diff --git a/text/thesis/03Results.tex b/text/thesis/03Results.tex index 4aef5f4..577776e 100644 --- a/text/thesis/03Results.tex +++ b/text/thesis/03Results.tex @@ -2,8 +2,8 @@ \label{chp:results} \section{Number of Synergies} \label{res:noSyn} - To determine the number of synergies to use we predicted all EMG data with each technique and each number of synergies. The result is the plot in figure~\ref{fig:noSyn}.\\ - The plot tells that 2 and 4 synergies are good values for Autoencoders, for default nevertheless we use 3 synergies since we also use 3 dimensions of kinematics and so it is more comparable. Three is also the most efficient number of Synergies for PCA and NNMF (cf. Section \ref{dis:noSyn}).\\ + To determine the number of synergies to use I predicted all EMG data with each technique and each number of synergies. The result is the plot in figure~\ref{fig:noSyn}.\\ + The plot tells that 2 and 4 synergies are good values for Autoencoders, for default nevertheless 3 synergies are used here because there are also 3 dimensions of kinematics and so it is more comparable. Three is also the most efficient number of Synergies for PCA and NNMF (cf. Section \ref{dis:noSyn}).\\ \begin{figure} \centering \includegraphics[width=\textwidth,height=\textheight]{pictures/results/noSyn.png} @@ -64,7 +64,7 @@ \end{figure} \subsection{Trade-off parameter} \label{res:maxC} - With a cross validation we compare the results for the soft-margin parameter for $\lambda=0.1,1,10$. The results are shown in figure~\ref{fig:svmCV}.\\ + With a cross validation the results for the soft-margin parameter are compared for $\lambda=0.1,1,10$. The results are shown in figure~\ref{fig:svmCV}.\\ \begin{figure} \caption{results of crossvalidation of the Support Vector Machine} @@ -200,7 +200,7 @@ \subsubsection{Pause} Whether there is a pause of 1s or only 0.5s doesn't make a significant difference for Autoencoder ($p\approx0.13$), PCA ($p\approx0.29$), NMF ($p\approx0.15$) or Velocities ($p\approx0.95$). \subsubsection{EMG} - We also predict EMG from EEG. The results are shown in figure \ref{fig:EEGemg}. There are no significant differences between the channels ($p\approx0.29$). + For comparison also EMG was predicted from EEG. The results are shown in figure \ref{fig:EEGemg}. There are no significant differences between the channels ($p\approx0.29$). \begin{figure} \centering \includegraphics[width=\textwidth]{pictures/results/EEGemg.png} @@ -262,7 +262,7 @@ \subsection{Cross-validation of Ridge Parameter}%TODO In tables \ref{tab:ridgeParamEMGkin}, \ref{tab:ridgeParamHighKin} and \ref{tab:ridgeParamAO6Kin} we find the number of 'wins' for each parameter\footnote{\ref{tab:ridgeParamHighKin} and \ref{tab:ridgeParamAO6Kin} were calculated with a order for Burg's method of 50 instead of the later default of 250}. A 'win' refers to a run where this $\lambda$ scored the highest correlation.\\ For EMG there is no clear preference but it seems like 100 should work as parameter. For EEG we see a clear preference for $\lambda=100$. Low Frequencies seem to prefer a lower parameter about 10 however this was only evaluated for one session. %TODO, if better results - For all other runs we used $\lambda = 100$ for all methods, better results might be possible with a parameter adapted better. + For all other runs $\lambda = 100$ is used for all methods, better results might be possible with a parameter adapted better. \begin{table} \centering \begin{math} diff --git a/text/thesis/04Discussion.tex b/text/thesis/04Discussion.tex index 1fff8ea..2e1d4a1 100644 --- a/text/thesis/04Discussion.tex +++ b/text/thesis/04Discussion.tex @@ -8,42 +8,42 @@ A correlation about $0.2$ cannot be used for a BCI. There might be some way of improving the predictions and it might be done several times to higher the correlations, finding another approach however is more promising.\\ Additionally in many cases a BCI is needed there are no EMG signals since the muscles do not work as they should (e.g. after stroke) and so do not generate the corresponding activity. - Out of these reasons we only use EMG as benchmark for other approaches: If the muscles would work this correlation could be reached. + Out of these reasons I only use EMG as benchmark for other approaches: If the muscles would work this correlation could be reached. \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 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 could mean that features of class 2 are found in other classes too and by that do not have strong predictive power. - The classification results we found for EEG are similar to them of \cite{Shiman15}. They found a classification accuracy of 39.5\%, we have a mean classification of 40.4\% and for targets only (no rest) even 43.6\%. However our findings for discrimination of movement and rest in EEG are a lot worse ($64.6\%$ vs. $38.5\%$). This is probably due to the training of our SVM since when only discriminating between movement and rest we also score $57.1\%$. Higher frequencies with more muscle artifacts (cf. \ref{res:topo} and \ref{dis:topo}) are more predictive for the difference between movement or rest however less predictive for the different classes. So the SVM when trained to distinguish the classes gives higher predictive power to the lower frequencies. + The classification results I found for EEG are similar to them of \cite{Shiman15}. They found a classification accuracy of 39.5\%, I have a mean classification of 40.4\% and for targets only (no rest) even 43.6\%. However my findings for discrimination of movement and rest in EEG are a lot worse ($64.6\%$ vs. $38.5\%$). This is probably due to the training of the SVM since when only discriminating between movement and rest my setup also scores $57.1\%$. Higher frequencies with more muscle artifacts (cf. \ref{res:topo} and \ref{dis:topo}) are more predictive for the difference between movement or rest however less predictive for the different classes. So the SVM when trained to distinguish the classes gives higher predictive power to the lower frequencies. 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 is 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. \section{Low Frequencies} \label{dis:lf} - Our findings concerning low frequencies are a lot less promising than e.g. in \cite{Lew14}.\\ + My findings concerning low frequencies are a lot less promising than e.g. in \cite{Lew14}.\\ 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 artifacts 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. + I show that the use of low frequencies (at least as I did it here) has no advantage over the use of EMG (see table \ref{tab:pCorr}). This might also be a hint that movement artifacts 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 this 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:cmFull}). 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. This matches the understanding of low frequencies as pre-movement activation mainly belonging to voluntary movement. The subjects probably plan all the possible movements while in rest to execute once the stimulus is shown. \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.\\ + I expected better performance when predicting velocities instead of absolute positions. The findings however show the opposite. The performance is quite a lot better when predicting positions directly.\\ This might mean that both EMG and EEG data carry more information about the actual configuration and not only about the change. - Our findings do not match them of \cite{Ofner12} who found similar results for position and movement. However the task used by \citeauthor{Ofner12} was different from ours as they used self-motivated movement. + My findings do not match them of \cite{Ofner12} who found similar results for position and movement. However the task used by \citeauthor{Ofner12} was different from ours as they used self-motivated movement. \section{Pause} \label{dis:pause} The use of a 1 second pause before movement onset only shows significant differences for classification of EMG and predicting Synergies from low frequencies. \subsection{Classification from EMG} - When doing classification from EMG data there is an great improvement when leaving the whole second before movement onset out. This results from the way we did the classification. Since we decided the beginning of movement based on the EMG data.\\ + When doing classification from EMG data there is an great improvement when leaving the whole second before movement onset out. This results from the way the classification was done, since the beginning of movement is defined based on the EMG data.\\ What this finding shows is that the threshold is chosen well to classify the movements. \subsection{Synergies from Low Frequencies} - There is a significant improvement for predicting Synergies from low frequency data. This shows again what \cite{Lew14} proposed; in low frequency features we find mainly pre-movement activation. Activity while moving is probably mostly occluded by motor commands. + There is a significant improvement when taking pre-movement data in for predicting Synergies from low frequency data. This shows again what \cite{Lew14} proposed; in low frequency features we find mainly pre-movement activation. Activity while moving is probably mostly occluded by motor commands. \section{Offset} \label{dis:offset} - Applying an offset when using EEG-data or not does not make a significant difference. This is probably due to our configuration with EEG windows as large as 1 second. If smaller windows were used an offset could help, in our setup we find no difference. + Applying an offset when using EEG-data or not does not make a significant difference. This is probably due to the configuration with EEG windows as large as 1 second. If smaller windows were used an offset could help, in my setup there is no difference. \section{Synergies} \label{dis:synergies} \subsection{Number of Synergies} @@ -52,14 +52,14 @@ For PCA and NNMF this value is reached at 3 as figure \ref{fig:noSyn} shows. The findings in the evaluation of the performance of different numbers of synergies show that 2 synergies are quite few but nevertheless have some predictive power. 