ArticlePDF Available

STARFAST: a Wireless Wearable EEG/ECG Biometric System based on the ENOBIO Sensor

Authors:

Abstract and Figures

Camí de l'Observatori Fabra s/npp 08035 Barcelona SPAIN 1 alejandro.riera@starlab.es 2 stephen.dunne@starlab.es 3 ivan.cester@starlab.es 4 giulio.ruffini@starlab.es Abstract—We present a wearable, wireless biometry system based on the new ENOBIO 4-channel electrophysiology recording device developed at Starlab. Features extracted from electroencephalogram (EEG) and electrocardiogram (ECG) recordings have proven to be unique enough between subjects for biometric applications. We show here that biometry based on these recordings offers a novel way to robustly authenticate or identify subjects. In this paper, we present a rapid and unobtrusive authentication method that only uses 2 frontal electrodes and a wrist worn electrode referenced to another one placed at the ear lobe. Moreover, the system makes use of a multistage fusion architecture, which demonstrates to improved system performance. The performance analysis of the system presented in this paper stems from an experiment with 416 test trials, where an Equal Error Rate (EER) of 0% is obtained after the EEG and ECG modalities fusion and using a complex boundary decision. If a lineal boundary decision is used we obtain a True Acceptance Rate (TAR) of 97.9% and a False Acceptance Rate (FAR) of 0.82%. The obtained performance measures improve the results of similar systems presented in earlier work.
Content may be subject to copyright.
STARFAST: a Wireless Wearable EEG/ECG
Biometric System based on the ENOBIO Sensor
Alejandro Riera#1, Stephen Dunne#2, Iván Cester#3, Giulio Ruffini#3
#STARLAB BARCELONA SL
Camí de l’Observatori Fabra s/npp
08035 Barcelona SPAIN
1alejandro.riera@starlab.es
2stephen.dunne@starlab.es
3ivan.cester@starlab.es
4giulio.ruffini@starlab.es
AbstractWe present a wearable, wireless biometry system
based on the new ENOBIO 4-channel electrophysiology
recording device developed at Starlab. Features extracted from
electroencephalogram (EEG) and electrocardiogram (ECG)
recordings have proven to be unique enough between subjects
for biometric applications. We show here that biometry based on
these recordings offers a novel way to robustly authenticate or
identify subjects. In this paper, we present a rapid and
unobtrusive authentication method that only uses 2 frontal
electrodes and a wrist worn electrode referenced to another one
placed at the ear lobe. Moreover, the system makes use of a
multistage fusion architecture, which demonstrates to improved
system performance. The performance analysis of the system
presented in this paper stems from an experiment with 416 test
trials, where an Equal Error Rate (EER) of 0% is obtained after
the EEG and ECG modalities fusion and using a complex
boundary decision. If a lineal boundary decision is used we
obtain a True Acceptance Rate (TAR) of 97.9% and a False
Acceptance Rate (FAR) of 0.82%. The obtained performance
measures improve the results of similar systems presented in
earlier work.
I. INTRODUCTION
The present paper introduces a method to authenticate
people from their physiological activity, concretely the
combination of ECG and EEG data. We call this system
STARFAST (STAR Fast Authentication bio-Scanner Test).
Several biometric modalities are already being exploited
commercially for person authentication: voice recognition,
face recognition and fingerprint recognition are among the
more common modalities nowadays. But other types of
biometrics are being studied as well: ADN analysis, keystroke,
gait, palm print, ear shape, hand geometry, vein patterns, iris,
retina and written signature [33].
Although these different techniques for authentication exist
nowadays, they present some problems. Typical biometric
traits, such as fingerprint, voice and retina, are not universal,
and can be subject to physical damage (dry skin, scars, loss of
voice...). In fact, it is estimated that 2-3% of the population is
missing the feature that is required for authentication, or that
the provided biometric sample is of poor quality. Furthermore,
these systems are subject of attacks such as presenting a
registered deceased person, dismembered body part or
introduction of fake biometric samples.
New types of Biometrics, such as electroencephalography
(EEG) [1, 2, 3, 4, 5, 6, 7, 8, 9, 25] and electrocardiography
(ECG) [14, 15, 16, 17 ,18], are based on physiological signals,
rather than more traditional biological traits. These have some
advantages: Since every living and functional person has a
recordable EEG/ECG signal, the EEG/ECG feature is
universal. Moreover brain or heart damage is something that
rarely occurs, so it seems to be quite invariant across time.
Finally it seems very difficult to fake an EEG/ECG signature
or to attack an EEG/ECG biometric system.
An ideal biometric system should present the following
characteristics: 100% reliability, user friendliness, fast
operation and low cost. The perfect biometric trait should
have the following characteristics: very low intra-subject
variability, very high inter-subject variability, very high
stability over time and universality. In the next section we
show the general architecture and the global performance of
the system we have developed.
II. METHODS AND RESULTS
In this paper, we present a rapid and unobtrusive
authentication/identification method that only uses 2 frontal
electrodes (for EEG recording) with another electrode placed
on the left wrist (for ECG recording)and all 3 referenced to
another one placed at the right earlobe. Moreover the system
makes use of a multi-stage fusion architecture, which has been
demonstrated to improve system performance.
