c o m p u t e r m e t h o d s a n d p r o g r a m s i n b i o m e d i c i n e 1 2 1 ( 2 0 1 5 ) 127–136 jo ur nal ho me p ag e: www.intl.elsevierhealt h.com/journals/cmpb Subject identification via ECG fiducial-based systems: Influence of the type of QT interval correction Francesco Gargiulo a , Antonio Fratini b , Mario Sansone a , Carlo Sansone a,∗ a University of Naples Federico II, Department of Electrical Engineering and Information Technologies, via Claudio 21, 80125 Naples, Italy b Aston University, School of Life and Health Sciences, Aston Triangle, B4 7ET Birmingham, United Kingdom a r t i c l e i n f o Article history: Received 21 September 2014 Received in revised form 20 May 2015 Accepted 28 May 2015 Keywords: Electrocardiogram QT interval correction Biometrics identification systems Classification a b s t r a c t Electrocardiography (ECG) has been recently proposed as biometric trait for identification purposes. Intra-individual variations of ECG might affect identification performance. These variations are mainly due to Heart Rate Variability (HRV). In particular, HRV causes changes in the QT intervals along the ECG waveforms. This work is aimed at analysing the influence of seven QT interval correction methods (based on population models) on the performance of ECG-fiducial-based identification systems. In addition, we have also considered the influ- ence of training set size, classifier, classifier ensemble as well as the number of consecutive heartbeats in a majority voting scheme. The ECG signals used in this study were collected from thirty-nine subjects within the Physionet open access database. Public domain soft- ware was used for fiducial points detection. Results suggested that QT correction is indeed required to improve the performance. However, there is no clear choice among the seven explored approaches for QT correction (identification rate between 0.97 and 0.99). MultiLayer Perceptron and Support Vector Machine seemed to have better generalization capabilities, in terms of classification performance, with respect to Decision Tree-based classifiers. No such strong influence of the training-set size and the number of consecutive heartbeats has been observed on the majority voting scheme. © 2015 Elsevier Ireland Ltd. All rights reserved. 1. Introduction During the past decades, the feasibility bio-medical signals, such as electroencephalography, heart-rate variability, blood pressure and pulse oximetry, for subject identification [1] was studied. The idea of using electrocardiography (ECG) for iden- tification purposes is however recent [2,3]. ∗ Corresponding author. Tel.: +39 0817683640; fax: +39 0812531726. E-mail addresses: a.fratini@aston.ac.uk (A. Fratini), carlosan@unina.it (C. Sansone). As well known, a proper biometric should posses peculiar characteristics such as uniqueness, permanence, universality and collectability and ECG shows these particularities. Hoekema et al. [4] highlighted the uniqueness of ECG signal on the basis of geometrical and physiological factors. Wuebbeler et al. [5] revealed its permanence by observing similarities of healthy subjects’ ECG data gathered repetitively during several years. ECG can be easily collected from the whole population http://dx.doi.org/10.1016/j.cmpb.2015.05.012 0169-2607/© 2015 Elsevier Ireland Ltd. All rights reserved.