4 synergies are no great improvement compared to 3 synergies.\\ - This means doing our analyses with 3 synergies should give a representative picture of the performance of synergies. + This means doing the analyses with 3 synergies should give a representative picture of the performance of synergies. \subsection{Autoencoder, PCA or NMF} In many applications the synergies computed with different methods perform similar, however some differences can be found. \subsubsection{Prediction from EEG} PCA data is predicted from EEG significantly worse than e.g. autoencoder data ($p<0.001$). Between NMF and autoencoder there is no significant difference.\\ - We conclude autoencoder and NMF are to prefer when looking for good predictability from EEG. + So autoencoder and NMF are to prefer when looking for good predictability from EEG. \subsubsection{Number of Synergies} - With our data we can not show a better performance of an autoencoder with only 2 synergies. Similar to the other methods of synergy calculation there is a significant decrease in predictive performance.\\ + With my data I can not show a better performance of an autoencoder with only 2 synergies. Similar to the other methods of synergy calculation there is a significant decrease in predictive performance.\\ Also the absolute prediction is not significantly better or worse than the prediction via other synergies. \subsection{Prediction via Synergies} Of course the prediction via Synergies is a bit worse than direct prediction, since the machine learning techniques could do the same dimensionality reduction and also much more.\\ @@ -75,10 +75,10 @@ In the beta channel (see figure \ref{fig:topoBeta}) we see high activity in the right hemisphere. This is probably an artifact of muscle movements since the commands to drive the right arm should be produced in the left hemisphere.\\ However - as we see in prediction from EMG - the muscle activity is not very predictive for the direction of movement. EEG is even better than EMG meaning there has to be more information the decision is based on than movement artifacts.\\ This information for example can be found in the alpha band (see figure \ref{fig:topoAlpha}). Here we see clear activation in the left hemisphere and no impact of movement artifacts since the right hemisphere shows no prominent differences in activation.\\ - What is interesting in the alpha band is that main activation is measured in the occipital lobe usually associated with visual processing. Since the cue was presented auditory our findings support the idea of the dorsal pathway. This pathway is often called \qq{Where Path} or sometimes \qq{How Path} of visual processing opposing to the ventral \qq{What Path} (cf. \cite{Ungerleider82}). The dorsal pathway is said to be involved in reaching tasks. This is supported by our findings. + What is interesting in the alpha band is that main activation is measured in the occipital lobe usually associated with visual processing. Since the cue was presented auditory the findings support the idea of the dorsal pathway. This pathway is often called \qq{Where Path} or sometimes \qq{How Path} of visual processing opposing to the ventral \qq{What Path} (cf. \cite{Ungerleider82}). The dorsal pathway is said to be involved in reaching tasks. This is supported by the findings. - When comparing reaches to different targets we also find differences in other brain regions. For example when comparing classes 2 and 4 we find differences differences in anterior regions of the parietal lobe (see figure \ref{fig:topoAlpha24}). Positive values stand for higher activation in class 2.\\ - Here we find the difference in activation in the expected area: the premotoric regions. When predicting movements a focus should be laid on this region, here different movements can be discriminated. The main difference between movement and rest are found in the occipital lobe, for a BCI also this region should be monitored. + When comparing reaches to different targets there are also differences in other brain regions. For example when comparing classes 2 and 4 we find differences differences in anterior regions of the parietal lobe (see figure \ref{fig:topoAlpha24}). Positive values stand for higher activation in class 2.