The EEG/ECG recording device is ENOBIO [23, 24, 32,
35], a product developed at STARLAB BARCELONA SL. It
is a wireless 4 channel (plus the common mode) device with
active electrodes. It is therefore quite unobtrusive, fast and
easy to place. Even though ENOBIO can work in dry mode, in
this study conductive gel has been used (see fig. 1).
Fig. 1: ENOBIO sensor embedded in a cap. We can see the 4 channel inputs
(red pins). In the picture, only two channels are plugged. The data are
transmitted wirelessly to the laptop.
The general schema used is described below:
Fig. 2 General scheme of the method. The data acquisition module is the
software that controls the ENOBIO sensor in order to capture the raw data.
Remember that 4 channels are recorded: 2 EEG channels placed in the
forehead, 1 ECG channel placed in the left wrist and 1 electrode placed in the
right earlobe for referencing the data. At this point the data is separate in EEG
data and ECG data and sent to two parallel but different biometric modules
for EEG and ECG (the difference is not shown in the scheme for simplicity).
For the signature extraction module, four 3-minutes takes are needed. Once
the signatures are extracted, they are both stored in the database for further
retrieval when an authentication process takes place. Then the recognition
module provides an authentication score for both modalities and finally the
fusion module provides the final decision. The enrolment and the
authentication test follow a common path until the feature extraction. Then
the red arrows indicates the enrolment path and the green ones the
authentication path.
Briefly, the preprocessing module segments the recorded
takes into 4 seconds epochs. From each one of those epochs
we extract 5 different features: auto-regression coefficients,
fast Fourier transform, mutual information, coherence and
cross correlation [10, 11, 12, 19, 20, 21]. The classifier used in
both the signature extraction module and in the recognition
module is the Fisher Discriminant Analysis [13], with 4
different discriminant functions (linear, diagonal linear,
quadratic and diagonal quadratic). During the enrolment
process, we need four 3-minutes takes, and these are used to
select the best combinations of features and classifiers, and
then to train the classifiers for each subject. This new feature
is what we call ‘personal classifier’ approach, and it improves
the performance of the system considerably. The
authentication test takes are 1-minute long. The preprocessing
and the feature extraction are equivalent to the enrolment case.
The recognition module loads the trained classifiers for each
modality (ECG and EEG) and an independent score is then
provided for each. Then the fusion module [22] provides a
final decision about the subject authentication.
In order to test the performance of our system we use 48
legal situations (when a subject claims to be himself), 350
impostor situations (when an enrolled subject claims to be
another subject from the database) and 16 intruder situations
(when a subject who is not enrolled in the system claims to be
a subject belonging to the database). Once the EEG and the
ECG biometrics results are fused, using a complex boundary
decision (dotted line 2 in fig. 3), we can obtain an ideal
performance, that is True Acceptance Rate (TAR) = 100% and
False Acceptance Rate (FAR) = 0%. If a linear boundary
decision is used (line 1 in fig. 3), we obtain a TAR = 97.9%
and a FAR = 0.82%. The results are summarized in table I.
Fig. 3: Bidimensional decision space. Ordinates represent the ECG
probabilities and abscises the EEG probabilities. Red crosses represent
impostor/intruder cases and green crosses represent legal cases. Two decision
functions are represented
This system has been tested as well to validate the initial
state of users, and has been proved sensitive enough to detect
it. If a subject has suffered from sleep deprivation [28],
alcohol intake [26, 27] or drug ingestion when passing an
authentication test, the authentication performance decreases.
This fact provides evidence that such a system is able to detect
not only the identity of a subject but his state as well.
TABLE I
TRUE ACCEPTANCE RATE AND FALSE ACCEPTANCE RATE FOR EEG AND ECG
MODALITIIES AND FOR THE FUSION OF BOTH MODALITIES. FUSION 1 IS DONE
USING THE BOUNDARY DECISION LINE 1 AND FUSION 2 USING THE BOUNDARY
DECISION LINE 2. WE OBSERVE THAT THE TAR FOR THE FUSION 1 IS THE SAME
THAN THE ONE OBTAINED WITH THE ECG MODALITY, BUT THE FAR DECREASES
BY A FACTOR HIGHER THAN 2.
TAR FAR
EEG 79.2%% 21.8%
ECG 97.9% 2.1%
FUSION 1 97.9% 0.82%
FUSION 2 100% 0%
III. CONCLUSION AND FUTURE WORK
These results show that the authentication of people from
physiologic data can be achieved using techniques of machine
learning. Concretely it shows that the fusion of two (or more)
independent biometric modules increases the performance of
the system by applying a fusion stage after obtaining the
biometric scores.
This result shows that processing the different
physiological modalities separately on different processing
modules, and introducing a data fusion step, the resulting
performance can be increased. Applying a very similar
approach, we could easily adapt the system to do emotion
recognition [29, 30, 34] from physiological data, or develop a
Brain Computer Interface, just starting from different ground
truth data. From our point of view, this easy to extend feature
of our system is the more interesting part of our study along
with the ‘personal classifier’ approach which improves
considerably the performance of the system.
