bp/QMUL_Final_Project
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Working on feature analysis literature review section

Browse Source
This commit is contained in:
Sam Perry
2017-01-07 16:15:10 +00:00
parent 650ef58f89
commit 8da8bd7fdb
1 changed files with 51 additions and 6 deletions
Download Patch File Download Diff File Expand all files Collapse all files
Project_Writeup.tex
+51 -6
View File
@@ -69,14 +69,14 @@
\begin{document}
\title{ECS750P --- Final Project}
\subtitle{\LARGE{Extraction and Analysis of RR Intervals from PCG Signals for the
Classification of Heart Abnormalities}}
\subtitle{\LARGE{Extraction and Analysis of Statistical Features from PCG
Signals for the Classification of Heart Abnormalities}}
\author{Sam Perry --- EC16039}
\maketitle
\section{Literature Review}
There are currently a wide variety of methods employed for the analysis and
There are currently a wide variety of methods are employed for the analysis and
classification of PCG signals. Current research focuses on a number of areas,
the most relevant of which are:
\begin{itemize}
@@ -95,16 +95,61 @@ the most relevant of which are:
splitting of the FHSs, in particular using wavelet
decomposition~\parencite{LiangHuiying1997, Vepa2008}. This allows for
the separation of components based on their frequency content in
addition to temporal characteristics.\\
place of or addition to their temporal characteristics.\\
In addition, Machine learning algorithms have been employed, such as k
Nearest Neighbour~\parencite{Gupta2007} and Neural
Networks~\parencite{Oskiper2002} to improve segment classification.
More recently, particular success has been observed in Springer's use
of logistic regression and Hidden semi-Markov
models~\citeyearpar{Springer2016}.
\item A plethora of methods exist for the extraction of statistical
\item Signal Pre-processing?
Removal of ectopic beats in RR estimation~\parencite{Dash2009}
\item A wide variety of methods exist for the extraction of statistical
features from PCG data. These features are used for the creation of
robust, meaningful representations of the data.
robust, meaningful representations of the data.\\
The use of spectral representations for PCG data are prominent in the
literature. The ability to separate activity across the frequency
spectrum reveals patterns that may not be attainable by analysing the
time domain signal alone.\\
Due to the need for low frequency analysis and the high noise levels
found in PCG signals, it has been found that the traditional FFT
method for extracting spectral information may not be
suitable~\parencite{Akay1990}. For this reason, parametric methods for
spectral estimation have been a popular choice for extraction of such information.
Methods such as AR, ARMA, AR-HOS and MUSIC have been shown to provide spectral
representations suitable for analysis and classification of heart
sound~\parencite{Ergen2001, Schmidt2015}.\\
Other methods such as Wavelet Decomposition and MFCCs have also been
successfully employed for extracting spectral data for purposes such
as heart valve disease identification and heart murmur
detection~\parencite{Quiceno-Manrique2010a, Maglogiannis2009}.\\
In addition to direct analysis on the signal, the ability to segment
and extract RR values from the signal allows for their statistical
analysis, both in the time and frequency domain, for use as features.\\
Dash et al. use a number of time-based statistical analysis on the RR
time series for the detection of atrial fibrilation. Statistical
analyses such as RMSSD, Shannon Entropy and Turning-point Ratio are
used as feature vectors for classification of
signals~\parencite{Dash2009}. A similar approach is used by Yaghouby
et al. for the generalized classification of heart abnormality. Here,
other features such as HR Mean, Standard deviation, pNN50 and
Triangular Index are used for classification with promising
results~\parencite{Yaghouby2009}.
Frequency domain analysis of RR values can also be considered by
calculating the PSD of the RR values via similar methods for spectral
analysis as with the direct signal.
RR Frequency Domain Features
RR Time-frequency domain features VFCDM~\parencite{Dash2009}
RR Non-linear features
~\parencite{Yaghouby2009}
\item Classification of signals for diagnostic purposes. The aim being to
distinguish healthy signals from those with certain heart
conditions/abnormality. Machine learning techniques are commonly used