Systems, Man & Cybernetics - October 2017 - 9

EEG-Based Biometrics
and feature extraction. The data
State of the Art
acquisition stage records raw EEG
In any experimental
EEG measures the electrical activisignals by placing electrodes on
ty of millions of neurons within the
the scalp of subjects [16]. Preproprotocol adopted
brain, and the amplitude of its
cessing removes artifacts from the
for EEGBS, the
potential varies between 10 and
collected EEG. The feature extrac200 μV. Generally, EEG's information module withdraws salient
proper selection
tive features lie within the frequenand informative features to generof discriminative
cy range of 0.5-45 Hz, composed of
ate a subject-specific distinct EEG
EEG features is a
delta (0.5-4 Hz), theta (4-8 Hz),
template. Finally, these templates
alpha (8-12 Hz), beta (12-30 Hz),
are stored in the database against
crucial determinant
and gamma (>30 Hz) bands [16],
each subject. The generated temin identification
[18]. Many studies have explored
plates during enrollment form the
EEG patterns associated with varibackbone of success for any bioor authentication
ous brain activations to retrieve
metric recognition system. After
success rates.
subject-dependent characteristics.
generating secure templates, live
The protocol used in the experiEEG patterns ob--tained during
mental design for producing speidentification or authentication
cific brain patterns determines the
modes are compiled into represenfruitfulness of any EEGBS because it greatly impacts the
tative feature vectors that are then compared with the
reliability and distinctiveness of the features generated.
stored templates [11], [18].
Three types of brain activation patterns are mainly
explored in existing EEGBS studies, and they are generatAuthentication Mode
ed when the subject
Authentication of any biometric system requires a
claimed identity from an individual. The claimed per1)	 relaxes with closed/open eyes
son's unique identity number and extracted EEG feature
2)	 responds to visual stimuli
vector (query template) are then matched with the
3)	 performs a set of mental tasks (imagined speech, imagirespective enrolled template in the database. As seen in
nary rotation of three-dimensional objects, counting,
Figure 1, the verification process performs only one-toand mental computation, among others).
one matching, because the query template must be comA detailed review of various biometric systems using difpared with the respective identity only. The verification
ferent protocols up until 2013 can be found in [18]. The folsystem accepts the claimed person as a client or rejects
lowing subsections provide a brief overview of these
him or her as an imposter based on the computed
paradigms and focus on developments since 2013.
matching score [18].
Resting-State EEG
Identification Mode
The resting state with eyes closed (REC) and eyes open
(REO) are the most commonly used protocols in brainUnlike in authentication, a claimed identity is not required
wave-based recognition systems [10], [18]. They are easy
in identification. For a given query template, all stored
to use and comfortable. During this state, alpha waves are
templates in the database are processed to find the best
manifest by a peak frequency of 10 Hz and reported to be
possible match, as shown in Figure 1. In both identification
highly distinctive in subject-specific neurophysiological
and verification modes, data acquisition, preprocessing,
analysis. Most of the existing EEGBS studies based on
and feature exaction modules function in a similar manREO or REC depend on features extracted from alphaner, but there is a small difference in the matching module.
band EEG or from a wider band of 0.5-45 Hz, using feature
In the identification system, the purpose is to determine
extraction techniques such as power spectral density
the top k similar subjects from the database of size D,
(PSD) estimation, autoregressive (AR) models, functional
where k ≤ D, and k is considered to be the rank of the subconnectivity analysis, wavelet transformation, Burg's
group. The rate at which the genuine subject's template
reflection coefficients, and bump modeling. Extracted feaappears as the best match (rank-1 match) based on the
tures are then classified by simple threshold selection promatching score is termed the correct recognition rate
cedures or machine -lea r ning /patter n-recognition
(CRR), and it is a frequently used performance measure in
algorithms [10].
identification. For verification, the performance accuraSince 1999, more than a dozen studies have investigated
cies are generally expressed in terms of false acceptance
the effectiveness of resting-state brain activity [19]-[25],
rate, false rejection rate (FRR), genuine acceptance rate,
and, among these, the best reported identification accuraequal error rate (EER), and half-total error rate (HTER)
cy was described in a recent work published in 2014, which
[11]. In a robust system, CRR is high, whereas error rates
achieved a CRR of 100% using a database of 108 subjects
are as low as possible.
	

O c tob e r 2017

IEEE SYSTEMS, MAN, & CYBERNETICS MAGAZINE	

9



Table of Contents for the Digital Edition of Systems, Man & Cybernetics - October 2017