The system described could have different applications for
Virtual Reality. It can validate in a continuous way that the
person supposed to be tele-present in an audiovisual
interactive space is actually the person that is supposed to be.
This could facilitate the personalization of the reaction of the
virtual environment [31], or secure interactions that guarantee
the authenticity of the person behind.
Although the system described here was oriented towards
person identification, its performance has been significantly
modified by introducing physiological data obtained in altered
states such as the ones resulting from sleep deprivation. This
indicates that such a system could be used to extract
dynamically changing, such as physiological activity related
to mood or to intense cognitive activity. For example, it could
be used to extract the features described (sleep deprivation,
alcohol intake), but also information about basic emotions
(see, for example, [34]).
The dynamic extraction of such features could be used to
evaluate the response of people in virtual environments, as
well as adapt the behaviour of such environments to the
information extracted dynamically.
The advantage that such a system would present compared
to currently existing approaches is that –by having built a
decisional system that is completely modular- we could
estimate each class independently of the other classes obtained,
which would allow us to have a modular approach to define
the interaction between the human and the machine.
Finally we would like to highlight the usefulness of using a
single system for user state monitoring and user
personalization. Assuming that the system is worn anyway for
physiological feedback, this same system can personalize your
experience because it knows who you are without any
interaction required by the user.
ACKNOWLEDGMENT
The authors wish to thank STARLAB BARCELONA S.L.
for supporting this research and for providing the ENOBIO
sensor. STARLAB BARCELONA S.L. is a private research
company with the goal of transforming science into
technologies with a profound and positive impact on society.
The authors also wish to thank the HUMABIO project
(Contract number 026990) who funded part of this research.
HUMABIO is a EC co-funded "Specific Targeted Research
Project" (STREP) where new types of biometrics are
combined with state of the art sensorial technologies in order
to enhance security in a wide spectrum of applications like
transportation safety and continuous authentication in safety
critical environments like laboratories, airports and/or other
buildings.
REFERENCES
[1] Eischen S., Luctritz J. and Polish J. (1995) Spectral analysis of EEG
from Families. Biological Psycholology,Vol. 41, pp. 61-68.
[2] Hazarika N., Tsoi A. and Sergejew A. (1997) Nonlinear considerations
in EEG signal Classification. IEEE Transactions on signal Processing,
Vol. 45, pp.829-836.
[3] Marcel S., Mill J. (2005) Person authentication using brainwaves
(EEG) and maximum a posteriori model adaptation. IDIAP Research
Report 05-81, 11 pp.
[4] Mohammadi G. et al. (2006) Person identification by using AR model
for EEG signals. Proc. 9th International Conference on Bioengineering
Technology (ICBT2006), Czech Republic,5 pp.
[5] Paranjape R. et al.(2001)The electroencephalogram as a biometric.
Proc. Canadian Conf. On Electrical and Computer Engineering, pp.
1363-1366.
[6] Poulos M. et al. (1998) Person identification via the EEG using
computational geometry algorithms. Proceedings of the Ninth
European Signal Processing, EUSIPCO’98, Rhodes, Greece.
September1998,pp. 2125-2128.
[7] Poulos M. et al. (1999) Parametric person identification from EEG
using computational geometry. Proc. 6th International Conference on
Electronics, Circuits and Systems (ICECS’99),v. 2, pp. 1005-1008.
[8] PoulosM.et al. (2001) On the use of EEG features towards person
identification via neural networks. Medical Informatics & the Internet
in Medicine, v. 26, pp. 35-48.
[9] Poulos M. et al. (2002) Person identification from the EEG using
nonlinear signal classification. Methods of Information in Medicine,v.
41, pp. 64-75.
[10] Remond A., Ed. (1997) EEG Informatics. A didactic review of methods
and applications of EEG data processing. Elsevier Scientific
Publishing Inc., New York,1997.
[11] Sviserskaya N., Korolkova T.(1995) Genetic Features of the spatial
organization of the human cerebral cortex. Neuroscience and
Behavioural Physiology, Vol.25,N.5,pp. 370-376.
[12] Deriche M., Al-Ani A. (2001) A new algorithm for EEG feature
selection using mutual information. Acoustics, Speech, and Signal
Processing, 2001. Proceedings. ’01,pp. 1057 - 1060vol.2
[13] Duda R.etal.,PatternClassification, Wiley, New York, 2001.
[14] Biel L. et al. (2001) ECG analysis: a new approach in human
identification. IEEE Transactions on Instrumentation and Measurement,
Vol. 50, N. 3, pp.808-812.
[15] Chang C.K. (2005) Human identification using one lead ECG. Master
Thesis. Department of Computer Science and Information Engineering.
Chao yang University of Technology (Taiwan).
[16] Israel S. et al. (2005) EGC to identify individuals. Pattern Recognition,
38, pp.133-142.
