diff --git a/oldMcode/correlation2.m b/oldMcode/correlation2.m
new file mode 100644
index 0000000..ce92014
--- /dev/null
+++ b/oldMcode/correlation2.m
@@ -0,0 +1,9 @@
+function [R2]=correlation2(A,B)
+    if size(A)~=size(B)
+        error('dimension missmatch')
+    end
+    R2=zeros(size(A,2),1);
+    for i=1:size(A,2)
+        R2(i)=corr(A(:,i),B(:,i))^2;
+    end
+end
\ No newline at end of file
diff --git a/oldMcode/noOfSynergies.m b/oldMcode/noOfSynergies.m
index 6dea77d..e62db76 100644
--- a/oldMcode/noOfSynergies.m
+++ b/oldMcode/noOfSynergies.m
@@ -1,42 +1,42 @@
-maxSize=6;
+maxSize=min(10,size(trainingData,2));
 
-mseAutoenc=zeros([maxSize,1]);
+r2Autoenc=zeros([maxSize,size(trainingData,2)]);
 for i=1:maxSize
     ae=trainAutoencoder(trainingData,i,'ShowProgressWindow',false);
     predicted=predict(ae,trainingData);
-    mseAutoenc(i)=mse(trainingData-predicted);
+    r2Autoenc(i,:)=correlation2(trainingData,predicted);
 end
 
 fig=figure();
 subplot(1,3,1);
-plot(mseAutoenc)
+plot(r2Autoenc)
 title('Autoencoder')
 xlabel('number of syergies')
-ylabel('mse')
+ylabel('R^2')
 
 %PCA
 [COEFF,SCORE,latent] = pca(trainingData,'Centered',false);
-msePCA=zeros([maxSize,1]);
+r2PCA=zeros([maxSize,size(trainingData,2)]);
 for i=1:maxSize
     predicted=SCORE(:,1:i)*COEFF(:,1:i)';
-    msePCA(i)=mse(trainingData-predicted);
+    r2PCA(i,:)=correlation2(trainingData,predicted);   
 end
 subplot(1,3,2);
-plot(msePCA)
+plot(r2PCA)
 title('PCA')
 xlabel('number of syergies')
-ylabel('mse')
+ylabel('R^2')
 
 %NNMF
-mseNNMF=zeros([maxSize,1]);
+r2NNMF=zeros([maxSize,size(trainingData,2)]);
 for i=1:maxSize
     [W,H]=nnmf(trainingData,i);
     predicted=W*H;
-    mseNNMF(i)=mse(trainingData-predicted);
+    r2NNMF(i,:)=correlation2(trainingData,predicted);
 end
 
 subplot(1,3,3);
-plot(mseNNMF)
+plot(r2NNMF)
 title('NNMF')
 xlabel('number of syergies')
-ylabel('mse')
\ No newline at end of file
+ylabel('R^2')
\ No newline at end of file
diff --git a/usedMcode/generateTrainingData.m b/usedMcode/generateTrainingData.m
index 35533f0..e675727 100644
--- a/usedMcode/generateTrainingData.m
+++ b/usedMcode/generateTrainingData.m
@@ -4,7 +4,7 @@
     signalWindowEEG=bci_sf*windowEEG;
     tempEEG=zeros([32,fix(floor(size(signal,1)/signalWindowEEG-1)*windowEEG/shift+1),maxEEGFreq-minEEGFreq+1]);
     tempEEGlf=zeros([32,fix(floor(size(signal,1)/signalWindowEEG-1)*windowEEG/shift+1),noLFsamples]);
-    tempEMG=zeros(fix([size(signal,2)-3-32,fix(size(signal,1)/signalWindowEMG-1)*windowEMG/shift+1]));
+    tempEMG=zeros(fix([6,fix(size(signal,1)/signalWindowEMG-1)*windowEMG/shift+1]));
     
     %Filter around 50Hz and below 2 Hz
     [A,B]= butter(2,[48 52]/(bci_sf/2),'stop');
@@ -22,8 +22,11 @@
     trainingDataEEG=permute(tempEEG,[2 1 3]);
     trainingDataEEGlf=permute(tempEEGlf,[2 1 3]);
     
-    parfor i=33:size(signal,2)-3
-        tempEMG(i-32,:)=waveformLength(filtfilt(double(E),double(F),filtfilt(double(C),double(D),filtfilt(double(A),double(B),double(signal(:,i))))),bci_sf,windowEMG,shift);
+    usedChannels={'AbdPolLo','Biceps','Triceps','FrontDelt','MidDelt','BackDelt'};
+    emgchannels=find(ismember(params.ChannelNames.Value,usedChannels));
+    
+    parfor i=1:6;
+        tempEMG(i,:)=waveformLength(filtfilt(double(E),double(F),filtfilt(double(C),double(D),filtfilt(double(A),double(B),double(signal(:,emgchannels(i)))))),bci_sf,windowEMG,shift);
     end
     trainingDataEMG=permute(tempEMG,[2 1 3]);