ECG based human authentication with using Generalized Hurst Exponent

Using the ECG as a biometric trait provides significant advantages such as universality, uniqueness, robustness to attacks, liveness detection, continuous authentication and etc. The chaotic behavior of ECG has been proven in the studies and nonlinear methods have been applied to study the nonlinear properties of this signal. In this paper we apply four different nonlinear Methods, Rescaled Range Analysis (RSA), Higuchi's Fractal Dimension (HFD), Detrended Fluctuation Analysis (DFA) and Generalized Hurst Exponent (GHE) to extract features for authentication system. Support Vector Machine is used to classify the fractal feature together with some fiducial features. The proposed approach has been tested using 18 different subjects ECG signal of MIT-BIH Normal Sinus Rhythm Database. The obtained results show that the authentication accuracy is 99.06±0.26%.