[17] Kyoso M. (2001) Development of an ECG Identification System. Proc.
23rd Annual International IEEE Conference on Engineering in
Medicine and Biology Society, Istanbul, Turkey.
[18] Palaniappan R. and Krishnan S.M. (2004) Identifying individuals using
ECG beats. Proceedings International Conference on Signal Processing
and Communications,2004. SPCOM’04,pp. 569-572.
[19] WintererG.et al. (2003) Association of EEG coherence and anexonic
GABA(B)R gene polymorphism. Am JMed Genet B Neuropsychiatr
Genet,117:51-56.
[20] Kikuchi M. et al. (2000) Effect of normal aging upon inter hemispheric
EEG coherence: analysis during rest and photic stimulation. Clin
Electroencephalogr,31: 170-174.
[21] Moddemeijer R. (1989) On estimation of entropy and mutual
information of continuous distributions. Signal
Processingvol.16nr.3pp.233-246
[22] Ross A, Jain A. (2003) Information fusion in biometrics. Pattern
Recognition Letters 24pp.2115-2125
[23] G. Ruffini et al. (2006) A dry electrophysiology electrode using CNT
arrays. Sensors and Actuators A132 34-41
[24] G. Ruffini et al. (2007) ENOBIO dry electrophysiology electrode; first
human trial plus wireless electrode system. 29th IEEE EMBS Annual
International Conference.
[25] A. Riera et al. (2007) Unobtrusive Biometric System Based on
Electroencephalogram Analysis. EURASIP Journal on Advances in
Signal Processing. Volume 2008 (2008), Article ID 143728
[26] Hogansetal. (1961) Effects of ethyl alcohol on EEG and avoidance
behavior of chronic electrode monkeys. Am JPhysio, 201: 434-436
[27] J.Sorbeletal. (1996) Alcohol Effects on the Heritability of EEG Spectral
Power alcoholism: clinical and experimental research. RESEARCH.
Vol. 20, No. 9. December 1996.
[28] S. Jin et al (2004) Effects of total sleep-deprivation on waking human
EEG: functional cluster analysis. Clinical Neurophysiology, Volume
115, Issue 12, Pages 2825-2833
[29] KazuhikoTakahashi(2004) Remarks on Emotion Recognition from Bio-
Potential Signals. 2nd International Conference on Autonomous
Robots and Agents.
[30] A. Haag et al. (2004) Emotion Recognition Using Bio-sensors: First
Steps towards an Automatic System. Springer-Verlag Berlin Heidelberg,
ADS, LNAI 3068,pp. 36-48.
[31] J.Llobera (2007) Narratives within Immersive Technologies.
arXiv:0704.2542.
[32] G.Ruffini et al. (2006) First human trials of a dry electrophysiology
sensor using a carbon nanotube array interface.
arXiv:physics/0701159
[33] V. Gracia et al. (2006) State of the Art in Biometrics Research and
Market Survey. HUMABIO Project (EU FP6 contract no 026990).
Deliverable N.1.4.www.humabio-eu.org
[34] Rainville, P, Bechara, A, Naqvi, N, Damasio, A. Basic emotions are
associated with distinct patterns of cardio respiratory activity.
International Journal of psychophysiology 61 (2006)
[35] Iván Cester et al. ENOBIO: Wearable, Wireless, 4-channel
electrophysiology recording system optimized for dry electrodes.
Presented in pHealth conference 2008 (Valencia)
... The perfect biometric modality 3 should possess a very low intra-subject variability besides having both a very high inter-subject variability and stability over time [234]. The variability between different ECG signals from the same individual or variability within one ECG (the latter is also called beat-to-beat variability) is termed the intrasubject variability [235]. ...
... This may reveal essentially in the heart rate variability, altering the morphology of the P-R and S-T segments [241], [242]. Notably, studies in [234], [237]- [242] have shown that intra-subject viability in ECG signals is the source of uncertainty that has prompted a primary setback in the application of the ECG signal as a biometric trait. There are several general techniques used for Artifact removal from ECG recordings. ...
Article
Full-text available
Electrocardiogram (ECG) has extremely discriminative characteristics in the biometric field and has recently received significant interest as a promising biometric trait. However, ECG signals are susceptible to several types of noises, such as baseline wander, powerline interference, and high/low-frequency noises, making it challenging to realize biometric identification systems precisely and robustly. Therefore, ECG signal denoising is a major pre-processing step and plays a crucial role in ECG-based biometric human identification. ECG signal analysis for biometric recognition can combine several steps, such as preprocessing, feature extraction, feature selection, feature transformation, and classification which is a very challenging task. Moreover, the selected success measures and proper structure of the ECG signal database play significant roles in biometric system analysis, considering that publicly available databases are essential by the research community to evaluate the performance of their proposed algorithms. In this survey, we review most of the techniques employed for the ECG as biometrics for human authentication. Firstly, we present an overview and discussion on ECG signal preprocessing, feature extraction, feature selection, and feature transformation for ECG-based biometric systems. Secondly, we present a survey of the available ECG databases to evaluate and compare the acquisition protocol, acquisition hardware, and acquisition resolution (bits) for ECG-based biometric systems. Thirdly, we also present a survey on different techniques, including deep learning methods: deep supervised learning, deep semi-supervised learning, and deep unsupervised learning, for ECG signal classification. Lastly, we present the state-of-art approaches of information fusion in multimodal biometric systems.
