Learning deep features for task-independent EEG-based biometric verification

• Published in: Pattern recognition letters Vol. 143; pp. 122 - 129
• Main Author: Maiorana, Emanuele
• Format: Journal Article
• Language: English
• Published: Amsterdam Elsevier B.V 01.03.2021; Elsevier Science Ltd
• Subjects: Artificial neural networks; Biometrics; Brain; Cognitive tasks; Data acquisition; Deep Learning; EEG; Electroencephalography; Feasibility studies; Neural networks; Recognition; Biometrics; 68T10; Electroencephalography; 68T07; Deep Learning
• ISSN: 0167-8655; 1872-7344
• DOI: 10.1016/j.patrec.2021.01.004

•The feasibility of doing task-independent EEG-based biometric recognition is evaluated.•Siamese training is employed to force CNNs learning task-independent EEG characteristics.•Different EEG channels separately modeled to learn features specific of each brain area.•EEG signals compared at short and long time distances between enrolment and verification.•Analysis of performance achievable with reduced number of channels to improve usability. Considerable interest has been recently devoted to the exploitation of brain activity as biometric identifier in automatic recognition systems, with a major focus on data acquired through electroencephalography (EEG). Several researches have in fact confirmed the presence of discriminative characteristics within brain signals recorded while performing specific mental tasks. Yet, to make EEG-based recognition appealing for practical applications, it would be highly advisable to investigate the existence and permanence of such distinctive traits while performing different mental tasks. In this regard, the present study evaluates the feasibility of performing task-independent EEG-based biometric recognition. A deep learning approach using siamese convolutional neural networks is employed to extract, from the considered EEG recordings, subject-specific template representations. An extensive set of experimental tests, performed on a multi-session database comprising EEG data acquired from 45 subjects while performing six different tasks, is employed to evaluate whether it is actually possible to verify the identity of a subject using brain signals, regardless the performed mental task.