Image-Evoked Affect and its Impact on Eeg-Based Biometrics

Abstract

Electroencephalography (EEG) signals provide a representation of the brain's activity patterns and have been recently exploited for user identification and authentication due to their uniqueness and their robustness to interception and artificial replication. Nevertheless, such signals are commonly affected by the individual's emotional state. In this work, we examine the use of images as stimulus for acquiring EEG signals and study whether the use of images that evoke similar emotional responses leads to higher identification accuracy compared to images that evoke different emotional responses. Results show that identification accuracy increases when the system is trained with EEG recordings that refer to similar emotional states as the EEG recordings that are used for identification, demonstrating an up to 5.3% increase on identification accuracy compared to when recordings referring to different emotional states are used. Furthermore, this improvement holds independently of the features and classification algorithms employed.

BED: A New Data Set for EEG-Based Biometrics

“…This repository contains three sessions separated in time, considers a wide set of stimuli and has been produced by using a low-cost off-the-shelf EEG recording device. In addition, and as a consequence of recently published studies that report further gains when the emotional state is taken into account [8], [9], [33], we have also considered image-based stimuli that were specifically selected to elicit a set of representative emotional responses. This section describes the specific characteristics of this dataset.…”

“…This has led many authors to create proprietary datasets, designed according to their particular experimental setting [17], [18], [22], [23], [24], [25], [26], [27], [28], [29], [30]. Other authors have used public EEG datasets that were originally designed for purposes other than biometrics [8], [31], [32], [33]. This includes the one by UCI (University of California, Irvine) [34] and VEP (Visual Evoked Potentials) [35], which were initially conceived for image speech and alcoholism detection, respectively; or DEAP [36], MAHNOB-HCI [37], DREAMER [38], SEED [39], and the Lakhan et al [40] datasets, which were constructed with emotion recognition in mind.…”