Visually evoked potentials for EEG biometric recognition

Abstract

Electroencephalographs (EEG) signals elicited by means of visual stimuli are highly time-dependent as they vary due to the subject's attention, state of mind, position of electrodes, etc., during acquisition. In this paper we exploit the use of techniques tailored to the analysis of signals varying across time. Specifically, dynamic time warping (DTW) is a technique to find an optimal alignment between two time-dependent series as it successfully copes with the time deformations and different speeds that are associated with time-dependent data, whereas symbolic aggregate approximation (SAX) produces a symbolic representation for a time series and can be used to represent highly time-dependent data in time invariant manner. In this paper we investigate visually evoked potential (VEP)-based EEG signals using DTW and SAX method, in order to analyze the permanence issue of EEG signals by verifying its stability across time.