Classification of cardiosynchronous waveforms by projection to a Legendre Polynomial sub-space.

Aaron Jaech, Rebecca Blue, Robert Friedman, Marc O. Griofa, Marios Savvides, B. V.K.Vijaya Kumar

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

The use of Radio Frequency Impedance Interrogation (RFII) is being investigated for use as a noninvasive hemodynamic monitoring system and in the capacity of a biometric identifier. Biometric identification of subjects by cardiosynchronous waveform generated through RFII technology could allow the identification of subjects in operational and potentially hostile environments. Here, the filtering methods for extracting a unique biometric signature from the RFII signal are examined, including the use of Cepstral analysis for dynamically estimating the filter parameters. The projection of that signature to a Legendre Polynomial sub-space is proposed for increased class separability in a low dimensional space. Support Vector Machine (SVM) and k-Nearest Neighbor (k=3) classification are performed in the Legendre Polynomial sub-space on a small dataset. Both the k-Nearest Neighbor and linear SVM methods demonstrated highly successful classification accuracy, with 93-100% accuracy demonstrated by various classification methods. The results are highly encouraging despite the small sample size. Further analysis with a larger dataset will help to refine this process for the eventual application of RFII as a robust biometric identifier.

Fingerprint

Biometrics
Electric Impedance
Radio
Polynomials
Support vector machines
Biometric Identification
Hemodynamics
Sample Size
Technology
Monitoring
Support Vector Machine
Datasets

ASJC Scopus subject areas

  • Signal Processing
  • Biomedical Engineering
  • Computer Vision and Pattern Recognition
  • Health Informatics

Cite this

Classification of cardiosynchronous waveforms by projection to a Legendre Polynomial sub-space. / Jaech, Aaron; Blue, Rebecca; Friedman, Robert; Griofa, Marc O.; Savvides, Marios; Kumar, B. V.K.Vijaya.

In: Conference proceedings : ... Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Conference, 01.01.2012, p. 4307-4310.

Research output: Contribution to journalArticle

@article{8ded353cd5d940f7909465dcabe01d6c,
title = "Classification of cardiosynchronous waveforms by projection to a Legendre Polynomial sub-space.",
abstract = "The use of Radio Frequency Impedance Interrogation (RFII) is being investigated for use as a noninvasive hemodynamic monitoring system and in the capacity of a biometric identifier. Biometric identification of subjects by cardiosynchronous waveform generated through RFII technology could allow the identification of subjects in operational and potentially hostile environments. Here, the filtering methods for extracting a unique biometric signature from the RFII signal are examined, including the use of Cepstral analysis for dynamically estimating the filter parameters. The projection of that signature to a Legendre Polynomial sub-space is proposed for increased class separability in a low dimensional space. Support Vector Machine (SVM) and k-Nearest Neighbor (k=3) classification are performed in the Legendre Polynomial sub-space on a small dataset. Both the k-Nearest Neighbor and linear SVM methods demonstrated highly successful classification accuracy, with 93-100{\%} accuracy demonstrated by various classification methods. The results are highly encouraging despite the small sample size. Further analysis with a larger dataset will help to refine this process for the eventual application of RFII as a robust biometric identifier.",
author = "Aaron Jaech and Rebecca Blue and Robert Friedman and Griofa, {Marc O.} and Marios Savvides and Kumar, {B. V.K.Vijaya}",
year = "2012",
month = "1",
day = "1",
language = "English (US)",
pages = "4307--4310",
journal = "Conference proceedings : ... Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Conference",
issn = "1557-170X",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - JOUR

T1 - Classification of cardiosynchronous waveforms by projection to a Legendre Polynomial sub-space.

AU - Jaech, Aaron

AU - Blue, Rebecca

AU - Friedman, Robert

AU - Griofa, Marc O.

AU - Savvides, Marios

AU - Kumar, B. V.K.Vijaya

PY - 2012/1/1

Y1 - 2012/1/1

N2 - The use of Radio Frequency Impedance Interrogation (RFII) is being investigated for use as a noninvasive hemodynamic monitoring system and in the capacity of a biometric identifier. Biometric identification of subjects by cardiosynchronous waveform generated through RFII technology could allow the identification of subjects in operational and potentially hostile environments. Here, the filtering methods for extracting a unique biometric signature from the RFII signal are examined, including the use of Cepstral analysis for dynamically estimating the filter parameters. The projection of that signature to a Legendre Polynomial sub-space is proposed for increased class separability in a low dimensional space. Support Vector Machine (SVM) and k-Nearest Neighbor (k=3) classification are performed in the Legendre Polynomial sub-space on a small dataset. Both the k-Nearest Neighbor and linear SVM methods demonstrated highly successful classification accuracy, with 93-100% accuracy demonstrated by various classification methods. The results are highly encouraging despite the small sample size. Further analysis with a larger dataset will help to refine this process for the eventual application of RFII as a robust biometric identifier.

AB - The use of Radio Frequency Impedance Interrogation (RFII) is being investigated for use as a noninvasive hemodynamic monitoring system and in the capacity of a biometric identifier. Biometric identification of subjects by cardiosynchronous waveform generated through RFII technology could allow the identification of subjects in operational and potentially hostile environments. Here, the filtering methods for extracting a unique biometric signature from the RFII signal are examined, including the use of Cepstral analysis for dynamically estimating the filter parameters. The projection of that signature to a Legendre Polynomial sub-space is proposed for increased class separability in a low dimensional space. Support Vector Machine (SVM) and k-Nearest Neighbor (k=3) classification are performed in the Legendre Polynomial sub-space on a small dataset. Both the k-Nearest Neighbor and linear SVM methods demonstrated highly successful classification accuracy, with 93-100% accuracy demonstrated by various classification methods. The results are highly encouraging despite the small sample size. Further analysis with a larger dataset will help to refine this process for the eventual application of RFII as a robust biometric identifier.

UR - http://www.scopus.com/inward/record.url?scp=84880957436&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84880957436&partnerID=8YFLogxK

M3 - Article

SP - 4307

EP - 4310

JO - Conference proceedings : ... Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Conference

JF - Conference proceedings : ... Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Conference

SN - 1557-170X

ER -