Age, Sex, and Pathology Effects on Stability of Electroencephalographic Biometric Features Based on Measures of Interaction

Electroencephalographic (EEG) biometric features have attracted considerable interest, but they have also drawn major criticism as having low stability. Moreover, most published studies ignore the potential effect of individual factors interacting with stability on the performance of the examined system. We examined the effects of age, sex, and neurological conditions in 60 subjects: 1) using a single EEG recording; 2) when pooling two EEG sessions; and 3) when performing cross-session cross-validation in a biometric system based on multivariate autoregressive measures, in order to extend previous work on autoregressive coefficients. Feature-level fusion and wrapped feature subset-selection in multivariate autoregressive coefficients (MVAR), power spectral density, and 14 additional measures derived from the MVAR model resulted in a maximum area under the curve of receiver operating characteristics (AUC of ROC)/top equal error rate of 98.85/5.34 for a single EEG, 95.51/9.70 for EEG-pooling, and 85.34/22 for cross-session cross-validation. This best result was obtained by the transfer function polynomial, which outperformed the MVAR coefficients, based on the example data set used in this paper. Age, sex, and pathology significantly interacted with the stability of features ( $p<.001$ ). We suggest further investigation of frequency-dependent measures derived from the MVAR model. We emphasize the serious problem of ignoring stability in most previously published research and recommend accurate reporting of individual factors when studying EEG biometric features in multiple sessions for enrolment and authentication on separate days.

[1]  Shiliang Sun.  Multitask learning for EEG-based biometrics , 2008, 2008 19th International Conference on Pattern Recognition.

[2]  Ramaswamy Palaniappan,et al.  ON THE ANALYSIS OF VARIOUS TECHNIQUES FOR A NOVEL BRAIN BIOMETRIC SYSTEM , 2011 .

[3]  B. V. K. Vijaya Kumar,et al.  Subject identification from electroencephalogram (EEG) signals during imagined speech , 2010, 2010 Fourth IEEE International Conference on Biometrics: Theory, Applications and Systems (BTAS).

[4]  Fabio Babiloni,et al.  Human Brain Distinctiveness Based on EEG Spectral Coherence Connectivity , 2014, IEEE Transactions on Biomedical Engineering.

[5]  D I Boomsma,et al.  Genetic Influences on EEG Coherence in 5-Year-Old Twins , 1998, Behavior genetics.

[6]  Nurul Nadia Ahmad,et al.  Analysis of the EEG Signal for a Practical Biometric System , 2010 .

[7]  R. E. Greenblatt,et al.  Connectivity measures applied to human brain electrophysiological data , 2012, Journal of Neuroscience Methods.

[8]  Ramaswamy Palaniappan,et al.  A new method to identify individuals using signals from the brain , 2003, Fourth International Conference on Information, Communications and Signal Processing, 2003 and the Fourth Pacific Rim Conference on Multimedia. Proceedings of the 2003 Joint.

[9]  D I Boomsma,et al.  Longitudinal Genetic Analysis of EEG Coherence in Young Twins , 2001, Behavior genetics.

[10]  Patrizio Campisi,et al.  EEG biometrics for individual recognition in resting state with closed eyes , 2012, 2012 BIOSIG - Proceedings of the International Conference of Biometrics Special Interest Group (BIOSIG).

[11]  S.K. Setarehdan,et al.  Fisher linear discriminant based person identification using visual evoked potentials , 2008, 2008 9th International Conference on Signal Processing.

[12]  M. Kostilek,et al.  EEG biometric identification: Repeatability and influence of movement-related EEG , 2012, 2012 International Conference on Applied Electronics.

[13]  Arun Ross,et al.  Score normalization in multimodal biometric systems , 2005, Pattern Recognit..

[14]  Jean Gotman,et al.  High‐frequency oscillations: The state of clinical research , 2017, Epilepsia.

[15]  Ronald C. Petersen,et al.  Practice guideline update summary: Mild cognitive impairment , 2018, Neurology.

