Pulse active harmonic (PAH) features for ECG biometric authentication

Sairul Izwan Bin Safie, Haris Nur, Zainal Azavitra, John Soraghan, Lykourgos Petropoulakis

Research output: Chapter in Book/Report/Conference proceedingConference contribution book

Abstract

This paper presents a feature extraction method known as Pulse Active Harmonic (PAH) implemented on electrocardiograph (ECG) signals for biometric authentication. The technique is based on a pulse width modulation concept. A total of 200 Eggs from 100 subjects, taken from the Physikalisch-Technische Bundesanstalt (PTB) database are used in the simulations. Biometric performance profile such as the area under ROC (AUR) and equal error rate (EER) are then used to evaluate the results. This work shows that: a) the PAH method outperforms conventional temporal feature extraction techniques, b) its performance is comparable to other, previously introduced, Pulse Active based methods. Hence, owing to their close similarities Pulse Active approaches can readily be combined to form robust and inherently secure biometric authentication systems.
LanguageEnglish
Title of host publication2013 1st International Conference on Artificial Intelligence, Modelling and Simulation (AIMS)
PublisherIEEE
Pages255 - 260
Number of pages6
ISBN (Print)978-1-4799-3250-4
DOIs
Publication statusPublished - 5 Apr 2013

Fingerprint

Biometrics
Authentication
Feature extraction
Pulse width modulation

Keywords

  • electrocardiography
  • pulse active harmonics
  • feature extraction
  • harmonic analysis

Cite this

Bin Safie, S. I., Nur, H., Azavitra, Z., Soraghan, J., & Petropoulakis, L. (2013). Pulse active harmonic (PAH) features for ECG biometric authentication. In 2013 1st International Conference on Artificial Intelligence, Modelling and Simulation (AIMS) (pp. 255 - 260). IEEE. https://doi.org/10.1109/AIMS.2013.47
Bin Safie, Sairul Izwan ; Nur, Haris ; Azavitra, Zainal ; Soraghan, John ; Petropoulakis, Lykourgos. / Pulse active harmonic (PAH) features for ECG biometric authentication. 2013 1st International Conference on Artificial Intelligence, Modelling and Simulation (AIMS). IEEE, 2013. pp. 255 - 260
@inproceedings{25afc1de603047f4bef6e3b044edf76e,
title = "Pulse active harmonic (PAH) features for ECG biometric authentication",
abstract = "This paper presents a feature extraction method known as Pulse Active Harmonic (PAH) implemented on electrocardiograph (ECG) signals for biometric authentication. The technique is based on a pulse width modulation concept. A total of 200 Eggs from 100 subjects, taken from the Physikalisch-Technische Bundesanstalt (PTB) database are used in the simulations. Biometric performance profile such as the area under ROC (AUR) and equal error rate (EER) are then used to evaluate the results. This work shows that: a) the PAH method outperforms conventional temporal feature extraction techniques, b) its performance is comparable to other, previously introduced, Pulse Active based methods. Hence, owing to their close similarities Pulse Active approaches can readily be combined to form robust and inherently secure biometric authentication systems.",
keywords = "electrocardiography, pulse active harmonics, feature extraction, harmonic analysis",
author = "{Bin Safie}, {Sairul Izwan} and Haris Nur and Zainal Azavitra and John Soraghan and Lykourgos Petropoulakis",
year = "2013",
month = "4",
day = "5",
doi = "10.1109/AIMS.2013.47",
language = "English",
isbn = "978-1-4799-3250-4",
pages = "255 -- 260",
booktitle = "2013 1st International Conference on Artificial Intelligence, Modelling and Simulation (AIMS)",
publisher = "IEEE",

}

Bin Safie, SI, Nur, H, Azavitra, Z, Soraghan, J & Petropoulakis, L 2013, Pulse active harmonic (PAH) features for ECG biometric authentication. in 2013 1st International Conference on Artificial Intelligence, Modelling and Simulation (AIMS). IEEE, pp. 255 - 260. https://doi.org/10.1109/AIMS.2013.47

Pulse active harmonic (PAH) features for ECG biometric authentication. / Bin Safie, Sairul Izwan; Nur, Haris; Azavitra, Zainal; Soraghan, John; Petropoulakis, Lykourgos.

2013 1st International Conference on Artificial Intelligence, Modelling and Simulation (AIMS). IEEE, 2013. p. 255 - 260.

Research output: Chapter in Book/Report/Conference proceedingConference contribution book

TY - GEN

T1 - Pulse active harmonic (PAH) features for ECG biometric authentication

AU - Bin Safie, Sairul Izwan

AU - Nur, Haris

AU - Azavitra, Zainal

AU - Soraghan, John

AU - Petropoulakis, Lykourgos

PY - 2013/4/5

Y1 - 2013/4/5

N2 - This paper presents a feature extraction method known as Pulse Active Harmonic (PAH) implemented on electrocardiograph (ECG) signals for biometric authentication. The technique is based on a pulse width modulation concept. A total of 200 Eggs from 100 subjects, taken from the Physikalisch-Technische Bundesanstalt (PTB) database are used in the simulations. Biometric performance profile such as the area under ROC (AUR) and equal error rate (EER) are then used to evaluate the results. This work shows that: a) the PAH method outperforms conventional temporal feature extraction techniques, b) its performance is comparable to other, previously introduced, Pulse Active based methods. Hence, owing to their close similarities Pulse Active approaches can readily be combined to form robust and inherently secure biometric authentication systems.

AB - This paper presents a feature extraction method known as Pulse Active Harmonic (PAH) implemented on electrocardiograph (ECG) signals for biometric authentication. The technique is based on a pulse width modulation concept. A total of 200 Eggs from 100 subjects, taken from the Physikalisch-Technische Bundesanstalt (PTB) database are used in the simulations. Biometric performance profile such as the area under ROC (AUR) and equal error rate (EER) are then used to evaluate the results. This work shows that: a) the PAH method outperforms conventional temporal feature extraction techniques, b) its performance is comparable to other, previously introduced, Pulse Active based methods. Hence, owing to their close similarities Pulse Active approaches can readily be combined to form robust and inherently secure biometric authentication systems.

KW - electrocardiography

KW - pulse active harmonics

KW - feature extraction

KW - harmonic analysis

UR - http://ieeexplore.ieee.org/xpl/articleDetails.jsp?arnumber=6959925

U2 - 10.1109/AIMS.2013.47

DO - 10.1109/AIMS.2013.47

M3 - Conference contribution book

SN - 978-1-4799-3250-4

SP - 255

EP - 260

BT - 2013 1st International Conference on Artificial Intelligence, Modelling and Simulation (AIMS)

PB - IEEE

ER -

Bin Safie SI, Nur H, Azavitra Z, Soraghan J, Petropoulakis L. Pulse active harmonic (PAH) features for ECG biometric authentication. In 2013 1st International Conference on Artificial Intelligence, Modelling and Simulation (AIMS). IEEE. 2013. p. 255 - 260 https://doi.org/10.1109/AIMS.2013.47