玫瑰椅的情感驱动设计：整合EMD-KPCA-LSTM混合架构的女性偏好预测模型

clc; Clear Close all LSTM prediction tic Load origin_data.mat Load emd_data.mat Load KPCA_data.mat disp(‘⋯⋯⋯⋯⋯⋯⋯⋯⋯⋯⋯⋯⋯⋯⋯⋯⋯⋯⋯⋯⋯⋯⋯⋯⋯⋯⋯⋯⋯⋯⋯⋯⋯⋯⋯⋯⋯⋯⋯⋯⋯⋯⋯⋯⋯⋯’) disp(‘Single LSTM prediction’) disp(‘⋯⋯⋯⋯⋯⋯⋯⋯⋯⋯⋯⋯⋯⋯⋯⋯⋯⋯⋯⋯⋯⋯⋯⋯⋯⋯⋯⋯⋯⋯⋯⋯⋯⋯⋯⋯⋯⋯⋯⋯⋯⋯⋯⋯⋯⋯’) num_samples = length(X); % number of samples kim = 5; % delay step (kim historical data as independent variable) zim = 1; % Predict across zim time points or_dim = size(X,2); % Reconstruct the dataset i = 1: num_samples - kim - zim + 1 res(i, :) = [reshape(X(i: i + kim - 1, :), 1, kim*or_dim), X(i + kim + zim - 1, :)]; End. % Training and test set division outdim = 1; % last column of output num_size = 0.7; % Proportion of training set to dataset num_train_s = round(num_size * num_samples); % number of data samples in training set f_ = size(res, 2) - outdim; % input feature dimension P_train = res(1: num_train_s, 1: f_)'; T_train = res(1: num_train_s, f_ + 1: end)'; M = size(P_train, 2); P_test = res(num_train_s + 1: end, 1: f_)'; T_test = res(num_train_s + 1: end, f_ + 1: end)'; N = size(P_test, 2); % Data normalisation [p_train, ps_input] = mapminmax(P_train, 0, 1); p_test = mapminmax(‘apply’, P_test, ps_input); [t_train, ps_output] = mapminmax(T_train, 0, 1); t_test = mapminmax(‘apply’, T_test, ps_output); % Conversion Format i = 1 : M vp_train{i, 1} = p_train(:, i); vt_train{i, 1} = t_train(:, i); End For i = 1 : N vp_test{i, 1} = p_test(:, i); vt_test{i, 1} = t_test(:, i); End. % Create LSTM network with layers = [ ... layers = [ ... sequenceInputLayer(f_) % input layer lstmLayer(100) reluLaye