diff --git a/classifyAccordingToEMG.m b/classifyAccordingToEMG.m
index 79cdd2e..3acc515 100644
--- a/classifyAccordingToEMG.m
+++ b/classifyAccordingToEMG.m
@@ -1,15 +1,25 @@
 function [classification]=classifyAccordingToEMG(trainingDataEEG, trainingDataEMG, classes,shift,frequency,threshold)
+% classifyAccordingToEMG data classified as -1 should be taken out
     classification=zeros([size(trainingDataEEG,1),1]);
     oldclass=0;
     for i=1:size(trainingDataEEG,1)
         if mean(trainingDataEMG(i,:)) > threshold % is movement
             class=mode(classes(max(round(shift*frequency*i-frequency),1):min(round(i*shift*frequency-1),end)));
             if class <= 5 % task is to move
-                classification(i)=class;
-                oldclass=class;
+                if oldclass==0
+                    for j=max(fix(i-1/shift),1):fix(i-0.5/shift) % Pause before beginning of movement
+                        classification(j)=-1; %code for pause
+                    end
+                    for j=max(fix(i-0.5/shift),1):i % half a second before executed movement there should be activity (esp. EEG)
+                        classification(j)=class;
+                    end
+                    oldclass=class;
+                end
             else % task is to rest but movement not finished
                 classification(i)=oldclass;
             end
+        else
+            oldclass=0;
         end
     end
 end
\ No newline at end of file
diff --git a/kfoldCV.m b/kfoldCV.m
index 8a4587a..2aebb22 100644
--- a/kfoldCV.m
+++ b/kfoldCV.m
@@ -1,4 +1,4 @@
-function [model] = kfoldCV(classification,trainingData,k,cExpMax)
+function [model,maxC] = kfoldCV(classification,trainingData,k,cExpMax)
     noClasses=size(unique(classification),1);
     cvAccurancy=zeros(2*cExpMax+1,1);
     parfor cExp=1:2*cExpMax+1
diff --git a/read.m b/read.m
index 4f291bc..0d915ec 100644
--- a/read.m
+++ b/read.m
@@ -1,9 +1,11 @@
 %params
+disp('start')
+disp(datestr(datetime('now')))
 NFFT=2048;
 window=0.2;
 shift=0.2;
 k=10;
-maxExpC=7;
+maxExpC=5;
 maxFile=5;
 threshold=7500;
 
@@ -18,13 +20,30 @@
     fprintf('%ith file processed\n',i)
 end
 
+clear sig
+
 trainingDataEEG=cell2mat(trainingDataEEGcell);
 trainingDataEMG=cell2mat(trainingDataEMGcell);
-classes=cell2mat(classesCell);
+classesMat=cell2mat(classesCell);
+clear trainingDataEEGcell trainingDataEMGcell classesCell
 
-classification=classifyAccordingToEMG(trainingDataEEG, trainingDataEMG,classes,shift,params.SamplingRate.NumericValue,threshold);
+classificationWithPause=classifyAccordingToEMG(trainingDataEEG, trainingDataEMG,classesMat,shift,params.SamplingRate.NumericValue,threshold);
+clear classesMat
 
-smoothClassification=zeros(size(classification));
-for i=1:size(classification,1)
-    smoothClassification(i)=round(mean(classification(max(i-round(1/window),1):min(i+round(1/window),end))));        
-end
\ No newline at end of file
+smoothClassification=zeros(size(classificationWithPause));
+for i=1:size(classificationWithPause,1)
+    smoothClassification(i)=round(mean(classificationWithPause(max(i-round(1/window),1):min(i+round(1/window),end))));       
+end
+
+clear classificationWithPause
+
+trainingDataEEG=trainingDataEEG(smoothClassification~=-1,:,:);
+trainingDataEMG=trainingDataEMG(smoothClassification~=-1,:);
+classification=smoothClassification(smoothClassification~=-1);
+
+clear smoothClassification i
+save /home/jph/Uni/masterarbeit/data/AO1200msWindow50msShift.mat
+
+
+disp('end')
+disp(datestr(datetime('now')))
\ No newline at end of file
diff --git a/svm.m b/svm.m
index f298ba0..27c3fe8 100644
--- a/svm.m
+++ b/svm.m
@@ -14,11 +14,12 @@
 maxExpC=5; % c\in {2^i|i=-maxExpC:1:maxExpC}
 
 %choose to estimate based on EEG or EMG
-trainingData=trainingDataEMG;
+trainingData=trainingDataEEG;
 clear trainingDataEEG;
 clear trainingDataEMG;
 
 accurancy=zeros(k,3);
+maxC=zeros(k,1);
 noClasses=size(unique(classification),1);
 cm=zeros(noClasses);
 randMap=randperm(size(trainingData,1));
@@ -30,12 +31,11 @@
     remainingClasses=classification(mod(randMap,k)~=i-1);
     disp(datestr(datetime('now')))
     fprintf('create %ith model\n',i)
-    model=kfoldCV(remainingClasses,remaining,k,maxExpC);
-
+    [model,maxC(i)]=kfoldCV(remainingClasses,remaining,k,maxExpC);
     disp(datestr(datetime('now')))
+    
     [predictions,accurancy(i,:),pvalues]=svmpredict(leaveClasses,leaveOut(:,:),model);
     cm=cm+confusionmat(leaveClasses,predictions); %confusion matrix
     %cf: for each cue what was the prediction (maybe colourCoded)
-    %fprintf('%ith step done\n',i)
 end
 meanAccurancy=mean(accurancy(:,1))
\ No newline at end of file
diff --git a/text/collection.txt b/text/collection.txt
index 7025eb6..91d18a7 100644
--- a/text/collection.txt
+++ b/text/collection.txt
@@ -10,5 +10,5 @@
 new Classification
 ------------------
 Move/Rest EMG : 99.9535%
-Bewegungen EMG: 74.4832% *k=2, c=1*
+Bewegungen EMG: 77.7352%