【BILSTM分类】双向长短期记忆神经网络BILSTM-Adaboost分类预测【含Matlab源码 3973期】.zip

%% 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 tic % restoredefaultpath %% 读取数据 res = xlsread('数据集.xlsx'); %% 划分训练集和测试集% P_train = res(1: 250, 1: 12)'; T_train = res(1: 250, 13)'; M = size(P_train, 2); P_test = res(251: end, 1: 12)'; T_test = res(251: end, 13)'; N = size(P_test, 2); num_dim = size(P_train, 1); % 特征维度 num_class = length(unique(res(:, end))); % 类别数（Excel最后一列放类别） % 类别数（Excel最后一列放类别） %% 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 )'; %% 格式转换 for i = 1 : M p_train{i, 1} = P_train(:, i); end for i = 1 : N p_test{i, 1} = P_test(:, i); end %% 优化算法参数设置 pop = 6; % 数量 Max_iter = 8; % 最大迭代次数 dim = 3; % 优化参数个数 lb = [1e-3, 10, 1e-4]; % 参数取值下界(学习率，隐藏层节点，正则化系数) ub = [1e-2, 30, 1e-1]; % 参数取值上界(学习率，隐藏层节点，正则化系数) load('data.mat'); %% 记录最佳参数 best_lr = Best_pos(1, 1); best_hd = ceil(Best_pos(1, 2)); best_l2 = Best_pos(1, 3); %% 权重初始化 D = ones(1, M) / M; %% 参数设置 K = 7; % 弱回归器个数 H = 6; % 隐藏层节点个数 %% 建立模型 % ---------------------- 修改模型结构时需对应修改fical.m中的模型结构 -------------------------- layers = [ sequenceInputLayer(num_dim) % 输入层 bilstmLayer(best_hd, 'OutputMode', 'last') % BILSTM层 reluLayer % Relu激活层 fullyConnectedLayer(num_class) % 全连接层 softmaxLayer % 损失函数层 classificationLayer]; % 分类层 %% 参数设置 % ---------------------- 修改模型参数时需对应修改fical.m中的模型参数 -------------------------- options = trainingOptions('adam', ... % Adam 梯度下降算法 'MaxEpochs', 200, ... % 最大训练次数 500 'InitialLearnRate', best_lr, ... % 初始学习率 best_lr 'LearnRateSchedule', 'piecewise', ... % 学习率下降 'LearnRateDropFactor', 0.5, ... % 学习率下降因子 0.1 'LearnRateDropPeriod', 150, ... % 经过 400 次训练后 学习率为 best_lr * 0.5 'Shuffle', 'every-epoch', ... % 每次训练打乱数据集 'ValidationPatience', Inf, ... % 关闭验证 'L2Regularization', best_l2, ... % 正则化参数 'Verbose', false); %% 弱回归器回归 for i = 1 : K %% 打开最后一次的损失曲线 if K == i options.Plots = 'training-progress'; end %% 训练模型 net = trainNetwork(p_train, t_train, layers, options); %% 仿真预测 t_sim1{i} = predict(net, p_train); t_sim2{i} = predict(net, p_test ); %% 数据格式转换 ztrain = double(ind2vec(double(t_train)')); t_sim1{i} = double(t_sim1{i})'; t_sim2{i} = double(t_sim2{i})'; %% 预测误差 Error(i, :) = sum(abs(t_sim1{i} - ztrain)) / num_class; %% 调整D值 weight(i) = 0; for j = 1 : M if abs(Error(i, j)) > 0.1 weight(i) = weight(i) + D(i, j); D(i + 1, j) = D(i, j) * 1.1; else D(i + 1, j) = D(i, j); end end %% 弱分类器i权重 weight(i) = 0.5 / exp(abs(weight(i))); %% D值归一化 D(i + 1, :) = D(i + 1, :) / sum(D(i + 1, :)); end %% 强预测器预测 weight = weight / sum(weight); %% 强分类器分类结果 T_sim1 = zeros(num_class, M); T_sim2 = zeros(num_class, N); for i = 1 : K output1 = (weight(i) * t_sim1{i}); output2 = (weight(i) * t_sim2{i}); T_sim1 = output1 + T_sim1; T_sim2 = output2 + T_sim2; end %% 数据反归一化 T_sim1 = vec2ind(T_sim1); T_sim2 = vec2ind(T_sim2); %% 性能评价 error1 = sum((T_sim1 == T_train)) / M * 100 ; error2 = sum((T_sim2 == T_test )) / N * 100 ; %% 数据排序 [T_train, index_1] = sort(T_train); [T_test , index_2] = sort(T_test ); T_sim1 = T_sim1(index_1); T_sim2 = T_sim2(index_2); %% 绘图 figure plot(1: M, T_train, 'r-*', 1: M, T_sim1, 'b-o', 'LineWidth', 1) legend('真实值', 'BiLSTM-adaboost预测值') xlabel('预测样本') ylabel('预测结果') string = {'训练集预测结果对比'; ['准确率=' num2str(error1) '%']}; title(string) xlim([1, M]) grid figure plot(1: N, T_test, 'r-*', 1: N, T_sim2, 'b-o', 'LineWidth', 1) legend('真实值', 'BiLSTMadaboost预测值') xlabel('预测样本') ylabel('预测结果') string = {'测试集预测结果对比'; ['准确率=' num2str(error2) '%']}; title(string) xlim([1, N]) grid %% 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';