Systems, Man & Cybernetics - October 2017 - 10

[19]. This is one of the largest studies reported while using
both REO and REC. In this article, conventional PSD and
functional connectivity features extracted from 56 EEG
channels were fused together to achieve better results
than those that were state of art at the time. The same data
set has been used in an authentication mode with eigenvector centrality features extracted from the gamma band
(30-50 Hz), which reports an EER of 4.4% [21]. Both of
these methods report higher accuracy at the expense of
complex methods.
Another study [23] investigates the effectiveness of projecting PSD values (4-30 Hz) extracted from 19 EEG channels into eigenspace, where the compact representations
of EEG spectral characteristics provide an accuracy of
83.9%. The work in [46] proposes the detection of distinctive functional fingerprints (core subnetwork) of the phase
lag-index to help in elucidating crucial mechanisms related
to subject-specific EEG traits. Methods based on blind
source separation and sample entropy estimation are also
investigated in [48] using an extensive set of experimental
tests, which were performed over a large database comprising recordings taken from 50 healthy subjects during three
distinct sessions spanning a period of approximately one
month, in both REO and REC conditions. Using 19 EEG
channels, the highest recognition rate reported is 95% in
the case of REC EEG acquisition protocol. However, further analysis on its feasibility and stability is unreported.
Table 1 summarizes the main articles published with the
most recent developments since 2013.
Although reasonable biometric results have been
reported in REC/REO paradigms in the past, their intersession stability has been tested in only a few studies. A
database containing EEG signals taken from ten subjects in five sessions during two weeks was evaluated in
[24]. Though another recent study has analyzed the stability of REC/REO in a data set of 50 subjects during oneand-a-half months [25], extensive stability analyses with
larger data sets during longer periods of time are yet to
be carried out.

Visually Evoked Potentials
A potential obstacle when using the resting-state EEG
data for biometrics recognition may be the ambiguity of
the instruction due to a lack of stimuli. As a result, a large
number of EEGBS studies focus on visually evoked
potentials (VEPs) [26], [27]. VEPs represent subjects'
time-locked reaction to the presentation of a visual stimuli during EEG. Visual stimuli may comprise different
components, such as color, texture, motion, objects, readability (text versus nontext), and others. Each of these
components has an impact in the spatial, temporal, and
spectral domains of EEG. Most of the studies use visualstimulus-containing images of objects chosen from the
Snodgrass and Vanderwart public data set [28], which
includes images of black and white line drawings. During
the recording session, subjects are asked to remember
and recognize a stimulus for a fixed period of time. Of the
fewer than ten reported studies using the same image set,
the best recognition accuracy that was achieved was
99%, and this involved 20 subjects and features extracted
from 61 EEG channels [26]-[33].
To examine the stability of VEP related to text reading
as a biometric, eight subjects during an intersession temporal distance of six months were studied [31]. The
reported CRR was 82-97%. Another approach has been
proposed for creating enrollment and recognition data
sets [33], where EEG differences between responses to
self-face and non-self-face images were exploited to discriminate among ten subjects, and the authors reported
an average CRR of 86.1%. Generic VEPs and visual eventrelated potentials in response to visual stimuli of geometric figures, letters, and images were evaluated in [32] and
[49]. The study described in [32] reported an average EER
of 15% using 17 channels. These authors also investigated
the permanence issue of the considered EEG traits during
approximately a few weeks by verifying the stability of
the achievable recognition rates. The experimental tests
performed during three different sessions on a database
that included 50 subjects produced evidence of the

Table 1. Biometric systems using resting-state EEG patterns.

10	

Reference/Year/Protocol

Channels

Number of
-Subjects

[47], 2013, REC

3

[19], 2014, REC/REO

Methodology

Performance

36

Bump modeling
(0.5-30 Hz)

CRR = 99.69%

56

108

Spectral coherence-based connectivity (low pass at 50 Hz)

CRR = 75.8-100%

[21], 2015, REO

64

109

Eigenvector centrality

EER = 4.4%

[46], 2016, REO/REC

64

109

Phase-lag index

EER = 13%

[48], 2016, REC/REO

19

50

Blind source separation and
sample entropy

CRR = 95%

[25], 2016, REC/REO

19

50

AR + PSD

CRR = 80-90%

IEEE SYSTEMS, MAN, & CYBERNETICS MAGAZINE Oc tob e r 2017



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