... ECG biometrics Because of its inherent robustness to circumvention, obfuscation and replay attacks, a biosignals-based approach has been largely explored during the last decades [41]; here, the idea is to exploit vital signals typically employed for medical diagnoses -such as electroencephalogram (EEG) [25,41], photoplethysmography [35] and electrocardiogram (ECG) [7,2] -for biometric purposes. In particular, the latter is quite interesting because both the physiological and geometrical differences in each human heart correspond to uniqueness in the ECG morphology [51]. ...
... ECG biometrics Because of its inherent robustness to circumvention, obfuscation and replay attacks, a biosignals-based approach has been largely explored during the last decades [41]; here, the idea is to exploit vital signals typically employed for medical diagnoses -such as electroencephalogram (EEG) [25,41], photoplethysmography [35] and electrocardiogram (ECG) [7,2] -for biometric purposes. In particular, the latter is quite interesting because both the physiological and geometrical differences in each human heart correspond to uniqueness in the ECG morphology [51]. ...
Chapter
Full-text available
Applications such as surveillance, banking and healthcare deal with sensitive data whose confidentiality and integrity depends on accurate human recognition. In this sense, the crucial mechanism for performing an effective access control is authentication, which unequivocally yields user identity. In 2018, just in North America, around 445K identity thefts have been denounced. The most adopted strategy for automatic identity recognition uses a secret for encrypting and decrypting the authentication information. This approach works very well until the secret is kept safe. Electrocardiograms (ECGs) can be exploited for biometric purposes because both the physiological and geometrical differences in each human heart correspond to uniqueness in the ECG morphology. Compared with classical biometric techniques, e.g. fingerprints, ECG-based methods can definitely be considered a more reliable and safer way for user authentication due to ECG inherent robustness to circumvention, obfuscation and replay attacks. In this paper, the ECG WATCH, a non-expensive wristwatch for recording ECGs anytime, anywhere, in just 10 s, is proposed for user authentication. The ECG WATCH acquisitions have been used to train a shallow neural network, which has reached a 99% classification accuracy and 100% intruder recognition rate.
... In Riera et al. (2008a), proposed a new authentication system based on a combination of EEG and ECG signals. In this system, five features are extracted from the recorded signals, which are autoregression (AR) coefficients, fast Fourier transform (FFT), mutual information, coherence, and cross-correlation, then the extracted features are classified by Fisher discriminant analysis (FDA). ...
... This factor highly affects the consumer's acceptance of the system. However, the methods proposed in Chen et al. (2016), Heger et al. (2013), Jayarathne et al. (2016), Liew et al. (2015), Palaniappan and Mandic (2007), Poulos et al. (1999), Riera et al. (2008bRiera et al. ( , 2008a, La , Ruiz-Blondet et al. (2016), Shozawa et al. (2013) and Yeom et al. (2013) can be considered as simple methods, while the methods proposed at Ashby et al. (2011), Chuang et al. (2013), Palaniappan (2006) and Serwadda et al. (2015) require considerable time in preparation and maybe tiresome to the consumer. ...
Article
Several decades ago, attention was directed to biometrics as an alternative to passwords that can be discovered or ‘shoulder surfing’ by others. Various authentication methods have been provided that rely on the user’s biometrics, such as a fingerprint of a face, iris, voice, and others. Unfortunately, ways were found to imitate these visible fingerprints for using them in penetrations. Therefore, many researchers were interested in studying the possibility of using brainwaves for authentication purposes, as relying on hidden vital features increases the difficulty of breaking and imitation. This paper presents an analytical study of the proposed brainwave-based biometric authentication systems. It provides a comparison of signal acquisition methods for the brainwave-based authentication system. Also, the paper classifies brainwaves using its relevant features. It also presents the phases of the brainwave-based authentication system. Finally, it provides a detailed discussion of several factors that affect the accuracy of the brainwave-based authentication system results, and evaluate the compatibility level of the brainwave with the biometric requirements.
... The experimental session began with familiarising the participant with the operation of an instrumented bicycle, where all the participants could ride a bike in reality. Next, the participant was sat on the bicycle and the HTC Vive head-mounted display (HMD) (Borrego et al., 2018) and the EEG recording device Enobio (Riera et al., 2008) were put on their head. The Enobio headset used the following electrodes: FP1, FP2, Fz, C3, Cz, C4, P3 and P4 to record the signal from the whole scalp at sampling rate of 128 Hz 2 . ...
