Individual identification using electrocardiogram morphology

Abstract

The use of electrocardiogram as biometric has raised attention in the last decade and a wide variety of ECG features were explored to verify the feasibility of such a signal. In this work the authors aim to describe a simple template based approach to the electrocardiographic biometric identification using the morphology of individual's heartbeat. The developed algorithm was tested on different recordings made available in the Physionet public database Fantasia: two different sets of heartbeats were extracted from individual recordings one was used for the template building while the second for the tests. The performances of the algorithm are encouraging with a true acceptance rate of 99.4%, however, the procedure needs to be tested on different recordings of the same individual, or during the course of a whole day or physical activity

ECG-Based Subject Identification Using Common Spatial Pattern and SVM

“…In the preprocessing stage, different tasks are executed such as detrending and noise reduction [30][31][32][33][34]. For feature extraction, there are two main feature extraction algorithms that can be used: fiducial-based [12,24,31,[35][36][37][38][39][40] and non-fiducial-based [41][42][43][44][45][46]. In the classification stage, researchers have utilized different classifiers such as k-nearest neighbors (k-NN) algorithm, neural network (NN), random forest, and Support Vector Machine (SVM) [30,31,33,47,48].…”

Biometrics System Technology Trends Based on Bio-signal

“…The average and differential values are extracted as features after setting a section using morphological features [13]. [21], morphological features [22], autocorrelation (AC) [23], and heart rate variability feature values [24] are used. The features in the frequency domain are extracted using discrete wavelet transform (DWT) [25] and wavelet transform [3,18], Mel frequency cepstrum coefficients (MFCC) [17], ensemble empirical mode decomposition (EEMD) [26].…”

Statistical Assessment of Biometrical Signs by Electrocardiography

“…Морфологические признаки несут информацию о форме как всей ЭКГ в целом, так и образующих ее P-QRS-T -интервалов. Самым простым способом выделения таких признаков является усреднение величин, полученных из характерных интервалов кардиоцикла, которые были отцентрированы по R-пикам [5][6][7]. Некоторые исследователи предлагают использовать в качестве биометрических признаков углы наклона между сегментами, например, между сегментами ST и RS [3].…”