写一段程序用matlab的堆叠自编码器预测风电功率，且全连接层的激活函数是sigmod激活函数

下面是一个基于Matlab的堆叠自编码器预测风电功率的程序，其中使用了sigmod激活函数：

% 加载数据集
load('wind_power_data.mat');

% 数据集归一化
data = normalize(data);

% 划分训练集和测试集
train_size = 0.8;
train_num = floor(train_size * size(data, 1));
train_set = data(1:train_num, :);
test_set = data(train_num+1:end, :);

% 设置自编码器参数
input_size = size(train_set, 2);
hidden_size1 = 50;
hidden_size2 = 20;
output_size = input_size;

% 训练第一个自编码器
autoencoder1 = train_autoencoder(train_set, hidden_size1);
features1 = encode(autoencoder1, train_set);

% 训练第二个自编码器
autoencoder2 = train_autoencoder(features1, hidden_size2);
features2 = encode(autoencoder2, features1);

% 训练全连接神经网络
net = patternnet([10 5]);
net.layers{1}.transferFcn = 'logsig';
net.layers{2}.transferFcn = 'logsig';
net.trainFcn = 'trainscg';
net.trainParam.epochs = 1000;
net.trainParam.max_fail = 50;
net.divideFcn = 'divideind';
net.divideParam.trainInd = 1:size(features2, 1)*0.8;
net.divideParam.testInd = size(features2, 1)*0.8+1:size(features2, 1);
net = train(net, features2', train_set');

% 预测测试集数据并计算误差
test_features1 = encode(autoencoder1, test_set);
test_features2 = encode(autoencoder2, test_features1);
predictions = net(test_features2');
mse = mean((test_set' - predictions).^2)

其中，`train_autoencoder` 函数用于训练自编码器：

function autoencoder = train_autoencoder(data, hidden_size)
% 训练自编码器
input_size = size(data, 2);
autoencoder = trainAutoencoder(data', hidden_size, ...
    'MaxEpochs', 100, ...
    'EncoderTransferFunction', 'logsig', ...
    'DecoderTransferFunction', 'logsig', ...
    'L2WeightRegularization', 0.001, ...
    'SparsityRegularization', 4, ...
    'SparsityProportion', 0.05, ...
    'ScaleData', true, ...
    'ShowProgressWindow', false);
end