ECG biometric authentication based on non-fiducial approach using kernel methods

Identity recognition faces several challenges especially in extracting an individual's unique features from biometric modalities and pattern classifications. Electrocardiogram (ECG) waveforms, for instance, have unique identity properties for human recognition, and their signals are not periodi...

Full description

Bibliographic Details
Main Authors: Hejazi, Maryamsadat, Syed Mohamed, Syed Abdul Rahman Al-Haddad, Singh, Yashwant Prasad, Hashim, Shaiful Jahari, Abdul Aziz, Ahmad Fazli
Format: Article
Language:English
Published: Elsevier 2016
Online Access:http://psasir.upm.edu.my/id/eprint/43276/1/ECG%20biometric%20authentication%20based%20on%20non-fiducial%20approach%20using%20kernel%20methods.pdf
_version_ 1825929329389862912
author Hejazi, Maryamsadat
Syed Mohamed, Syed Abdul Rahman Al-Haddad
Singh, Yashwant Prasad
Hashim, Shaiful Jahari
Abdul Aziz, Ahmad Fazli
author_facet Hejazi, Maryamsadat
Syed Mohamed, Syed Abdul Rahman Al-Haddad
Singh, Yashwant Prasad
Hashim, Shaiful Jahari
Abdul Aziz, Ahmad Fazli
author_sort Hejazi, Maryamsadat
collection UPM
description Identity recognition faces several challenges especially in extracting an individual's unique features from biometric modalities and pattern classifications. Electrocardiogram (ECG) waveforms, for instance, have unique identity properties for human recognition, and their signals are not periodic. At present, in order to generate a significant ECG feature set, non-fiducial methodologies based on an autocorrelation (AC) in conjunction with linear dimension reduction methods are used. This paper proposes a new non-fiducial framework for ECG biometric verification using kernel methods to reduce both high autocorrelation vectors' dimensionality and recognition system after denoising signals of 52 subjects with Discrete Wavelet Transform (DWT). The effects of different dimensionality reduction techniques for use in feature extraction were investigated to evaluate verification performance rates of a multi-class Support Vector Machine (SVM) with the One-Against-All (OAA) approach. The experimental results demonstrated higher test recognition rates of Gaussian OAA SVMs on random unknown ECG data sets with the use of the Kernel Principal Component Analysis (KPCA) as compared to the use of the Linear Discriminant Analysis (LDA) and Principal Component Analysis (PCA).
first_indexed 2024-03-06T08:55:11Z
format Article
id upm.eprints-43276
institution Universiti Putra Malaysia
language English
last_indexed 2024-03-06T08:55:11Z
publishDate 2016
publisher Elsevier
record_format dspace
spelling upm.eprints-432762016-05-18T04:36:24Z http://psasir.upm.edu.my/id/eprint/43276/ ECG biometric authentication based on non-fiducial approach using kernel methods Hejazi, Maryamsadat Syed Mohamed, Syed Abdul Rahman Al-Haddad Singh, Yashwant Prasad Hashim, Shaiful Jahari Abdul Aziz, Ahmad Fazli Identity recognition faces several challenges especially in extracting an individual's unique features from biometric modalities and pattern classifications. Electrocardiogram (ECG) waveforms, for instance, have unique identity properties for human recognition, and their signals are not periodic. At present, in order to generate a significant ECG feature set, non-fiducial methodologies based on an autocorrelation (AC) in conjunction with linear dimension reduction methods are used. This paper proposes a new non-fiducial framework for ECG biometric verification using kernel methods to reduce both high autocorrelation vectors' dimensionality and recognition system after denoising signals of 52 subjects with Discrete Wavelet Transform (DWT). The effects of different dimensionality reduction techniques for use in feature extraction were investigated to evaluate verification performance rates of a multi-class Support Vector Machine (SVM) with the One-Against-All (OAA) approach. The experimental results demonstrated higher test recognition rates of Gaussian OAA SVMs on random unknown ECG data sets with the use of the Kernel Principal Component Analysis (KPCA) as compared to the use of the Linear Discriminant Analysis (LDA) and Principal Component Analysis (PCA). Elsevier 2016 Article PeerReviewed application/pdf en http://psasir.upm.edu.my/id/eprint/43276/1/ECG%20biometric%20authentication%20based%20on%20non-fiducial%20approach%20using%20kernel%20methods.pdf Hejazi, Maryamsadat and Syed Mohamed, Syed Abdul Rahman Al-Haddad and Singh, Yashwant Prasad and Hashim, Shaiful Jahari and Abdul Aziz, Ahmad Fazli (2016) ECG biometric authentication based on non-fiducial approach using kernel methods. Digital Signal Processing, 52. pp. 72-86. ISSN 1051-2004; ESSN: 1095-4333 http://www.sciencedirect.com/science/article/pii/S1051200416000373 10.1016/j.dsp.2016.02.008
spellingShingle Hejazi, Maryamsadat
Syed Mohamed, Syed Abdul Rahman Al-Haddad
Singh, Yashwant Prasad
Hashim, Shaiful Jahari
Abdul Aziz, Ahmad Fazli
ECG biometric authentication based on non-fiducial approach using kernel methods
title ECG biometric authentication based on non-fiducial approach using kernel methods
title_full ECG biometric authentication based on non-fiducial approach using kernel methods
title_fullStr ECG biometric authentication based on non-fiducial approach using kernel methods
title_full_unstemmed ECG biometric authentication based on non-fiducial approach using kernel methods
title_short ECG biometric authentication based on non-fiducial approach using kernel methods
title_sort ecg biometric authentication based on non fiducial approach using kernel methods
url http://psasir.upm.edu.my/id/eprint/43276/1/ECG%20biometric%20authentication%20based%20on%20non-fiducial%20approach%20using%20kernel%20methods.pdf
work_keys_str_mv AT hejazimaryamsadat ecgbiometricauthenticationbasedonnonfiducialapproachusingkernelmethods
AT syedmohamedsyedabdulrahmanalhaddad ecgbiometricauthenticationbasedonnonfiducialapproachusingkernelmethods
AT singhyashwantprasad ecgbiometricauthenticationbasedonnonfiducialapproachusingkernelmethods
AT hashimshaifuljahari ecgbiometricauthenticationbasedonnonfiducialapproachusingkernelmethods
AT abdulazizahmadfazli ecgbiometricauthenticationbasedonnonfiducialapproachusingkernelmethods