Article
Road risk analysis is one of the key research areas in transport, where the impact of perceived risk on choices, especially in a dynamic setting, has been long recognised. However, due to the lack of dynamic data and the difficulty in capturing risk perception, the existing studies typically resort to static and stated approaches to infer the experienced level of risk of individuals. In this paper, we aimed to address this research gap through developing a hybrid choice model that jointly employed dynamic data on cycling behaviour in virtual reality and neural data to evaluate how the fluctuations in momentary risk perception influence the behaviour of cyclists. The results of the developed model confirm our hypotheses, demonstrating that cyclists reduce their speed when approaching a junction as the potential for a collision with passing cars increases. Moreover, the latent component allowed us to establish a link between the neural data, the amplitude of alpha brainwaves, and objective risk measures. In line with our hypothesis, we found that decreased alpha amplitude is associated with higher perceived risk which in turn increases the likelihood of braking. The implications of our study are manifold. On the one hand, it shows the ability of virtual reality to elicit complex cyclists’ behaviour and the feasibility of a joint collection of dynamic neural and choice data. On the other hand, we demonstrate the potential of the employment of neural data in a hybrid model framework as an indicator of risk that allows us to gain a better understanding of cycling behaviour and associated neural processing. These promising findings pave the way for future studies that would explore the advantages of neuroscientific inputs in the choice models.
... The fusion of multiple signal sources has also been used to increase biometric verification performance. For instance, [27] proposes two-factor verification using a person's fingerprint and [28] a system which fuses EEG and ECG to identify subjects with 97.90% accuracy. Some studies have tried using EMG analysis as part of such a fused approach. ...
Article
Full-text available
Electromyogram (EMG) acquisition and analysis is growing in importance with human attempts to interact with and control equipment such as robots, prostheses or virtual environments. In some cases, only approved users should be permitted these capabilities. For these applications, securing EMG-based control is a major open question - to the best of the authors’ knowledge, no prior art exists which can identify individuals from a wide range of wrist-hand gestures EMG readings within the wearable device. This paper addresses this problem. Techniques are presented which allow EMG to be used as a biometric, allowing users to verify themselves. An EMG-sensing armband attached to the lower forearm is used to anonymously authenticate users as a member of an approved group, or to identify themselves uniquely. For the development of extensive biometric system, three EMG datasets with similar EMG sensing in different sessions were exploited. For verification, accuracy of up to 93% is achieved, with 92% achieved for identification. The system is also shown to operate in real-time on an ARM Cortex A-53 embedded processor suitable for housing in an EMG wearable device, incurring latencies of 1.06 ms and 1.61 ms for verification and identification respectively. These metrics are comfortably sufficient for use in real-time, battery-powered EMG authentication devices.
... An authentication system proposed by Riera et al. [26] was using a combination of ECG and EEG signals for discriminating against the situation. The achieved accuracy for this study was higher than others even for relaxation task. ...
Article
Full-text available
Security authentication is one of the most important levels of information security. Nowadays, human biometric techniques are the most secure methods for authentication purposes that cover the problems of older types of authentication like passwords and pins. There are many advantages of recent biometrics in terms of security; however, they still have some disadvantages. Progresses in technology made some specific devices, which make it possible to copy and make a fake human biometric because they are all visible and touchable. According to this matter, there is a need for a new biometric to cover the issues of other types. Brainwave is human data, which uses them as a new type of security authentication that has engaged many researchers. There are some research and experiments, which are investigating and testing EEG signals to find the uniqueness of human brainwave. Some researchers achieved high accuracy rates in this area by applying different signal acquisition techniques, feature extraction and classifications using Brain–Computer Interface (BCI). One of the important parts of any BCI processes is the way that brainwaves could be acquired and recorded. A new Signal Acquisition Strategy is presented in this paper for the process of authorization and authentication of brain signals specifically. This is to predict image memorability from the user’s brain to use mental imagery as a visualization pattern for security authentication. Therefore, users can authenticate themselves with visualizing a specific picture in their minds. In conclusion, we can see that brainwaves can be different according to the mental tasks, which it would make it harder using them for authentication process. There are many signal acquisition strategies and signal processing for brain-based authentication that by using the right methods, a higher level of accuracy rate could be achieved which is suitable for using brain signal as another biometric security authentication.
... A brief discussion on how the modality characteristics, performance evaluation metrics, security, and privacy affect future design solutions for WBS is discussed in Section 6. While Section 7 presents the open research challenges and of the following: brainwaves associated with stimuli, iris structure [30], retinal patterns [194], vocal resonance while speaking prerecorded phrases [149,195], skull conduction in response to audio waves propagating within the head [184], signals from the heart [23,180], vein pattern on the underside of the skin, gait while walking or striding [64,81], signals generated by muscles in motion [[201], Mechanomyograph (MMG) signals generated by muscles upon activation [25], fingerprint patterns [57], readings of pressure applied by fingertips when holding objects like pens, car keys, steering wheel, computer mouse, door handle, and so forth, patterns from signature and body odor [135], and Photoplethysmograph (PPG) denoting the absorption of light through a body part in accordance with heartrate pulses [53,123]. ...