[16]  Olaf Sporns,et al.  Cerebral cartography and connectomics , 2015, Philosophical Transactions of the Royal Society B: Biological Sciences.

[17]  Michael Eichler,et al.  On the Evaluation of Information Flow in Multivariate Systems by the Directed Transfer Function , 2006, Biological Cybernetics.

[18]  L.A. Baccald,et al.  Generalized Partial Directed Coherence , 2007, 2007 15th International Conference on Digital Signal Processing.

[19]  Su Yang,et al.  On the Effectiveness of EEG Signals as a Source of Biometric Information , 2012, 2012 Third International Conference on Emerging Security Technologies.

[20]  Nariyoshi Yamaguchi,et al.  Gender Differences in Quantitative EEG at Rest and during Photic Stimulation in Normal Young Adults , 1994, Clinical EEG.

[21]  J. Geweke,et al.  Measures of Conditional Linear Dependence and Feedback between Time Series , 1984 .

[22]  Patrizio Campisi,et al.  On the Permanence of EEG Signals for Biometric Recognition , 2016, IEEE Transactions on Information Forensics and Security.

[23]  Gian Luca Marcialis,et al.  An EEG-Based Biometric System Using Eigenvector Centrality in Resting State Brain Networks , 2015, IEEE Signal Processing Letters.

[24]  Andreas Uhl,et al.  Reliability of EEG Measures of Interaction: A Paradigm Shift Is Needed to Fight the Reproducibility Crisis , 2017, Front. Hum. Neurosci..

[25]  Bin Hu,et al.  A Real-Time Electroencephalogram (EEG) Based Individual Identification Interface for Mobile Security in Ubiquitous Environment , 2011, 2011 IEEE Asia-Pacific Services Computing Conference.

[26]  M. Kaminski,et al.  Determination of information flow direction among brain structures by a modified directed transfer function (dDTF) method , 2003, Journal of Neuroscience Methods.

[27]  Mingzhou Ding,et al.  Evaluating causal relations in neural systems: Granger causality, directed transfer function and statistical assessment of significance , 2001, Biological Cybernetics.

[28]  S. Rossi,et al.  Clinical neurophysiology of aging brain: From normal aging to neurodegeneration , 2007, Progress in Neurobiology.

[29]  Wolfgang Klimesch,et al.  Resting state alpha frequency is associated with menstrual cycle phase, estradiol and use of oral contraceptives , 2014, Brain Research.

[30]  Patrizio Campisi,et al.  EEG Biometrics Using Visual Stimuli: A Longitudinal Study , 2016, IEEE Signal Processing Letters.

[31]  Wenyao Xu,et al.  Exploring EEG-based biometrics for user identification and authentication , 2014, 2014 IEEE Signal Processing in Medicine and Biology Symposium (SPMB).

[32]  Vassilios Chrissikopoulos,et al.  Person identification based on parametric processing of the EEG , 1999, ICECS'99. Proceedings of ICECS '99. 6th IEEE International Conference on Electronics, Circuits and Systems (Cat. No.99EX357).

[33]  F. Babiloni,et al.  Methods to highlight consistency in repeated EEG recordings , 2012 .

[34]  Areej Al-Wabil,et al.  Using brain signals patterns for biometric identity verification systems , 2014, Comput. Hum. Behav..

[35]  Z. Jane Wang,et al.  Hashing the mAR coefficients from EEG data for person authentication , 2009, 2009 IEEE International Conference on Acoustics, Speech and Signal Processing.

[36]  Gian Luca Marcialis,et al.  Experimental results on multi-modal fusion of EEG-based personal verification algorithms , 2016, 2016 International Conference on Biometrics (ICB).

[37]  Howida AbdelFattah Shedeed.  A new method for person identification in a biometric security system based on brain EEG signal processing , 2011, 2011 World Congress on Information and Communication Technologies.