Systems, Man & Cybernetics - October 2017 - Cover1
Systems, Man & Cybernetics - October 2017 - Cover2
Systems, Man & Cybernetics - October 2017 - 1
Systems, Man & Cybernetics - October 2017 - 2
Systems, Man & Cybernetics - October 2017 - 3
Systems, Man & Cybernetics - October 2017 - 4
Systems, Man & Cybernetics - October 2017 - 5
Systems, Man & Cybernetics - October 2017 - 6
Systems, Man & Cybernetics - October 2017 - 7
Systems, Man & Cybernetics - October 2017 - 8
Systems, Man & Cybernetics - October 2017 - 9
Systems, Man & Cybernetics - October 2017 - 10
Systems, Man & Cybernetics - October 2017 - 11
Systems, Man & Cybernetics - October 2017 - 12
Systems, Man & Cybernetics - October 2017 - 13
Systems, Man & Cybernetics - October 2017 - 14
Systems, Man & Cybernetics - October 2017 - 15
Systems, Man & Cybernetics - October 2017 - 16
Systems, Man & Cybernetics - October 2017 - 17
Systems, Man & Cybernetics - October 2017 - 18
Systems, Man & Cybernetics - October 2017 - 19
Systems, Man & Cybernetics - October 2017 - 20
Systems, Man & Cybernetics - October 2017 - 21
Systems, Man & Cybernetics - October 2017 - 22
Systems, Man & Cybernetics - October 2017 - 23
Systems, Man & Cybernetics - October 2017 - 24
Systems, Man & Cybernetics - October 2017 - 25
Systems, Man & Cybernetics - October 2017 - 26
Systems, Man & Cybernetics - October 2017 - 27
Systems, Man & Cybernetics - October 2017 - 28
Systems, Man & Cybernetics - October 2017 - 29
Systems, Man & Cybernetics - October 2017 - 30
Systems, Man & Cybernetics - October 2017 - 31
Systems, Man & Cybernetics - October 2017 - 32
Systems, Man & Cybernetics - October 2017 - 33
Systems, Man & Cybernetics - October 2017 - 34
Systems, Man & Cybernetics - October 2017 - 35
Systems, Man & Cybernetics - October 2017 - 36
Systems, Man & Cybernetics - October 2017 - 37
Systems, Man & Cybernetics - October 2017 - 38
Systems, Man & Cybernetics - October 2017 - 39
Systems, Man & Cybernetics - October 2017 - 40
Systems, Man & Cybernetics - October 2017 - 41
Systems, Man & Cybernetics - October 2017 - 42
Systems, Man & Cybernetics - October 2017 - 43
Systems, Man & Cybernetics - October 2017 - 44
Systems, Man & Cybernetics - October 2017 - Cover3
Systems, Man & Cybernetics - October 2017 - Cover4
https://www.nxtbook.com/nxtbooks/ieee/smc_202310
https://www.nxtbook.com/nxtbooks/ieee/smc_202307
https://www.nxtbook.com/nxtbooks/ieee/smc_202304
https://www.nxtbook.com/nxtbooks/ieee/smc_202301
https://www.nxtbook.com/nxtbooks/ieee/smc_202210
https://www.nxtbook.com/nxtbooks/ieee/smc_202207
https://www.nxtbook.com/nxtbooks/ieee/smc_202204
https://www.nxtbook.com/nxtbooks/ieee/smc_202201
https://www.nxtbook.com/nxtbooks/ieee/smc_202110
https://www.nxtbook.com/nxtbooks/ieee/smc_202107
https://www.nxtbook.com/nxtbooks/ieee/smc_202104
https://www.nxtbook.com/nxtbooks/ieee/smc_202101
https://www.nxtbook.com/nxtbooks/ieee/smc_202010
https://www.nxtbook.com/nxtbooks/ieee/smc_202007
https://www.nxtbook.com/nxtbooks/ieee/smc_202004
https://www.nxtbook.com/nxtbooks/ieee/smc_202001
https://www.nxtbook.com/nxtbooks/ieee/smc_201910
https://www.nxtbook.com/nxtbooks/ieee/smc_201907
https://www.nxtbook.com/nxtbooks/ieee/smc_201904
https://www.nxtbook.com/nxtbooks/ieee/smc_201901
https://www.nxtbook.com/nxtbooks/ieee/smc_201810
https://www.nxtbook.com/nxtbooks/ieee/smc_201807
https://www.nxtbook.com/nxtbooks/ieee/smc_201804
https://www.nxtbook.com/nxtbooks/ieee/smc_201801
https://www.nxtbook.com/nxtbooks/ieee/systems_man_cybernetics_1017
https://www.nxtbook.com/nxtbooks/ieee/systems_man_cybernetics_0717
https://www.nxtbook.com/nxtbooks/ieee/systems_man_cybernetics_0417
https://www.nxtbook.com/nxtbooks/ieee/systems_man_cybernetics_0117
https://www.nxtbook.com/nxtbooks/ieee/systems_man_cybernetics_1016
https://www.nxtbook.com/nxtbooks/ieee/systems_man_cybernetics_0716
https://www.nxtbook.com/nxtbooks/ieee/systems_man_cybernetics_0416
https://www.nxtbook.com/nxtbooks/ieee/systems_man_cybernetics_0116
https://www.nxtbook.com/nxtbooks/ieee/systems_man_cybernetics_1015
https://www.nxtbook.com/nxtbooks/ieee/systems_man_cybernetics_0715
https://www.nxtbook.com/nxtbooks/ieee/systems_man_cybernetics_0415
https://www.nxtbook.com/nxtbooks/ieee/systems_man_cybernetics_0115
https://www.nxtbookmedia.com