file=xlsread('Myvector.xlsx');
data=cell(size(file,2),1);
id=find(~isnan(data{2}));
numObservations = numel (id);
idxTraining=ceil(85/100*numObservations);
idxTesting=floor(15/100*numObservations);
idxTrain=id(1:idxTraining);
idxTest=id(idxTraining+1:end);
dataTrain = Ec(idxTrain);
XTrainn = (XTrain - muX) ./ sigmaX;
TTrainn = (TTrain - muT) ./ sigmaT;
numChannels = size(data{1},1);
sequenceInputLayer(numChannels)
fullyConnectedLayer(numChannels)
options = trainingOptions('adam', ...
'ExecutionEnvironment','cpu', ...
'MaxEpochs',maxEpochs, ...
'MiniBatchSize',miniBatchSize, ...
'GradientThreshold',1, ...
'Plots','training-progress');
net = trainNetwork(XTrainn,TTrainn,layers,options);
XTest = (X - muX) ./ sigmaX
TTest = (X - muT) ./ sigmaT;
YTest = predict(net,XTest)
rmse(i) = sqrt(mean((YTest(i) - TTest(i)).^2));
numTimeSteps = size(Ec,2);
numPredictionTimeSteps = numTimeSteps;
Y = zeros(numChannels,numPredictionTimeSteps);
for t = 1:numPredictionTimeSteps
[net,Y(:,t)] = predictAndUpdateState(net,Xt);