diff --git a/text/thesis/01Introduction.tex b/text/thesis/01Introduction.tex index d897f3e..8b32a2f 100644 --- a/text/thesis/01Introduction.tex +++ b/text/thesis/01Introduction.tex @@ -1,5 +1,7 @@ \chapter{Introduction} +\label{introduction} \section{Motivation} +\label{intro:matovation} %TODO: More explanation, maybe better link to the topic \qq{Reading the mind} is something humanity is and always was exited about. Whatever one may think about the possibility of doing so as a human, computers have a chance to catch a glimpse of the (neuronal) activity in the human brain and interpret it.\\ Here we use electroencephalography (EEG) to record brain activity and try to predict arm movements from the data.\\ @@ -12,6 +14,7 @@ Predicting synergies instead of positions or movement is nearer to the concept the nervous system uses. This should make them easier to predict while we can also use them to move an robotic arm or an quadrocopter. \section{Scientific background} +\label{intro:background} \subsection{BCIs} The idea of BCIs began to spread in the 1970s when Vidal published his paper (\cite{Vidal73}).\\ First approaches used invasive BCIs earlier in Animals (rodents and monkeys) later also in humans. Invasive BCIs in humans were mostly implanted when the human was under brain surgery for another reason like epilepsy. Problems of invasive BCIs are the need to cut through skull and dura mater. This can lead to infections and severe brain damage.\\ @@ -21,7 +24,15 @@ When using EEG one measures the electrical fields on the scalp that are generated by activity of neurons in the brain. These measurements allow some interpretation about what is happening inside the skull. In our application we use the recorded currents directly to train a SVM or as predictor for regression.\\ The frequencies typically used for movement prediction in EEG are about 8-24 Hz (\cite{Blokland15},\cite{Ahmadian13},\cite{Wang09}). \subsection{Low Frequencies} - Another approach is looking at the low frequency features (below 1Hz) in the signal. %TODO citing - \subsection{Support Vector Machines (SVM)} + Another approach is looking at the low frequency features (below 2Hz) in the signal. This was done by Liu et al. (\cite{Liu11}) and Antelis et al. (\cite{Antelis13}) for example.\\ + Antelis et al. found correlations between hand movement and low frequency signal of $(0.29,0.15,0.37)$ in the dimensions respectively.\\ + We used this method here for comparison but did not find significant correlation with the kinematics. %TODO: significant? \subsection{Synergies} - + Movement of the arm (and other parts of the body) are under-determined meaning with given trajectory there are different muscle contractions possible. One idea how this problem could be solved by our nervous system are synergies. Proposed by Bernstein in 1967 (\cite{Bernstein67}) they describe the goal of the movement (e.g. the trajectory) instead of controlling single muscles. This would mean however that predicting the activity of single muscles from EEG is harder than predicting a synergy which in turn determines the contraction of muscles.\\ + Synergies are usually gotten from EMG signal through a principal component analysis (PCA, cf. \ref{tool:pca}), non-negative matrix factorisation (NMF, cf. \ref{tool:nmf}) or autoencoders (a form of neuronal network, cf. \ref{intro:autoenc},\ref{tool:autoenc}). + \subsection{Autoencoders} + \label{intro:autoenc} + Autoencoders are a specific type of artificial neural networks (ANN). They work like typical ANNs by adjusting weights between the layers however they don't predict an unknown output but they predict their own input. What is interesting now is manipulating the size of the hidden layer where the size of the hidden layer has to be smaller than the input size. Now in the hidden layer the information of the input can be found in a condensed form (e.g. synergies instead of single muscle activity).