Abstract

The study of the behavior of ion-channels can provide significant information to detect metal ions and small organic molecules in solution. Discrimination of different ion-channels can be performed by extracting appropriate features from their signals and using them for classification. In this paper, we consider features extracted from the Fourier, wavelet and Walsh power spectra of the ion-channel signals. We compare the performance of all the three sets of features using support vector machines. We perform classification of signals from simulated and real ion-channels and present the results. Results obtained show that the transform domain features achieve high classification rates in addition to high sensitivity and specificity rates.

Original languageEnglish (US)
Pages (from-to)219-224
Number of pages6
JournalBiomedical Signal Processing and Control
Volume6
Issue number3
DOIs
StatePublished - Jul 2011

Fingerprint

Ion Channels
Ions
Power spectrum
Metal ions
Support vector machines
Metals
Sensitivity and Specificity
Molecules

Keywords

  • Classification
  • Ion-channel
  • Power spectral density
  • Walsh power spectrum
  • Wavelet power spectrum

ASJC Scopus subject areas

  • Health Informatics
  • Signal Processing

Cite this

Transform domain features for ion-channel signal classification. / Ramamurthy, Karthikeyan Natesan; Thiagarajan, Jayaraman J.; Sattigeri, Prasanna; Goryll, Michael; Spanias, Andreas; Thornton, Trevor; Phillips, Stephen.

In: Biomedical Signal Processing and Control, Vol. 6, No. 3, 07.2011, p. 219-224.

Research output: Contribution to journalArticle

Ramamurthy, Karthikeyan Natesan ; Thiagarajan, Jayaraman J. ; Sattigeri, Prasanna ; Goryll, Michael ; Spanias, Andreas ; Thornton, Trevor ; Phillips, Stephen. / Transform domain features for ion-channel signal classification. In: Biomedical Signal Processing and Control. 2011 ; Vol. 6, No. 3. pp. 219-224.
@article{c247d720943b46e794e1ab4a9bd3d4df,
title = "Transform domain features for ion-channel signal classification",
abstract = "The study of the behavior of ion-channels can provide significant information to detect metal ions and small organic molecules in solution. Discrimination of different ion-channels can be performed by extracting appropriate features from their signals and using them for classification. In this paper, we consider features extracted from the Fourier, wavelet and Walsh power spectra of the ion-channel signals. We compare the performance of all the three sets of features using support vector machines. We perform classification of signals from simulated and real ion-channels and present the results. Results obtained show that the transform domain features achieve high classification rates in addition to high sensitivity and specificity rates.",
keywords = "Classification, Ion-channel, Power spectral density, Walsh power spectrum, Wavelet power spectrum",
author = "Ramamurthy, {Karthikeyan Natesan} and Thiagarajan, {Jayaraman J.} and Prasanna Sattigeri and Michael Goryll and Andreas Spanias and Trevor Thornton and Stephen Phillips",
year = "2011",
month = "7",
doi = "10.1016/j.bspc.2010.09.002",
language = "English (US)",
volume = "6",
pages = "219--224",
journal = "Biomedical Signal Processing and Control",
issn = "1746-8094",
publisher = "Elsevier BV",
number = "3",

}

TY - JOUR

T1 - Transform domain features for ion-channel signal classification

AU - Ramamurthy, Karthikeyan Natesan

AU - Thiagarajan, Jayaraman J.

AU - Sattigeri, Prasanna

AU - Goryll, Michael

AU - Spanias, Andreas

AU - Thornton, Trevor

AU - Phillips, Stephen

PY - 2011/7

Y1 - 2011/7

N2 - The study of the behavior of ion-channels can provide significant information to detect metal ions and small organic molecules in solution. Discrimination of different ion-channels can be performed by extracting appropriate features from their signals and using them for classification. In this paper, we consider features extracted from the Fourier, wavelet and Walsh power spectra of the ion-channel signals. We compare the performance of all the three sets of features using support vector machines. We perform classification of signals from simulated and real ion-channels and present the results. Results obtained show that the transform domain features achieve high classification rates in addition to high sensitivity and specificity rates.

AB - The study of the behavior of ion-channels can provide significant information to detect metal ions and small organic molecules in solution. Discrimination of different ion-channels can be performed by extracting appropriate features from their signals and using them for classification. In this paper, we consider features extracted from the Fourier, wavelet and Walsh power spectra of the ion-channel signals. We compare the performance of all the three sets of features using support vector machines. We perform classification of signals from simulated and real ion-channels and present the results. Results obtained show that the transform domain features achieve high classification rates in addition to high sensitivity and specificity rates.

KW - Classification

KW - Ion-channel

KW - Power spectral density

KW - Walsh power spectrum

KW - Wavelet power spectrum

UR - http://www.scopus.com/inward/record.url?scp=79959931418&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=79959931418&partnerID=8YFLogxK

U2 - 10.1016/j.bspc.2010.09.002

DO - 10.1016/j.bspc.2010.09.002

M3 - Article

AN - SCOPUS:79959931418

VL - 6

SP - 219

EP - 224

JO - Biomedical Signal Processing and Control

JF - Biomedical Signal Processing and Control

SN - 1746-8094

IS - 3

ER -