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

Sairul Izwan Bin Safie; John Soraghan; Lykourgos Petropoulakis

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

Sairul Izwan Bin Safie, John Soraghan, Lykourgos Petropoulakis

Electronic And Electrical Engineering

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

8 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.

Original language	English
Pages	55-58
Number of pages	4
Publication status	Published - 16 Jun 2011
Event	18th International Conference on Systems, Signals and Image Processing (IWSSIP 2011) - , Sarajevo, Bosnia and Herzegovina Duration: 16 Jun 2011 → 18 Jun 2011

Conference

Conference	18th International Conference on Systems, Signals and Image Processing (IWSSIP 2011)
Country/Territory	Bosnia and Herzegovina
City	, Sarajevo
Period	16/06/11 → 18/06/11

Keywords

pulse active bit
biometric
electrocardiography

Cite this

@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 = jun,

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",

}

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

T2 - 18th International Conference on Systems, Signals and Image Processing (IWSSIP 2011)

Y2 - 16 June 2011 through 18 June 2011

ER -

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

Abstract

Conference

Keywords

Other files and links

Fingerprint

Cite this