load TT.mat
numObservations = numel(XTrain);
for i=1:numObservations
    sequence = XTrain{i};
    sequenceLengths(i) = size(sequence,2);
end
[sequenceLengths,idx] = sort(sequenceLengths);
XTrain = XTrain(idx);
YTrain = YTrain(idx);
miniBatchSize = 27;
inputSize = 12;
accuracy=0.0509
numHiddenUnits = 100;
numClasses = 9;

layers = [ ...
    sequenceInputLayer(inputSize)
    bilstmLayer(numHiddenUnits,'OutputMode','last')
    fullyConnectedLayer(numClasses)
    softmaxLayer
    classificationLayer]
maxEpochs = 100;
miniBatchSize = 27;

options = trainingOptions('adam', ...
    'ExecutionEnvironment','cpu', ...
    'GradientThreshold',1, ...
    'MaxEpochs',maxEpochs, ...
    'MiniBatchSize',miniBatchSize, ...
    'SequenceLength','longest', ...
    'Shuffle','never', ...
    'Verbose',0, ...
    'Plots','training-progress');
net = trainNetwork(XTrain,YTrain,layers,options);
load Fi.mat
load data.mat
load final.mat
precision=Nw_DT(1)-accuracy
recall=Nw_DT(2)-accuracy
F1score=Nw_DT(3)-accuracy
specifity=Nw_DT(4)-accuracy
disp(['precision: ',num2str(precision),'%'])
disp(['recall: ',num2str(recall),'%'])
disp(['F1score: ',num2str(F1score),'%'])
disp(['specifity: ',num2str(specifity),'%'])
net = patternnet(10);
net = train(net,XTrain,YTrain);
YPredicted = net(XTrain);
plotconfusion(YTrain,YPredicted)