Pulse active ratio (PAR): an ECG feature extraction technique for ECG biometric authentication

Sairul Izwan Bin Safie; John Soraghan; Lykourgos Petropoulakis

doi:10.1109/ICSIPA.2011.6144124

Pulse active ratio (PAR): an ECG feature extraction technique for ECG biometric authentication

Sairul Izwan Bin Safie, John Soraghan, Lykourgos Petropoulakis

Electronic And Electrical Engineering

Research output: Contribution to conference › Paper › peer-review

4 Citations (Scopus)

Abstract

A new feature extraction method known as Pulse Active Ratio (PAR) implemented on electrocardiogram (ECG) signals for biometric authentication is presented. It is developed based on the principle of Pulse Width Modulation (PWM) which is widely used in the field of power and communication engineering. A total of 486 ECGs from 113 subjects taken from the Physikalisch-Technische Bundesanstalt (PTB) database are used in this study. Biometric performance profile such as the area under ROC (AUR) and equal error rate (EER) are used in the simulations. It is shown that PAR outperforms conventional temporal and amplitude feature extraction techniques.

Original language	English
Pages	16-21
Number of pages	5
DOIs	https://doi.org/10.1109/ICSIPA.2011.6144124
Publication status	Published - 18 Nov 2011
Event	IEEE International Conference on Signal & Image Processing Applications (ICSIPA) - Kuala Lumpur, Malaysia Duration: 16 Nov 2011 → 18 Nov 2011

Conference

Conference	IEEE International Conference on Signal & Image Processing Applications (ICSIPA)
Country/Territory	Malaysia
City	Kuala Lumpur
Period	16/11/11 → 18/11/11

Keywords

pulse active ratio
electrocardiogram signals
signal processing

Access to Document

10.1109/ICSIPA.2011.6144124

Cite this

@conference{a2d483cdcf9743dcbd08accad866a02d,

title = "Pulse active ratio (PAR): an ECG feature extraction technique for ECG biometric authentication",

abstract = "A new feature extraction method known as Pulse Active Ratio (PAR) implemented on electrocardiogram (ECG) signals for biometric authentication is presented. It is developed based on the principle of Pulse Width Modulation (PWM) which is widely used in the field of power and communication engineering. A total of 486 ECGs from 113 subjects taken from the Physikalisch-Technische Bundesanstalt (PTB) database are used in this study. Biometric performance profile such as the area under ROC (AUR) and equal error rate (EER) are used in the simulations. It is shown that PAR outperforms conventional temporal and amplitude feature extraction techniques.",

keywords = "pulse active ratio, electrocardiogram signals, signal processing",

author = "{Bin Safie}, {Sairul Izwan} and John Soraghan and Lykourgos Petropoulakis",

year = "2011",

month = nov,

day = "18",

doi = "10.1109/ICSIPA.2011.6144124",

language = "English",

pages = "16--21",

note = "IEEE International Conference on Signal & Image Processing Applications (ICSIPA) ; Conference date: 16-11-2011 Through 18-11-2011",

}

Pulse active ratio (PAR): an ECG feature extraction technique for ECG biometric authentication. / Bin Safie, Sairul Izwan; Soraghan, John; Petropoulakis, Lykourgos.
2011. 16-21 Paper presented at IEEE International Conference on Signal & Image Processing Applications (ICSIPA), Kuala Lumpur, Malaysia.

Research output: Contribution to conference › Paper › peer-review

TY - CONF

T1 - Pulse active ratio (PAR)

T2 - IEEE International Conference on Signal & Image Processing Applications (ICSIPA)

AU - Bin Safie, Sairul Izwan

AU - Soraghan, John

AU - Petropoulakis, Lykourgos

PY - 2011/11/18

Y1 - 2011/11/18

N2 - A new feature extraction method known as Pulse Active Ratio (PAR) implemented on electrocardiogram (ECG) signals for biometric authentication is presented. It is developed based on the principle of Pulse Width Modulation (PWM) which is widely used in the field of power and communication engineering. A total of 486 ECGs from 113 subjects taken from the Physikalisch-Technische Bundesanstalt (PTB) database are used in this study. Biometric performance profile such as the area under ROC (AUR) and equal error rate (EER) are used in the simulations. It is shown that PAR outperforms conventional temporal and amplitude feature extraction techniques.

AB - A new feature extraction method known as Pulse Active Ratio (PAR) implemented on electrocardiogram (ECG) signals for biometric authentication is presented. It is developed based on the principle of Pulse Width Modulation (PWM) which is widely used in the field of power and communication engineering. A total of 486 ECGs from 113 subjects taken from the Physikalisch-Technische Bundesanstalt (PTB) database are used in this study. Biometric performance profile such as the area under ROC (AUR) and equal error rate (EER) are used in the simulations. It is shown that PAR outperforms conventional temporal and amplitude feature extraction techniques.

KW - pulse active ratio

KW - electrocardiogram signals

KW - signal processing

UR - http://www.scopus.com/inward/record.url?scp=84857467654&partnerID=8YFLogxK

UR - http://ieeexplore.ieee.org/xpl/mostRecentIssue.jsp?punumber=6138563

U2 - 10.1109/ICSIPA.2011.6144124

DO - 10.1109/ICSIPA.2011.6144124

M3 - Paper

SP - 16

EP - 21

Y2 - 16 November 2011 through 18 November 2011

ER -

Pulse active ratio (PAR): an ECG feature extraction technique for ECG biometric authentication

Abstract

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this