Pulse active bit (PAB) feature extractor for ECG biometric authentication

Sairul Izwan Bin Safie, John Soraghan, Lykourgos Petropoulakis

Research output: Contribution to conferencePaper

6 Citations (Scopus)

Abstract

This paper presents a new feature extraction method known as Pulse Active Bit (PAB) implemented on electrocardiograph (ECG) signals for biometric authentication. This method is developed based on a simple amplitude comparison between two signals for feature extraction. 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 then used to evaluate the results. It is shown in this study that PAB outperforms conventional temporal feature extraction techniques.

Conference

Conference18th International Conference on Systems, Signals and Image Processing (IWSSIP 2011)
CountryBosnia and Herzegovina
City, Sarajevo
Period16/06/1118/06/11

Fingerprint

Biometrics
Authentication
Feature extraction
Electrocardiography

Keywords

  • pulse active bit
  • biometric
  • electrocardiography

Cite this

Bin Safie, S. I., Soraghan, J., & Petropoulakis, L. (2011). Pulse active bit (PAB) feature extractor for ECG biometric authentication. 55-58. Paper presented at 18th International Conference on Systems, Signals and Image Processing (IWSSIP 2011), , Sarajevo, Bosnia and Herzegovina.
Bin Safie, Sairul Izwan ; Soraghan, John ; Petropoulakis, Lykourgos. / Pulse active bit (PAB) feature extractor for ECG biometric authentication. Paper presented at 18th International Conference on Systems, Signals and Image Processing (IWSSIP 2011), , Sarajevo, Bosnia and Herzegovina.4 p.
@conference{8fbba6221f8d4b85b437dde2ae8af65b,
title = "Pulse active bit (PAB) feature extractor for ECG biometric authentication",
abstract = "This paper presents a new feature extraction method known as Pulse Active Bit (PAB) implemented on electrocardiograph (ECG) signals for biometric authentication. This method is developed based on a simple amplitude comparison between two signals for feature extraction. 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 then used to evaluate the results. It is shown in this study that PAB outperforms conventional temporal feature extraction techniques.",
keywords = "pulse active bit, biometric, electrocardiography",
author = "{Bin Safie}, {Sairul Izwan} and John Soraghan and Lykourgos Petropoulakis",
year = "2011",
month = "6",
day = "16",
language = "English",
pages = "55--58",
note = "18th International Conference on Systems, Signals and Image Processing (IWSSIP 2011) ; Conference date: 16-06-2011 Through 18-06-2011",

}

Bin Safie, SI, Soraghan, J & Petropoulakis, L 2011, 'Pulse active bit (PAB) feature extractor for ECG biometric authentication' Paper presented at 18th International Conference on Systems, Signals and Image Processing (IWSSIP 2011), , Sarajevo, Bosnia and Herzegovina, 16/06/11 - 18/06/11, pp. 55-58.

Pulse active bit (PAB) feature extractor for ECG biometric authentication. / Bin Safie, Sairul Izwan; Soraghan, John; Petropoulakis, Lykourgos.

2011. 55-58 Paper presented at 18th International Conference on Systems, Signals and Image Processing (IWSSIP 2011), , Sarajevo, Bosnia and Herzegovina.

Research output: Contribution to conferencePaper

TY - CONF

T1 - Pulse active bit (PAB) feature extractor for ECG biometric authentication

AU - Bin Safie, Sairul Izwan

AU - Soraghan, John

AU - Petropoulakis, Lykourgos

PY - 2011/6/16

Y1 - 2011/6/16

N2 - This paper presents a new feature extraction method known as Pulse Active Bit (PAB) implemented on electrocardiograph (ECG) signals for biometric authentication. This method is developed based on a simple amplitude comparison between two signals for feature extraction. 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 then used to evaluate the results. It is shown in this study that PAB outperforms conventional temporal feature extraction techniques.

AB - This paper presents a new feature extraction method known as Pulse Active Bit (PAB) implemented on electrocardiograph (ECG) signals for biometric authentication. This method is developed based on a simple amplitude comparison between two signals for feature extraction. 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 then used to evaluate the results. It is shown in this study that PAB outperforms conventional temporal feature extraction techniques.

KW - pulse active bit

KW - biometric

KW - electrocardiography

UR - http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=5977401

M3 - Paper

SP - 55

EP - 58

ER -

Bin Safie SI, Soraghan J, Petropoulakis L. Pulse active bit (PAB) feature extractor for ECG biometric authentication. 2011. Paper presented at 18th International Conference on Systems, Signals and Image Processing (IWSSIP 2011), , Sarajevo, Bosnia and Herzegovina.