Development of Heartbeat Based Biometric System Using Wavelet Transform

Electrocardiogram (ECG) is a new biometric trait that has an advantage as it is an internal modality which indicates to be difficult of counterfeiting. The ECG records the heart activity and it is unique as different individuals have distinct heart structure. Hence, it provides vital information for differentiating one individual from another. One of the techniques to extract the salient information from the ECG signal is by using discrete wavelet transform (DWT). However, in order to develop a reliable ECG based biometric system using DWT, there are many parameters that need to be determined. In this study, we study the effect of different parameters used for de-noising orders, threshold levels and type of mother wavelets to the final authentication performance of our developed system. For the authentication stage, Support Vector Machine (SVM) is used as classifier. The system performance is evaluated based on Genuine Acceptance Rate (GAR), False Acceptance Rate (FAR) and Equal Error Rate (EER) by using the scores given by the SVM. The combination of de-noising order 3, heursure threshold method and db6 mother wavelet yields the top performance with GAR of 92.5% at FAR of 5% and EER of 6.9499% have been achieved. At the end of this paper, a simple ECG based security system is then constructed so as to show the feasibility of this study to be implemented in real-time situation.

[1]  P. Deepa Shenoy,et al.  Heartbeat biometrics for human authentication , 2011, Signal Image Video Process..

[2]  Robert Plonsey,et al.  Bioelectromagnetism: Principles and Applications of Bioelectric and Biomagnetic Fields , 1995 .

[3]  Jeffrey M. Hausdorff,et al.  Physionet: Components of a New Research Resource for Complex Physiologic Signals". Circu-lation Vol , 2000 .

[4]  K. J. Chee,et al.  Development of Heartbeat Detection Kit for Biometric Authentication System , 2016, KES.

[5]  A. Uchiyama,et al.  Development of an ECG identification system , 2001, 2001 Conference Proceedings of the 23rd Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[6]  Noureddine Belgacem,et al.  ECG Based Human Authentication using Wavelets and Random Forests , 2012 .

[7]  L. O'Gorman,et al.  Comparing passwords, tokens, and biometrics for user authentication , 2003, Proceedings of the IEEE.

[8]  D. Hatzinakos,et al.  ECG Biometric Recognition Without Fiducial Detection , 2006, 2006 Biometrics Symposium: Special Session on Research at the Biometric Consortium Conference.

[9]  Ajita Rattani.  Introduction to Adaptive Biometric Systems , 2015 .

[10]  Liqing Zhang,et al.  ECG Feature Extraction and Classification Using Wavelet Transform and Support Vector Machines , 2005, 2005 International Conference on Neural Networks and Brain.

[11]  J. Koseeyaporn,et al.  Human Identification System Based ECG Signal , 2005, TENCON 2005 - 2005 IEEE Region 10 Conference.

[12]  Chih-Yu Hsu,et al.  A Novel Personal Identity Verification Approach Using a Discrete Wavelet Transform of the ECG Signal , 2008, 2008 International Conference on Multimedia and Ubiquitous Engineering (mue 2008).

[13]  Nadine Eberhardt,et al.  Bioelectrical Signal Processing In Cardiac And Neurological Applications , 2016 .