\\ + Here the difference in activation is found in the expected area: the premotoric regions. When predicting movements a focus should be laid on this region, here different movements can be discriminated. The main difference between movement and rest are found in the occipital lobe, for a BCI also this region should be monitored. \begin{figure} \centering \includegraphics[width=0.9\textwidth]{pictures/results/topoAlpha24.png} diff --git a/text/thesis/05Future.tex b/text/thesis/05Future.tex index 0f71171..c09a712 100644 --- a/text/thesis/05Future.tex +++ b/text/thesis/05Future.tex @@ -1,27 +1,27 @@ \section{Future Work} \label{chp:fut} \subsection{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}).\\ + My results in the topic of classification are not very reliable since I 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. \subsection{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 having 4 movements (as in our setting) is not enough to use an artificial arm. + For this analysis also a variable number of classes would be interesting since having 4 movements (as in this setting) is not enough to use an artificial arm. \subsection{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.\\ + There is no significant effect of an offset in my 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 if it is necessary to use large windows, an offset is unnecessary. \subsection{Use of EEG channels} To achieve higher performance it would be interesting to identify those EEG channels that contribute most in an good estimation of arm movements or position. There should be channels that do not carry much information for those differentiations, this however has to be explored better.\\ In this context research could also be done to find out which frequencies allow for the best predictions. - Our findings predict a better performance for the alpha band and occipital and parietal regions. A more detailed work on this specific topic however is necessary to decide based on more data. + My findings predict a better performance for the alpha band and occipital and parietal regions. A more detailed work on this specific topic however is necessary to decide based on more data. \subsection{Self-chosen movement} - For a better use of low frequency features our work could be re-done with data recorded when subjects move voluntarily. This might also influence the way synergies are predicted and could lead to an better prediction.\\ + For a better use of low frequency features my work could be re-done with data recorded when subjects move voluntarily. This might also influence the way synergies are predicted and could lead to an better prediction.\\ Additionally this task matches the requirements for an BCI better, as movement in daily life is more voluntary than decided by a single auditory cue. \subsection{Synergies} \subsubsection{Generation of Synergies} - We proofed the plausibility of synergies here so the next step could be to improve the acquisition. Generating them from EMG may include unnecessary information. The generation of synergies as an intermediate step between EEG (or generally brain activity) and EMG (or generally muscle activity) my achieve even better results.\\ - A dimensionality reduction in EEG only probably will not work since there is to much unrelated activity, EMG only bears the problem of lower fit to the movement as we showed.\\ - An idea could be to try a dimensionality reduction on EEG of parts of the brain known to be involved in arm movement. This however is a far less general approach than the methods we used.\\ + I showed the plausibility of synergies here so the next step could be to improve the acquisition. Generating them from EMG may include unnecessary information. The generation of synergies as an intermediate step between EEG (or generally brain activity) and EMG (or generally muscle activity) my achieve even better results.\\ + A dimensionality reduction in EEG only probably will not work since there is to much unrelated activity, EMG only bears the problem of lower fit to the movement as is shown above.\\ + An idea could be to try a dimensionality reduction on EEG of parts of the brain known to be involved in arm movement. This however is a far less general approach than the methods I used.\\ A more general approach would be a neural network trained to predict EMG from EEG. The hidden layer of this network again could be used as synergies. \subsubsection{Autoencoders} - We did not find significantly better performance of autoencoders even with only 2 synergies. Since this was not the focus of our work here that might however be possible. Additional research is needed to answer which method is best to generate synergies. + I did not find significantly better performance of autoencoders even with only 2 synergies. Since this was not the focus of the work here that might however be possible. Additional research is needed to answer which method is best to generate synergies.