruLayer( numHiddenUnits, 'OutputMode', 'last',"Name", "bigru4" )] ); lgraph = connectLayers(lgraph, "seqfold/out", "conv_1"); % 折叠层输出 连接 卷积层输入 lgraph = connectLayers(lgraph, "seqfold/miniBatchSize", "sequnfold/miniBatchSize"); % 折叠层输出连接反折叠层输入 lgraph = connectLayers(lgraph, "relu_2", "sequnfold/in"); % 激活层输出 连接 反折叠层输入 lgraph = connectLayers(lgraph, "input", "flip1"); lgraph = connectLayers(lgraph, "flip2", "cat1/in2"); lgraph = connectLayers(lgraph, "cat1", "flip3"); lgraph = connectLayers(lgraph, "bigru4", "cat2/in2"); %% 参数设置 options = trainingOptions('adam', ... % Adam 梯度下降算法 'MaxEpochs', 500,... % 最大训练次数 1000 'InitialLearnRate', 0.001,... % 初始学习率为0.001 'L2Regularization', 0.001,... % L2正则化参数 'LearnRateSchedule', 'piecewise',... % 学习率下降 'LearnRateDropFactor', 0.1,... % 学习率下降因子 0.1 'LearnRateDropPeriod', 400,... % 经过800次训练后 学习率为 0.001*0.1 'Shuffle', 'every-epoch',... % 每次训练打乱数据集 'ValidationPatience', Inf,... % 关闭验证 'Plots', 'training-progress',... % 画出曲线 'Verbose', false); %% 训练 net = trainNetwork(p_train, t_train, lgraph, options); %% 预测 t_sim1 = predict(net, p_train); t_sim2 = predict(net, p_test ); %% 反归一化 T_sim1 = vec2ind(t_sim1'); T_sim2 = vec2ind(t_sim2'); %% 混淆矩阵 figure cm = confusionchart(T_train, T_sim1); cm.Title = 'Confusion Matrix for Train Data'; cm.ColumnSummary = 'column-normalized'; cm.RowSummary = 'row-normalized'; figure cm = confusionchart(T_test, T_sim2); cm.Title = 'Confusion Matrix for Test Data'; cm.ColumnSummary = 'column-normalized'; cm.RowSummary = 'row-normalized';