Session Invariant EEG Signatures using Elicitation Protocol Fusion and Convolutional Neural Network

Debie, E; Moustafa, N; Vasilakos, A

Session Invariant EEG Signatures using Elicitation Protocol Fusion and Convolutional Neural Network

Debie, E Moustafa, N Vasilakos, A

Permalink

Publisher:: Institute of Electrical and Electronics Engineers (IEEE)
Publication Type:: Journal Article
Citation:: IEEE Transactions on Dependable and Secure Computing, 2022, 19, (4), pp. 2488-2500
Issue Date:: 2022-01-01

Closed Access

	Filename	Description	Size
	Session_Invariant_EEG_Signatures_using_Elicitation_Protocol_Fusion_and_Convolutional_Neural_Network.pdf	Published version	1.82 MB	Adobe PDF	View/Open

Copyright Clearance Process

Recently Added
In Progress
Closed Access

This item is closed access and not available.

Full metadata record

Field	Value	Language
dc.contributor.author	Debie, E
dc.contributor.author	Moustafa, N
dc.contributor.author	Vasilakos, A https://orcid.org/0000-0003-1902-9877
dc.date.accessioned	2023-04-05T02:06:26Z
dc.date.available	2023-04-05T02:06:26Z
dc.date.issued	2022-01-01
dc.identifier.citation	IEEE Transactions on Dependable and Secure Computing, 2022, 19, (4), pp. 2488-2500
dc.identifier.issn	1545-5971
dc.identifier.issn	1941-0018
dc.identifier.uri	http://hdl.handle.net/10453/169145
dc.description.abstract	Brain signals are potential biometric markers in user authentication, complementing existing biometric authentication techniques (such as those based on fingerprint, iris and facial recognition). This paper proposes a novel EEG fusion method to examine the reliability and durability of EEG biometric markers across recording sessions. Our hypothesis is that models trained using EEG signals collected during various elicitation protocols can capture generalised brain patterns that pertain personalised information which can improve the durability of biometric systems. Different protocols are likely to produce different responses across brain regions, which can result in more identifiable responses from EEG. In our approach, an end-to-end convolutional neural network (CNN) model is adopted for feature extraction and classification of raw EEG data. The proposed method is evaluated on two EEG datasets which were collected over two separate sessions on different days using multiple different EEG elicitation protocols. Within-session and across-session experiments were conducted. Results for within session experiments showed that CNN models with protocol fusion can achieve similar if not better results than models trained with single protocol. In across-session scenarios, models trained with the proposed protocol fusion approach significantly outperformed single protocol based models. The obtained results illustrate the durability and reliability capabilities of the proposed fusion approach
dc.language	en
dc.publisher	Institute of Electrical and Electronics Engineers (IEEE)
dc.relation.ispartof	IEEE Transactions on Dependable and Secure Computing
dc.relation.isbasedon	10.1109/TDSC.2021.3060775
dc.rights	info:eu-repo/semantics/closedAccess
dc.subject	0803 Computer Software, 0804 Data Format, 0805 Distributed Computing
dc.subject.classification	Strategic, Defence & Security Studies
dc.title	Session Invariant EEG Signatures using Elicitation Protocol Fusion and Convolutional Neural Network
dc.type	Journal Article
utslib.citation.volume	19
utslib.for	0803 Computer Software
utslib.for	0804 Data Format
utslib.for	0805 Distributed Computing
pubs.organisational-group	/University of Technology Sydney
pubs.organisational-group	/University of Technology Sydney/Faculty of Engineering and Information Technology
pubs.organisational-group	/University of Technology Sydney/Faculty of Engineering and Information Technology/School of Electrical and Data Engineering
utslib.copyright.status	closed_access	*
pubs.consider-herdc	false
dc.date.updated	2023-04-05T02:06:22Z
pubs.issue	4
pubs.publication-status	Published
pubs.volume	19
utslib.citation.issue	4

Abstract:

Brain signals are potential biometric markers in user authentication, complementing existing biometric authentication techniques (such as those based on fingerprint, iris and facial recognition). This paper proposes a novel EEG fusion method to examine the reliability and durability of EEG biometric markers across recording sessions. Our hypothesis is that models trained using EEG signals collected during various elicitation protocols can capture generalised brain patterns that pertain personalised information which can improve the durability of biometric systems. Different protocols are likely to produce different responses across brain regions, which can result in more identifiable responses from EEG. In our approach, an end-to-end convolutional neural network (CNN) model is adopted for feature extraction and classification of raw EEG data. The proposed method is evaluated on two EEG datasets which were collected over two separate sessions on different days using multiple different EEG elicitation protocols. Within-session and across-session experiments were conducted. Results for within session experiments showed that CNN models with protocol fusion can achieve similar if not better results than models trained with single protocol. In across-session scenarios, models trained with the proposed protocol fusion approach significantly outperformed single protocol based models. The obtained results illustrate the durability and reliability capabilities of the proposed fusion approach

Please use this identifier to cite or link to this item:

http://hdl.handle.net/10453/169145