report.tex

\documentclass[11pt,a4paper]{article}

\setcounter{secnumdepth}{6}

\usepackage{standalone}

\usepackage{geometry} % Used to adjust the document margins
%~ \geometry{bindingoffset=1cm}
\usepackage{fullpage}
\usepackage{multirow}
%~ \usepackage{wasysym}
\usepackage{setspace}
\doublespacing

\usepackage{graphicx}
\usepackage[font=footnotesize]{caption}
\usepackage[noadjust]{cite}
\usepackage[toc,page]{appendix}
\usepackage{hyperref}


\usepackage{amsmath}
\usepackage{amsfonts}

%~ \usepackage{sidecap}
\usepackage{caption}
\usepackage{subcaption}


\usepackage[colorinlistoftodos,disable]{todonotes}
%~ \usepackage[colorinlistoftodos]{todonotes}
\usepackage{csquotes}
\usepackage{parskip} % Spaces between paragraphs


\usepackage[acronym]{glossaries}
% add binding margins


\makeglossaries

%~ \renewcommand*\abstractname{Summary}

% http://www.tex.ac.uk/cgi-bin/texfaq2html?label=altabcr
\setcounter{MaxMatrixCols}{50}

% package name:
\newcommand{\py}{\texttt{python}}
\newcommand{\pr}{\texttt{pyrem}}
\newcommand{\pyeeg}{\texttt{PyEEG}}
\newcommand{\ctit}{\emph}
\newcommand{\ptit}{\emph}

\newcommand{\eg}{\emph{e.g.}}
\newcommand{\ie}{\emph{i.e.}}

\newcommand{\specialcell}[2][c]{\begin{tabular}[#1]{@{}c@{}}#2\end{tabular}}


\newcommand{\FIXME}[2][]{\todo[color=cyan, #1]{\textbf{QG:} #2}}
\newcommand{\TODO}[2][]{\todo[color=red, #1]{\textbf{QG:} #2}}

\newcommand{\citationneeded}[2][]{\todo[color=brown, fancyline, #1]{\textbf{Citation Needed:} #2}}
\newcommand{\contrib}{\emph}
\begin{document}

\pagenumbering{roman}

\title{Vigilance state prediction using random forest and time interval feature space}
\author{Quentin Geissmann\\
\\	
\\
\\
\\
Supervised by Giorgio Gilestro\\
\\
\\
Imperial College London
\\
\\
\\
Words count in main text: 4996\\
\\
}
\date{\today}

\clearpage\maketitle
\thispagestyle{empty}
\newpage{}

\listoftodos
\newpage



% our acronyms
\newacronym{rem}{REM}{Rapid Eye Movement}
\newacronym{nrem}{NREM}{Non-Rapid Eye Movement}
\newacronym{eeg}{EEG}{Electroencephalogram}
\newacronym{emg}{EMG}{Electromyogram}
%~ \newacronym{eog}{EOG}{ElectroOculoGram}
\newacronym{svm}{SVM}{Support Vector Machine}
\newacronym{ann}{ANN}{Artificial Neural Network}
\newacronym{hmm}{HMM}{Hidden Markov Model}

%~ 
%~ \newglossaryentry{epoch}
%~ {
  %~ name=epoch,
  %~ description={todo
   %~ },
  %~ sort = epoch
%~ }
%~ 
%~ \newglossaryentry{$fs$}
%~ {
  %~ name=fs,
  %~ description={Samplig frequency
   %~ },
  %~ sort = fs
%~ }



\begin{abstract}

Electroencephalography (EEG) is a very widespread technique which is routinely used
as a diagnostic tool for brain dysfunctions and to investigate neurological
phenomenons.
Because of its relatively non-invasive nature,
it is widely used to determine and quantify sleep stages in humans and model
mammals such as rodents.
Historically, labelling of EEG recordings has been performed visually by trained
human experts. This task is extremely tedious and quite subjective.   
Despite recent efforts to develop an automatic classifier of sleep stages,
little adoption has occurred, and manual scoring is still the standard.

This study presents a high accuracy classifier of sleep stages that
could lead to an efficient software tool for biologists.
Exhaustive feature extraction based on discrete wavelet decomposition was used
in combination with a random forest classifier and was demonstrated to achieve
an overall accuracy of as high as 92\%.
In order to optimise feature extraction and pave the way for a future software
implementation, \pr{}, a \py{} package was also developed. \pr{} is here shown
to outperform an alternative runtime implementation by several orders of magnitude.
	%~ \\
	%~ \\
%~ \begin{itemize}
%~ \item Words in main text: 4996
%~ \item Words in headers: 84
%~ \item Words outside text (captions, etc.): 943
%~ \end{itemize}

\end{abstract}

\newpage

\tableofcontents
\newpage
\printglossaries

\newpage
\pagenumbering{arabic}

\input{intro}
\newpage{}
\input{matmet}
\newpage{}
\input{results}
\newpage{}
\input{discussion}

\newpage{}
\bibliography{report.bib}{}
\bibliographystyle{ieeetr}

%~ 
\newpage{}
\begin{appendices}
\section{\pr{} documentation}
In order to complement the following documentation, an interactive online version is available at \href{http://gilestrolab.github.io/pyrem/}{http://gilestrolab.github.io/pyrem/}.
\pr{}'s source code is available at \href{https://github.com/gilestrolab/pyrem/tree/master/src/}{https://github.com/gilestrolab/pyrem/tree/master/src/}
\end{appendices}
   
\end{document}