基于MATLAB 编程的自编码LSTM，基于lstm的分类预测

clc clear close all %% 加载数据 load maydata.mat rand('seed',0) [m nn]=sort(rand(1,1054)); m=900; train_data1 = num(nn(1:900),1:1:8)';%训练数据的输入数据 test_data1 = num(nn(1:900),9)';%训练数据的输出数据 [train_data,inputps]=mapminmax(train_data1,0,1);%训练数据的输入数据的归一化 trainout = zeros(9,900); for ii = 1:900 trainout(test_data1(ii),ii)=1; end % [trainout,outputps]=mapminmax(test_data1,0,1);%训练数据的输出数据的归一化 data_length=size(train_data,1); data_num=size(train_data,2); %% 网络参数初始化 % 结点数设置 input_num=8; cell_num=20; output_num=9; % 网络中门的偏置 bias_input_gate=rand(1,cell_num); bias_forget_gate=rand(1,cell_num); bias_output_gate=rand(1,cell_num); % ab=1.2; % bias_input_gate=ones(1,cell_num)/ab; % bias_forget_gate=ones(1,cell_num)/ab; % bias_output_gate=ones(1,cell_num)/ab; %网络权重初始化 ab=15; weight_input_x=rand(input_num,cell_num)/ab; weight_input_h=rand(output_num,cell_num)/ab; weight_inputgate_x=rand(input_num,cell_num)/ab; weight_inputgate_c=rand(cell_num,cell_num)/ab; weight_forgetgate_x=rand(input_num,cell_num)/ab; weight_forgetgate_c=rand(cell_num,cell_num)/ab; weight_outputgate_x=rand(input_num,cell_num)/ab; weight_outputgate_c=rand(cell_num,cell_num)/ab; %hidden_output权重 weight_preh_h=rand(cell_num,output_num); %网络状态初始化 cost_gate=1e5; h_state=rand(output_num,data_num); cell_state=rand(cell_num,data_num); %% 网络训练学习 for iter=1:5 iter yita=0.1; %每次迭代权重调整比例 for m=1:data_num %前馈部分 if(m==1) gate=tanh(train_data(:,m)'*weight_input_x); input_gate_input=train_data(:,m)'*weight_inputgate_x+bias_input_gate; output_gate_input=train_data(:,m)'*weight_outputgate_x+bias_output_gate; for n=1:cell_num input_gate(1,n)=1/(1+exp(-input_gate_input(1,n))); output_gate(1,n)=1/(1+exp(-output_gate_input(1,n))); end forget_gate=zeros(1,cell_num); forget_gate_input=zeros(1,cell_num); cell_state(:,m)=(input_gate.*gate)'; else gate=tanh(train_data(:,m)'*weight_input_x+h_state(:,m-1)'*weight_input_h); input_gate_input=train_data(:,m)'*weight_inputgate_x+cell_state(:,m-1)'*weight_inputgate_c+bias_input_gate; forget_gate_input=train_data(:,m)'*weight_forgetgate_x+cell_state(:,m-1)'*weight_forgetgate_c+bias_forget_gate; output_gate_input=train_data(:,m)'*weight_outputgate_x+cell_state(:,m-1)'*weight_outputgate_c+bias_output_gate; for n=1:cell_num input_gate(1,n)=1/(1+exp(-input_gate_input(1,n))); forget_gate(1,n)=1/(1+exp(-forget_gate_input(1,n))); output_gate(1,n)=1/(1+exp(-output_gate_input(1,n))); end cell_state(:,m)=(input_gate.*gate+cell_state(:,m-1)'.*forget_gate)'; end pre_h_state=tanh(cell_state(:,m)').*output_gate; h_state(:,m)=(pre_h_state*weight_preh_h)'; %误差计算 Error=h_state(:,m)-trainout(:,m); Error_Cost(1,iter)=sum(Error.^2); % if(Error_Cost(1,iter)<cost_gate) if iter==50 flag=1; break; else [ weight_input_x,... weight_input_h,... weight_inputgate_x,... weight_inputgate_c,... weight_forgetgate_x,... weight_forgetgate_c,... weight_outputgate_x,... weight_outputgate_c,... weight_preh_h ]=fun_weight1(m,yita,Error,... weight_input_x,... weight_input_h,... weight_inputgate_x,... weight_inputgate_c,... weight_forgetgate_x,... weight_forgetgate_c,... weight_outputgate_x,... weight_outputgate_c,... weight_preh_h,... cell_state,h_state,... input_gate,forget_gate,... output_gate,gate,... train_data,pre_h_state,... input_gate_input,... output_gate_input,... forget_gate_input); end end % if(Error_Cost(1,iter)<cost_gate) % break; % end end Error_Cost = sort(Error_Cost,'descend'); plot(Error_Cost,'k-*'); title('误差曲线图'); %% 使用后121个检验 %数据加载 test_final11=num(nn(901:1054),1:8)';%测试数据的输入数据 test_final1=mapminmax('apply',test_final11,inputps); test_output=num(nn(901:1054),9)'; %测试数据的输出数据 %前馈 m=2:155; lstmout= []; for ii = 1:154 test_final = test_final1(:,ii); gate=tanh(test_final'*weight_input_x+h_state(:,m(ii)-1)'*weight_input_h); input_gate_input=test_final'*weight_inputgate_x+cell_state(:,m(ii)-1)'*weight_inputgate_c+bias_input_gate; forget_gate_input=test_final'*weight_forgetgate_x+cell_state(:,m(ii)-1)'*weight_forgetgate_c+bias_forget_gate; output_gate_input=test_final'*weight_outputgate_x+cell_state(:,m(ii)-1)'*weight_outputgate_c+bias_output_gate; for n=1:cell_num input_gate(1,n)=1/(1+exp(-input_gate_input(1,n))); forget_gate(1,n)=1/(1+exp(-forget_gate_input(1,n))); output_gate(1,n)=1/(1+exp(-output_gate_input(1,n))); end cell_state_test=(input_gate.*gate+cell_state(:,m(ii)-1)'.*forget_gate)'; pre_h_state=tanh(cell_state_test').*output_gate; h_state_test=(pre_h_state*weight_preh_h)'; lstmout = [lstmout h_state_test]; end % test_output % lstmout % test_output1 = (mapminmax('reverse',test_output,outputps)); % lstmout1= round(mapminmax('reverse',lstmout,outputps)); [mx,lstmout1] = max(lstmout); figure (2) plot(lstmout1,'r*') hold on plot(test_output,'bo') xlabel('样本数/个') ylabel('标签类别') title('长短区期记忆神经网络') legend('预测输出','期望输出')