Article
Full-text available
Biometric research is directed increasingly toward Wearable Biometric Systems (WBS) for user authentication and identification. However, prior to engaging in WBS research, how their operational dynamics and design considerations differ from those of Traditional Biometric Systems (TBS) must be understood. While the current literature is cognizant of those differences, there is no effective work that summarizes the factors where TBS and WBS differ, namely, their modality characteristics, performance, security, and privacy. To bridge the gap, this article accordingly reviews and compares the key characteristics of modalities, contrasts the metrics used to evaluate system performance, and highlights the divergence in critical vulnerabilities, attacks, and defenses for TBS and WBS. It further discusses how these factors affect the design considerations for WBS, the open challenges, and future directions of research in these areas. In doing so, the article provides a big-picture overview of the important avenues of challenges and potential solutions that researchers entering the field should be aware of. Hence, this survey aims to be a starting point for researchers in comprehending the fundamental differences between TBS and WBS before understanding the core challenges associated with WBS and its design.
... A typical WBAN, shown in Figure 3, is an interconnection of multiple independent wearable sensors, each of which measure specific signals from a modality included but not limited to be one of the following: brainwaves associated with stimuli, iris structure [30], retinal patterns [194], vocal resonance while speaking prerecorded phrases [149,195], skull conduction in response to audio waves propagating within the head [184], signals from the heart [23,180], vein pattern on the underside of the skin, gait while walking or striding [64,81], signals generated by muscles in motion [ [201], Mechanomyograph (MMG) signals generated by muscles upon activation [25], fingerprint patterns [57], readings of pressure applied by fingertips when holding objects like pens, car keys, steering wheel, computer mouse, door handle, etc., patterns from signature and body odor [135], and Photoplethysmograph (PPG) denoting the absorption of light through a body part in accordance with heartrate pulses [53,123]. ...
Preprint
Biometric research is directed increasingly towards Wearable Biometric Systems (WBS) for user authentication and identification. However, prior to engaging in WBS research, how their operational dynamics and design considerations differ from those of Traditional Biometric Systems (TBS) must be understood. While the current literature is cognizant of those differences, there is no effective work that summarizes the factors where TBS and WBS differ, namely, their modality characteristics, performance, security and privacy. To bridge the gap, this paper accordingly reviews and compares the key characteristics of modalities, contrasts the metrics used to evaluate system performance, and highlights the divergence in critical vulnerabilities, attacks and defenses for TBS and WBS. It further discusses how these factors affect the design considerations for WBS, the open challenges and future directions of research in these areas. In doing so, the paper provides a big-picture overview of the important avenues of challenges and potential solutions that researchers entering the field should be aware of. Hence, this survey aims to be a starting point for researchers in comprehending the fundamental differences between TBS and WBS before understanding the core challenges associated with WBS and its design.
Chapter
Current user authentication systems are based on PIN code, password, or biometrics traits, which can have some limitations in usage and security. Lifestyle authentication has become a new research approach in which the promising idea is to use the location history since it is relatively unique. Even when people live in the same area or have occasional travel, it does not vary from day to day. For Global Positioning System (GPS) data, previous work used the longitude, latitude, and timestamp as the classification features. In this paper, we investigate a new approach utilizing distance coherence, which can be extracted from the GPS itself without the need to require other information. We applied three ensemble classifications, including RandomForest, ExtraTrees, and Bagging algorithms. The experimental result showed that our approach could achieve 99.42%, 99.12%, and 99.25% of accuracy, respectively.
Article
Full-text available
Person identification based on spectral information extracted from the EEG is addressed in this work-a problem that has not yet been seen in a signal processing framework. Spectral features are extracted non-parametrically from real EEG data recorded from healthy individuals. Neural network classification is applied on these features using a Learning Vector Quantizer in an attempt to experimentally investigate the connection between a person's EEG and genetically specific information. The proposed method, compared with previously proposed methods, has yielded encouraging correct classification scores in the range of 80% to 100% (case-dependent). These results are in agreement with previous research showing evidence that the EEG carries genetic information.
Article
Full-text available
ENOBIO is a 4 channel wireless EEG/EOG/ECG/EMG system. We recorded EEG signal with ENOBIO and the benchmark ActiveTwo system from Biosemi simultaneously. Although ENOBIO was performing at its lowest gain setting, the quality of both signals is very similar and the peak for alpha band has similar amplitude for both systems.
Conference Paper
Full-text available
The purpose of this paper is to present a new identification engine for an ECG identification system. The system identifies subjects based on a comparison of a patient's ECG with previously registered ECG feature parameters. These feature parameters are sampled from the intervals and durations of the electrocardiographic waves extracted using characteristic points appearing on the waveform of the second order derivative and are identified using discriminant analysis. Suitable combinations of feature parameters are selected and the accuracy of the proposed technique verified using ECGs from nine normal subjects.
