diff --git a/text/TODO.txt b/text/TODO.txt
index 808b7f1..bfbc3d1 100644
--- a/text/TODO.txt
+++ b/text/TODO.txt
@@ -120,6 +120,7 @@
 * really blinking? (p.27)
 * why is EEG better than EMG?
 * why are positions better than velocities?
+* confusion matrices
 * Topoplot interpretieren
 
 TODO
diff --git a/text/thesis/04Discussion.tex b/text/thesis/04Discussion.tex
index fd96321..3f1bfa9 100644
--- a/text/thesis/04Discussion.tex
+++ b/text/thesis/04Discussion.tex
@@ -11,7 +11,9 @@
 \section{EEG}
 \label{dis:eeg}
     Predictions from EEG to velocities and position are significantly better than those from EMG (see tables \ref{tab:pCorr},~\ref{tab:corrKin},~\ref{tab:pCorrPos} and \ref{tab:corrPos}).\\
-    This might be because %TODO: reason
+    This might be because EMG has a hard time classifying the different movements due to massive activity while moving. This can be seen in the confusion matrix (\ref{fig:cmEMG}). Many data points belonging to class 2 or 4 are classified as 3 in error. The classification between movement and rest however works fine.\\
+    All in all few samples are classified as class 2 even though the training was done on a balanced set. This %TODO really?
+    could mean that features of class 2 are found in other classes too and by that do not have strong predictive power.
 
     When predicting velocities or positions from EEG there is no significant difference between $x$ and $y$. The difference between $x$ and $y$ and the angle $\theta$ is larger for velocities than for absolute positions since the absolute angle prediction a lot better than the prediction of change.\\
     This again is an indication that the actual position is more important for the activity in brain than the change of position as itself.
@@ -21,6 +23,8 @@
     The reason for that might be that the movements were not self induced but extrinsically motivated by a cue. \citeauthor{Lew14} however use low frequencies exactly for the purpose to detect voluntary movement.\\
     We show that the use of low frequencies (at least as we did it here) has no advantage over the use of EMG (see table \ref{tab:pCorr}). This might also be a hint that movement relics were have the biggest part in low frequencies while moving. This however makes it impossible to use them for continuous tasks.\\
     Low frequencies are great to early detect voluntary movement but are not applicable in our configuration.
+
+    Which is interesting nevertheless is, that low frequencies also occur in rest. Quite some of the movements are classified as rest (see figure \ref{fig:cmEEG}). If a sample is classified correctly as movement it is quite likely that is is also classified correctly - however with an preference on class 3 again. %TODO - naja
 \section{Velocities and Positions}
 \label{dis:velPos}
     We expected better performance when predicting velocities instead of absolute positions. Our findings however show the opposite. The performance is quite a lot better when predicting positions directly.\\
diff --git a/text/thesis/05Future.tex b/text/thesis/05Future.tex
index a215025..26f3354 100644
--- a/text/thesis/05Future.tex
+++ b/text/thesis/05Future.tex
@@ -1,6 +1,10 @@
 \chapter{Future Work}
-    \section{new Data set}
-        Are the results different because of the new classification?
+    \section{Classification}
+        Our results in the topic of classification are not very reliable since we did the classification based on EMG (cf. section \ref{mm:newClass}). It would be interesting to analyze data where the stimulus is matched to the EEG signal and check for early detectability (e.g. with low frequencies as \cite{Lew14}).\\
+        Additionally classification - which is enough for some tasks - could be compared to regression. If there is only a limited set of movements a robotic prosthesis has to perform, it could use classification. This should give a lower error rate since the different movements can be distinguished better.
+    \section{Measurement of error}
+        For comparison of regression and classification it could be interesting to introduce another measure for performance than just classified correctly or not. It could be interesting how much the predicted movement differs from the real even in the classification task. In that way one would get a measure to decide whether using classification instead of regression pays off.\\
+        For this analysis also a variable number of classes would be interesting since 4 movements (as in our setting) is not enough to use an artificial arm.
     \section{Offset}
         There is no significant effect of an offset in our configuration. When using smaller EEG windows however there might be one. This could be tried in further analyses with small EEG windows.\\
         These small windows however will probably bring other problems as e.g. unstable transformation into Fourier space. So maybe it is necessary to use large windows, then an offset is unnecessary.