\\ + Autoencoders have been successfully used by Spüler et al. to extract synergies from EMG (\cite{Spuler16}). Especially with a lower number of synergies autoencoders perform better than PCA or NMF because linear models fail to discover the agonist-antagonist relations that are typical for muscle movements. These however can be detected by autoencoders which allows for smaller number of used synergies. %TODO: naja... +\section{Overview} +%TODO diff --git a/text/thesis/02MaterialsAndMethods.tex b/text/thesis/02MaterialsAndMethods.tex new file mode 100644 index 0000000..05add02 --- /dev/null +++ b/text/thesis/02MaterialsAndMethods.tex @@ -0,0 +1,9 @@ +\chapter{Materials and Methods} +\label{mat} +\section{Tools} +\subsection{PCA} +\label{tool:pca} +\subsection{NMF} +\label{tool:nmf} +\subsection{Autoencoder} +\label{tool:autoenc} diff --git a/text/thesis/mylit.bib b/text/thesis/mylit.bib index b4a45d9..b293d6a 100755 --- a/text/thesis/mylit.bib +++ b/text/thesis/mylit.bib @@ -65,3 +65,30 @@ year = "2013", journal = "Frontiers in Human Neuroscience", } +@proceedings{Liu11, + editor = "J. Liu and C. Perdoni and B. He", + title = "Hand movement decoding by phase-locking low frequency EEG signals", + year = "2011", + note = "IEEE Eng Med Biol Soc." +} +@article{Antelis13, + author = "Javier M. Antelis and Luis Montesano and Ander Ramos-Murguialday and Niels Birbaumer and Javier Minguez", + title = "On the Usage of Linear Regression Models to Reconstruct Limb Kinematics from Low Frequency EEG Signals", + year = "2013", + journal = "PLoS ONE", +} +@book{Bernstein67, + title={The co-ordination and regulation of movements}, + author={Bernstein, N.}, + year={1967}, + publisher={Pergamon-Press} +} +@inproceedings{Spuler16, + author = {M. Spüler and N. Irastorza Landa and A. Sarasola Sanz and A. Ramos-Murguialday}, + title = {Extracting Muscle Synergy Patterns from EMG Data Using Autoencoders}, + booktitle = {Artificial Neural Networks and Machine Learning - ICANN 2016}, + publisher = "Springer International Publishing", + year = {2016}, + month = {09}, + pages = {47-54}, +} diff --git a/text/thesis/outline.txt b/text/thesis/outline.txt index 8458eb9..cd543e3 100644 --- a/text/thesis/outline.txt +++ b/text/thesis/outline.txt @@ -5,8 +5,6 @@ - BCI - EEG - LF - - SVM - - Regression - Synergies - NN, esp. Autoencoders - We'll see... @@ -38,7 +36,7 @@ - Movement - Rest - different Movements - prediction kinematics - - no Matching recordings + - non-matching recordings - Synergies - PCA - NNMF diff --git a/text/thesis/thesis.tex b/text/thesis/thesis.tex index 1773e54..fcd49a7 100644 --- a/text/thesis/thesis.tex +++ b/text/thesis/thesis.tex @@ -35,7 +35,7 @@ \title{Movement Prediction from EEG based on Synergies} \author{Jan-Peter Hohloch} -\renewcommand{\title}{Movement Prediction from EEG based on Synergies} +\renewcommand{\title}{Movement Prediction from EEG\\ based on Synergies} \newcommand{\subtitle}{Evaluation and Comparison to other Methods} \renewcommand{\author}{Jan-Peter Hohloch} \date{\today} @@ -79,7 +79,7 @@ \textbf{Hohloch, Jan-Peter:}\\ \emph{\title}\\ Master Thesis Informatics\\ Eberhard Karls Universität Tübingen\\ -Thesis period: May-Nov 2016 %TODO - adjust if necessary +Thesis period: June-Nov 2016 %TODO - adjust if necessary \end{minipage} \newpage @@ -100,7 +100,7 @@ \section*{Acknowledgements} Write here your acknowledgements. -% Martin, Rosenstiel, Bierbaumer(?) - Data, Nieselt for template, WSI, Fachschaft, Familie, ...? +% Martin, Rosenstiel, Birbaumer(?) - Data, Nieselt for template, WSI, Fachschaft, Familie, ...? \cleardoublepage @@ -158,10 +158,12 @@ \begin{tabbing} \textbf{EEG}\hspace{1cm}\=Electroencephalography\\ -%\textbf{BMI}\> Brain-machine-interface \\ -\textbf{BCI}\> Brain-computer-interface \\ +\textbf{BCI}\> Brain-Computer-Interface \\ \textbf{SVM}\> Support-Vector-Machine \\ \textbf{ECoG}\> Electrocorticography \\ +\textbf{PCA}\> Principal Component Analysis \\ +\textbf{NMF}\> non-Negative Matrix Factorisation \\ +\textbf{ANN}\> Artificial Neural Network \\ \end{tabbing} \cleardoublepage @@ -179,8 +181,8 @@ \cleardoublepage %% Materials & Methods -% \input{sec2} -% \cleardoublepage +\input{02MaterialsAndMethods} +\cleardoublepage %% Results % \input{sec3}