Non-fiducial based ECG biometric authentication using one-class support vector machine
Identity recognition encounters with several problems especially in feature extraction and pattern classification. Electrocardiogram (ECG) is a quasi-periodic signal which has highly discriminative characteristics in a population for subject recognition. The personal identity verification in a rando...
| Main Authors: | , , , , |
|---|---|
| Format: | Conference or Workshop Item |
| Language: | English |
| Published: |
IEEE
2017
|
| Online Access: | http://psasir.upm.edu.my/id/eprint/59477/ http://psasir.upm.edu.my/id/eprint/59477/1/Non-fiducial%20based%20ECG%20biometric%20authentication%20using%20one-class%20support%20vector%20machine.pdf |
| _version_ | 1848853932488523776 |
|---|---|
| author | Hejazi, Maryamsadat Syed Mohamed, Syed Abdul Rahman Al-Haddad Hashim, Shaiful Jahari Abdul Aziz, Ahmad Fazli Singh, Yashwant Prasad |
| author_facet | Hejazi, Maryamsadat Syed Mohamed, Syed Abdul Rahman Al-Haddad Hashim, Shaiful Jahari Abdul Aziz, Ahmad Fazli Singh, Yashwant Prasad |
| author_sort | Hejazi, Maryamsadat |
| building | UPM Institutional Repository |
| collection | Online Access |
| description | Identity recognition encounters with several problems especially in feature extraction and pattern classification. Electrocardiogram (ECG) is a quasi-periodic signal which has highly discriminative characteristics in a population for subject recognition. The personal identity verification in a random population using kernel-based binary and one-class Support Vector Machines (SVMs) has been considered by other biometric traits, but has been so far left aside for analysis of ECG signals. This paper investigates the effect of different parameters of data set size, labeling data, configuration of training and testing data sets, feature extraction, different recording sessions, and random partition methods on accuracy and error rates of these SVM classifiers. The experiments were carried out with defining a number of scenarios on ECG data sets designed rely on feature extractors which were modeled based on an autocorrelation in conjunction with linear and nonlinear dimension reduction methods. The experimental results show that Kernel Principal Component Analysis has lower error rate in binary and one-class SVMs on random unknown ECG data sets. Moreover, one-class SVM can be robust recognition algorithm for ECG biometric verification if the sufficient number of biometric samples is available. |
| first_indexed | 2025-11-15T11:01:50Z |
| format | Conference or Workshop Item |
| id | upm-59477 |
| institution | Universiti Putra Malaysia |
| institution_category | Local University |
| language | English |
| last_indexed | 2025-11-15T11:01:50Z |
| publishDate | 2017 |
| publisher | IEEE |
| recordtype | eprints |
| repository_type | Digital Repository |
| spelling | upm-594772018-03-07T01:35:01Z http://psasir.upm.edu.my/id/eprint/59477/ Non-fiducial based ECG biometric authentication using one-class support vector machine Hejazi, Maryamsadat Syed Mohamed, Syed Abdul Rahman Al-Haddad Hashim, Shaiful Jahari Abdul Aziz, Ahmad Fazli Singh, Yashwant Prasad Identity recognition encounters with several problems especially in feature extraction and pattern classification. Electrocardiogram (ECG) is a quasi-periodic signal which has highly discriminative characteristics in a population for subject recognition. The personal identity verification in a random population using kernel-based binary and one-class Support Vector Machines (SVMs) has been considered by other biometric traits, but has been so far left aside for analysis of ECG signals. This paper investigates the effect of different parameters of data set size, labeling data, configuration of training and testing data sets, feature extraction, different recording sessions, and random partition methods on accuracy and error rates of these SVM classifiers. The experiments were carried out with defining a number of scenarios on ECG data sets designed rely on feature extractors which were modeled based on an autocorrelation in conjunction with linear and nonlinear dimension reduction methods. The experimental results show that Kernel Principal Component Analysis has lower error rate in binary and one-class SVMs on random unknown ECG data sets. Moreover, one-class SVM can be robust recognition algorithm for ECG biometric verification if the sufficient number of biometric samples is available. IEEE 2017 Conference or Workshop Item PeerReviewed text en http://psasir.upm.edu.my/id/eprint/59477/1/Non-fiducial%20based%20ECG%20biometric%20authentication%20using%20one-class%20support%20vector%20machine.pdf Hejazi, Maryamsadat and Syed Mohamed, Syed Abdul Rahman Al-Haddad and Hashim, Shaiful Jahari and Abdul Aziz, Ahmad Fazli and Singh, Yashwant Prasad (2017) Non-fiducial based ECG biometric authentication using one-class support vector machine. In: Signal Processing: Algorithms, Architectures, Arrangements, and Applications (SPA 2017), 20-22 Sept. 2017, Poznan, Poland. (pp. 190-194). 10.23919/SPA.2017.8166862 |
| spellingShingle | Hejazi, Maryamsadat Syed Mohamed, Syed Abdul Rahman Al-Haddad Hashim, Shaiful Jahari Abdul Aziz, Ahmad Fazli Singh, Yashwant Prasad Non-fiducial based ECG biometric authentication using one-class support vector machine |
| title | Non-fiducial based ECG biometric authentication using one-class support vector machine |
| title_full | Non-fiducial based ECG biometric authentication using one-class support vector machine |
| title_fullStr | Non-fiducial based ECG biometric authentication using one-class support vector machine |
| title_full_unstemmed | Non-fiducial based ECG biometric authentication using one-class support vector machine |
| title_short | Non-fiducial based ECG biometric authentication using one-class support vector machine |
| title_sort | non-fiducial based ecg biometric authentication using one-class support vector machine |
| url | http://psasir.upm.edu.my/id/eprint/59477/ http://psasir.upm.edu.my/id/eprint/59477/ http://psasir.upm.edu.my/id/eprint/59477/1/Non-fiducial%20based%20ECG%20biometric%20authentication%20using%20one-class%20support%20vector%20machine.pdf |