Analysis of physiological signals using state space correlation entropy
In this letter, the authors propose a new entropy measure for analysis of time series. This measure is termed as the state space correlation entropy (SSCE). The state space reconstruction is used to evaluate the embedding vectors of a time series. The SSCE is computed from the probability of the cor...
Main Authors: | , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Wiley
2016-11-01
|
Series: | Healthcare Technology Letters |
Subjects: | |
Online Access: | https://digital-library.theiet.org/content/journals/10.1049/htl.2016.0065 |
id |
doaj-ffc5b23390b243728e3dc87eb3ea47ce |
---|---|
record_format |
Article |
spelling |
doaj-ffc5b23390b243728e3dc87eb3ea47ce2021-04-02T14:17:43ZengWileyHealthcare Technology Letters2053-37132016-11-0110.1049/htl.2016.0065HTL.2016.0065Analysis of physiological signals using state space correlation entropyRajesh Kumar Tripathy0Suman Deb1Suman Deb2Samarendra Dandapat3Samarendra Dandapat4Indian Institute of Technology GuwahatiIndian Institute of Technology GuwahatiIndian Institute of Technology GuwahatiIndian Institute of Technology GuwahatiIndian Institute of Technology GuwahatiIn this letter, the authors propose a new entropy measure for analysis of time series. This measure is termed as the state space correlation entropy (SSCE). The state space reconstruction is used to evaluate the embedding vectors of a time series. The SSCE is computed from the probability of the correlations of the embedding vectors. The performance of SSCE measure is evaluated using both synthetic and real valued signals. The experimental results reveal that, the proposed SSCE measure along with SVM classifier have sensitivity value of 91.60%, which is higher than the performance of both sample entropy and permutation entropy features for detection of shockable ventricular arrhythmia.https://digital-library.theiet.org/content/journals/10.1049/htl.2016.0065medical disorderselectrocardiographyelectroencephalographyspeechmedical signal processingspeech processingentropystate-space methodscorrelation methodstime seriessignal reconstructionsupport vector machinessignal classificationphysiological signalsstate space correlation entropytime seriesSSCEstate space reconstructionsynthetic valued signalsreal valued signalsSVM classifiersupport vector machinesample entropypermutation entropyshockable ventricular arrhythmiaECGEEGspeech |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Rajesh Kumar Tripathy Suman Deb Suman Deb Samarendra Dandapat Samarendra Dandapat |
spellingShingle |
Rajesh Kumar Tripathy Suman Deb Suman Deb Samarendra Dandapat Samarendra Dandapat Analysis of physiological signals using state space correlation entropy Healthcare Technology Letters medical disorders electrocardiography electroencephalography speech medical signal processing speech processing entropy state-space methods correlation methods time series signal reconstruction support vector machines signal classification physiological signals state space correlation entropy time series SSCE state space reconstruction synthetic valued signals real valued signals SVM classifier support vector machine sample entropy permutation entropy shockable ventricular arrhythmia ECG EEG speech |
author_facet |
Rajesh Kumar Tripathy Suman Deb Suman Deb Samarendra Dandapat Samarendra Dandapat |
author_sort |
Rajesh Kumar Tripathy |
title |
Analysis of physiological signals using state space correlation entropy |
title_short |
Analysis of physiological signals using state space correlation entropy |
title_full |
Analysis of physiological signals using state space correlation entropy |
title_fullStr |
Analysis of physiological signals using state space correlation entropy |
title_full_unstemmed |
Analysis of physiological signals using state space correlation entropy |
title_sort |
analysis of physiological signals using state space correlation entropy |
publisher |
Wiley |
series |
Healthcare Technology Letters |
issn |
2053-3713 |
publishDate |
2016-11-01 |
description |
In this letter, the authors propose a new entropy measure for analysis of time series. This measure is termed as the state space correlation entropy (SSCE). The state space reconstruction is used to evaluate the embedding vectors of a time series. The SSCE is computed from the probability of the correlations of the embedding vectors. The performance of SSCE measure is evaluated using both synthetic and real valued signals. The experimental results reveal that, the proposed SSCE measure along with SVM classifier have sensitivity value of 91.60%, which is higher than the performance of both sample entropy and permutation entropy features for detection of shockable ventricular arrhythmia. |
topic |
medical disorders electrocardiography electroencephalography speech medical signal processing speech processing entropy state-space methods correlation methods time series signal reconstruction support vector machines signal classification physiological signals state space correlation entropy time series SSCE state space reconstruction synthetic valued signals real valued signals SVM classifier support vector machine sample entropy permutation entropy shockable ventricular arrhythmia ECG EEG speech |
url |
https://digital-library.theiet.org/content/journals/10.1049/htl.2016.0065 |
work_keys_str_mv |
AT rajeshkumartripathy analysisofphysiologicalsignalsusingstatespacecorrelationentropy AT sumandeb analysisofphysiologicalsignalsusingstatespacecorrelationentropy AT sumandeb analysisofphysiologicalsignalsusingstatespacecorrelationentropy AT samarendradandapat analysisofphysiologicalsignalsusingstatespacecorrelationentropy AT samarendradandapat analysisofphysiologicalsignalsusingstatespacecorrelationentropy |
_version_ |
1721562633335734272 |