Systems, Man & Cybernetics - October 2017 - 13

of EEG channels, wavelet packet decomposition, sample
entropy estimation, functional connectivity, spectral coherence, bump modeling, mel-frequency cepstral coefficients,
and others [18], [47], [48], [57], [58]. Neural networks, linear
vector quantizers, support vector machines, k-nearest-neighbor classifiers, Gaussian mixture modeling, correlation/distance-based simple classifiers, linear/nonlinear discriminant
analysis, and others have been reported to be efficient classifiers in biometric recognition [14], [18], [31]. However, online
performance and stability of any of these methods in a practical environment has hardly been investigated.
Stability of Features
Genetic and neurophysiological studies have described
changes in human EEG activity over time. The reproducibility of EEG biometric features in subsequent sessions is
highly desirable for the success of the system. A number of
studies have reported on the analysis of long-term stability
of EEG biometric features. But most of these use restingstate scenarios. It has been reported that alpha-band EEG
is an efficient marker of a rest state, maintaining intersubject differences evenly for a period ten months [15]. Another study in [17] that spanned a period of 15 months also
suggested the alpha-band peak as a stable feature. But
reports in [37] using imagined speech highlight that recognition performance deteriorates when sessions are temporally apart. Although there are indications of the stability of
various EEG biometric features over time, extensive analyses involving a greater number of sessions during a longer
period of time (years) for various acquisition protocols
have not yet been reported.
Intrasubject Variability in EEG Patterns
In an ideal biometric system, the biometric trait is
expected to be time invariant. Therefore, the nonstationarity of the EEG signal must be seriously considered during EEGBS development. For the same subject, data
recorded during different sessions/days may vary due to
the inherent complex nature of the brain, subject mood
and emotions, changes in the placement of electrodes,
changes in the recording environment, the presence of
artifacts, and so forth [57]. This intrasubject variability of
EEG features renders the matching process and recognition in EEGBS more challenging. Adaptive schemes must
be proposed to track these variabilities and achieve high
recognition rates. Another hidden disadvantage of EEGbased biometrics is the possibility that a person is unable
to generate the template matching pattern if he or she is
under stress, even though the desire is there to reproduce
it correctly. The impact of these attributes on the performance of EEGBS must be thoroughly investigated.
Size of Data Set
Reports indicate the lack of an obvious "most-discriminative" brain region for EEGBS due to the lack of uniformity
across and within databases, tasks, and systems used for
	

biometric studies. The largest number of subjects analyzed
in EEG-based biometric studies is fewer than 125 [10], [18].
Resting states and activity-related EEG patterns have
shown reasonable performance among different sets of
people, so larger data sets must be investigated in detail to
assess the scalability, collectability, and permanence of
reported EEG features in various protocols.
In addition to the aforementioned technical issues, a
number of other considerations also present challenges to
successful EEGBS implementation. In the existing experimental designs, EEG signals are usually acquired in dimly
lit rooms where no external visual or audio stimuli are
present for distraction. In actual scenarios, different factors such as noisy surrounding environments, a degree of
fatigue, emotions, heart rate, and the use of drugs/alcohol
can affect EEG signals and features. These factors must
also be considered before practical deployment of EEGbased biometric systems can take place.
Acceptance of the Public
EEGBS may face some minor drawbacks in terms of
acceptability, because EEG recording may potentially
evoke ancestral worries related to "mind reading" and
emotion analysis. This may cause a sense of discomfort for
users. However, two key factors, an improvement in EEG
data collection protocols and enhancement in electrode
design, can substantially increase system popularity, but
no detailed investigations on the acceptability of EEGBS
have yet been reported. In addition, because EEG can
uncover existing/developing brain abnormalities, a few
may be reluctant to use this method. In the future, determining public opinion will help to assess the acceptability
of EEGBS and fine-tune its development process. Such a
survey on user feedback is not yet available.
Social, Cultural, and Legal Considerations
Although biometric systems based on EEG will truly benefit
any population, the lifelong association of the enrolled biometric trait with an individual and its potential use/connection in various identity records may generate social,
cultural, and legal concerns [44]. So, before deploying
EEGBS for public use, it is necessary to carefully consider
the possible limitations in real-time usage and engage in
public discussion to anticipate and minimize individual and
societal effects to avoid the chances for violating privacy
and human rights.
Feasibility in Unhealthy Subjects
Most of the available EEG-biometric studies use only
healthy subjects. But it is essential to analyze the feasibility
of EEG biometrics in individuals affected by common neurological disorders such as stroke and epilepsy. Epilepsy is a
brain disorder that can affect EEG signals, and, as a result,
it may impact EEG-based individual identification systems.
In [45], personal identification for two groups of subjects
(normal and epileptic) was analyzed to investigate the
O c tob e r 2017

IEEE SYSTEMS, MAN, & CYBERNETICS MAGAZINE	

13



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