ECG BASED HUMAN AUTHENTICATION USING WAVELETS AND RANDOM FORESTS
ECG BASED HUMAN AUTHENTICATION USING WAVELETS AND RANDOM
FORESTS
Noureddine Belgacem1 , Amine Nait-Ali2
, Régis Fournier2 and Fethi Bereksi-Reguig1
1Biomedical
Engineering Laboratory, Abou Bekr Belkaid University, Tlemcen, Algeria.2 Images Signals and Intelligent Systems
Laboratory, UPEC University, France
ABSTRACT
The electrocardiogram (ECG) is an emerging novel biometric for human identification. It can be combined
in a multi-modal biometric identification system or used alone for authentication of subjects. His primary
application can be in health care systems where the ECG is used for health measurements. It does
furthermore, better than any other biometrics measures, deliver the proof of subject’s being alive as extra
information which other biometrics cannot deliver as easily. The main purpose of this study is to present a
novel personal authentication approach for human authentication based on their ECG signals. We present
a methodology for identity verification that quantifies the minimum number of heartbeats required to
authenticate an enrolled individual. The cardiac signals were used to identify a total of 80 individuals
obtained from four ECG databases from the Physionet database (MIT-BIH, ST-T, NSR, PTB) and an ECG
database collected from 20 student volunteers from Paris Est University. Feature extraction was performed
by using Discrete Wavelet Transform (DWT). Wavelets have proved particularly effective for extracting
discriminative features in ECG signal classification. The Random Forest was then presented for the ECG
signals authentication. Preliminary experimental results indicate that the system is accurate and can
achieve a low false negative rate, low false positive rate and a 100% subject recognition rate for healthy
subjects with the reduced set of features.
KEYWORDS
ECG; human authentication; wavelet decomposition; random forests.
Source URL
VOLUME LINK
Comments
Post a Comment