Recurrence Quantification Analysis for PPG/ECG-Based Subject Authentication

Nowadays, the internet is used by billions of users around the world for many different purposes, some of which require user identity authentication. To face the challenge of reliable authentication, researchers have proposed various techniques, ranging from face recognition to fingerprints. The aim...

Full description

Saved in:
Bibliographic Details
Published in2022 4th International Conference on Data Intelligence and Security (ICDIS) pp. 288 - 291
Main Authors Alotaiby, Turkey N., Alshebeili, Saleh A., Alotibi, Gaseb, Alotaibi, Ghaith N.
Format Conference Proceeding
LanguageEnglish
Published IEEE 01.08.2022
Subjects
Authentication
Electrocardiography
Face recognition
Feature extraction
Fingerprint recognition
Linear discriminant analysis
PPG and ECG
Support vector machines
Online AccessGet full text

Cover

More Information
Summary:Nowadays, the internet is used by billions of users around the world for many different purposes, some of which require user identity authentication. To face the challenge of reliable authentication, researchers have proposed various techniques, ranging from face recognition to fingerprints. The aim of this study is to develop a PPG/ECG-based (Photoplethysmography/Electrocardiogram) user identity authentication approach using features extracted by recurrence quantification analysis (RQA). The PPG/ECG signal is segmented into frames and thirteen features are obtained using RQA. These features are then fed into four classifiers for user identity authentication purposes: linear discriminant analysis, support vector machine, naïve Bayes, and random forest. The best result obtained using this methodology is an average accuracy of 99.48% achieved using a random forest classifier with frame length of three seconds.
DOI:10.1109/ICDIS55630.2022.00051