Influence of QT correction on temporal and amplitude features for human identification via ECG

Author

Sansone, M. ; Fratini, A. ; Cesarelli, M. ; Bifulco, P. ; Pepino, A. ; Romano, M. ; Gargiulo, F. ; Sansone, Carlo

Author_Institution

Dept. of Electr. Eng. & Inf. Technol., Univ. Federico II of Naples, Naples, Italy

fYear

2013

fDate

9-9 Sept. 2013

Firstpage

22

Lastpage

27

Abstract

Identification of humans via ECG is being increasingly studied because it can have several advantages over the traditional biometric identification techniques. However, difficulties arise because of the heartrate variability. In this study we analysed the influence of QT interval correction on the performance of an identification system based on temporal and amplitude features of ECG. In particular we tested MLP, Naive Bayes and 3-NN classifiers on the Fantasia database. Results indicate that QT correction can significantly improve the overall system performance.

Keywords

Bayes methods; database management systems; electrocardiography; feature extraction; multilayer perceptrons; signal classification; 3-NN classifier; 3-nearest neighbour classifiers; ECG; Fantasia database; MLP; Naive Bayes classifier; QT interval correction; amplitude feature; heartrate variability; human identification system; multilayer perceptron classifier; temporal feature; Databases; Electrocardiography; Feature extraction; Heart beat; Heart rate variability;

fLanguage

English

Publisher

ieee

Conference_Titel

Biometric Measurements and Systems for Security and Medical Applications (BIOMS), 2013 IEEE Workshop on

Conference_Location

Naples

Print_ISBN

978-1-4799-0625-3

Type

conf

DOI

10.1109/BIOMS.2013.6656144

Filename

6656144