Article
Full-text available
A direct connection between ElectroEncephaloGram (EEG) and the genetic information of individuals has been investigated by neurophysiologists and psychiatrists since 1960’s; and it opens a new research area in the science. This paper focuses on the person identification based on feature extracted from the EEG which can show a direct connection between EEG and the genetic information of subjects. In this work the full EO EEG signal of healthy individuals are estimated by an autoregressive (AR) model and the AR parameters are extracted as features. Here for feature vector constitution, two methods have been proposed; in the first method the extracted parameters of each channel are used as a feature vector in the classification step which employs a competitive neural network and in the second method a combination of different channel parameters are used as a feature vector. Correct classification scores at the range of 80% to 100% reveal the potential of our approach for person classification/identification and are in agreement to the previous researches showing evidence that the EEG signal carries genetic information. The novelty of this work is in the combination of AR parameters and the network type (competitive network) that we have used. A comparison between the first and the second approach imply preference of the second one.
Article
Full-text available
Features extracted from electroencephalogram (EEG) recordings have proved to be unique enough between subjects for biometric applications. We show here that biometry based on these recordings offers a novel way to robustly authenticate or identify subjects. In this paper, we present a rapid and unobtrusive authentication method that only uses 2 frontal electrodes referenced to another one placed at the ear lobe. Moreover, the system makes use of a multistage fusion architecture, which demonstrates to improve the system performance. The performance analysis of the system presented in this paper stems from an experiment with 51 subjects and 36 intruders, where an equal error rate (EER) of 3.4% is obtained, that is, true acceptance rate (TAR) of 96.6% and a false acceptance rate (FAR) of 3.4%. The obtained performance measures improve the results of similar systems presented in earlier work.
Article
This paper proposes an emotion recognition system from multi-modal bio-potential signals. For emotion recognition, support vector machines (SVM) are applied to design the emotion classifier and its characteristics are investigated. Using gathered data under psychological emotion stimulation experiments, the classifier is trained and tested. In experiments of recognizing five emotion: joy, anger, sadness, fear, and relax, recognition rate of 41.7% is achieved. The experimental result shows that using multi-modal bio-potential signals is feasible and that SVM is well suited for emotion recognition tasks.
Article
We report the results from the first human trials of a new dry electrode sensor for surface biopotential applications. This sensor uses nanotechnology to improve performance and wearability. Standard electrodes for demanding applications such as EEG require skin preparation and/or the use of electrolytic substances to provide and effective electrical interface. The contact surface of the electrode described here is covered with an array of carbon nanotubes designed for penetration of the outer layers of the skin for improved electrical contact without the use of electrolytic gel. In previous papers we detailed the design concept and reported the results of the initial tests of a first prototype—immersion in saline solution and signal detection in animal skin. In this paper we describe the first human trials of the prototype, which indicate performance on par with state-of-the-art research-oriented wet electrodes. No side effects have been observed 6 months after the tests, and the subject did not report any pain or unusual sensations upon application of the electrode.
Article
User verification systems that use a single biometric indicator often have to contend with noisy sensor data, restricted degrees of freedom, non-universality of the biometric trait and unacceptable error rates. Attempting to improve the performance of individual matchers in such situations may not prove to be effective because of these inherent problems. Multibiometric systems seek to alleviate some of these drawbacks by providing multiple evidences of the same identity. These systems help achieve an increase in performance that may not be possible using a single biometric indicator. Further, multibiometric systems provide anti-spoofing measures by making it difficult for an intruder to spoof multiple biometric traits simultaneously. However, an effective fusion scheme is necessary to combine the information presented by multiple domain experts. This paper addresses the problem of information fusion in biometric verification systems by combining information at the matching score level. Experimental results on combining three biometric modalities (face, fingerprint and hand geometry) are presented.
Article
Mutual information is used in a procedure to estimate time-delays between recordings of electroencephalogram (EEG) signals originating from epileptic animals and patients. We present a simple and reliable histogram-based method to estimate mutual information. The accuracies of this mutual information estimator and of a similar entropy estimator are discussed. The bias and variance calculations presented can also be applied to discrete valued systems. Finally, we present some simulation results, which are compared with earlier work.ZusammenfassungDie Auswertung von Elektroenzephalogrammen bei Epilepsie-Kranken erfordert die Bestimmung von Totzeiten zwischen den einzelnen Aufzeichnungen. Hierzu sind Verfahren geeignet, die am informationstheoretischen Begriff “mittlere Transinformation” anknüpfen. In diesem Beitrag wird eine einfache und zuverlässige Methode beschrieben, die mittlere Transinformation auf der Basis experimenteller Daten zu schätzen. Diskutiert werden Erwartungstreue und Varianz der vorgeschlagenen Schätzfunktionen. Die theoretisch erzielten Ergebnisse werden mit experimentellen Daten verglichen, die an Signalfolgen mit Gauβ-verteilten Amplituden gewonnen wurden.RésuméL'information mutuelle est utilisée dans une procédure pour estimer les retards temporels entre les enregistrements de signaux electroencéphalographique (EEG) provenant des animaux et patients épileptiques. Nous présentons une méthode simple et fiable basée sur l'histogramme pour estimer l'information mutuelle. La précision de cet estimateur d'information mutuelle et celle estimateurs d'entropie sont discutées. Les calculs de biais et de variance présentés peuvent également être appliqués aux systèmes à valeurs discrètes. Finalement, nous présentons quelques résultats de simulations qui sont comparés aux travaux antérieurs.