[38]  Carlos M Travieso,et al.  EEG biometric identification: a thorough exploration of the time-frequency domain. , 2015, Journal of neural engineering.

[39]  L. Benedicenti,et al.  The electroencephalogram as a biometric , 2001, Canadian Conference on Electrical and Computer Engineering 2001. Conference Proceedings (Cat. No.01TH8555).

[40]  V. K. Murthy.  Estimation of the Cross-Spectrum , 1963 .

[41]  Jesús B. Alonso,et al.  Electroencephalogram subject identification: A review , 2014, Expert Syst. Appl..

[42]  L. Prichep,et al.  Guidelines for the Recording and Evaluation of Pharmaco-EEG Data in Man: The International Pharmaco-EEG Society (IPEG) , 2012, Neuropsychobiology.

[43]  Laleh Najafizadeh,et al.  On the invariance of EEG-based signatures of individuality with application in biometric identification , 2016, 2016 38th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC).

[44]  Chidchanok Lursinsap,et al.  Selecting Relevant EEG Signal Locations for Personal Identification Problem Using ICA and Neural Network , 2009, 2009 Eighth IEEE/ACIS International Conference on Computer and Information Science.

[45]  Su Yang,et al.  On the Usability of Electroencephalographic Signals for Biometric Recognition: A Survey , 2017, IEEE Transactions on Human-Machine Systems.

[46]  Bin Hu,et al.  Improving Individual Identification in Security Check with an EEG Based Biometric Solution , 2010, Brain Informatics.

[47]  Wolfgang Staffen,et al.  Using EEG, SPECT, and Multivariate Resampling Methods to Differentiate Between Alzheimer's and other Cognitive Impairments , 2016, 1606.09004.

[48]  Ramaswamy Palaniappan,et al.  Electroencephalogram Signals from Imagined Activities: A Novel Biometric Identifier for a Small Population , 2006, IDEAL.

[49]  Carles Grau,et al.  Unobtrusive Biometric System Based on Electroencephalogram Analysis , 2008, EURASIP J. Adv. Signal Process..

[50]  Zhanpeng Jin,et al.  Permanence of the CEREBRE brain biometric protocol , 2017, Pattern Recognit. Lett..

[51]  Ramaswamy Palaniappan,et al.  Improving visual evoked potential feature classification for person recognition using PCA and normalization , 2006, Pattern Recognit. Lett..

[52]  K. Yaffe,et al.  The projected effect of risk factor reduction on Alzheimer's disease prevalence , 2011, The Lancet Neurology.

[53]  G.K. Singhal,et al.  Person Identification Using Evoked Potentials and Peak Matching , 2007, 2007 Biometrics Symposium.

[54]  Jordi Solé i Casals,et al.  EEG based user recognition using BUMP modelling , 2013, 2013 International Conference of the BIOSIG Special Interest Group (BIOSIG).

[55]  W. Gersch,et al.  Epileptic Focus Location: Spectral Analysis Method , 1970, Science.

[56]  Fabio Babiloni,et al.  Brain waves based user recognition using the “eyes closed resting conditions” protocol , 2011, 2011 IEEE International Workshop on Information Forensics and Security.

[57]  Patrizio Campisi,et al.  Eigenbrains and Eigentensorbrains: Parsimonious bases for EEG biometrics , 2016, Neurocomputing.

[58]  Marc Wildi,et al.  Test–retest reliability of resting EEG spectra validates a statistical signature of persons , 2007, Clinical Neurophysiology.

[59]  Zhanpeng Jin,et al.  Brainprint: Assessing the uniqueness, collectability, and permanence of a novel method for ERP biometrics , 2015, Neurocomputing.

[60]  Hu Jian-feng,et al.  Multifeature biometric system based on EEG signals , 2009 .

[61]  Mingzhou Ding,et al.  Cortical functional network organization from autoregressive modeling of local field potential oscillations , 2007, Statistics in medicine.

[62]  Garima Bajwa,et al.  Neurokey: Towards a new paradigm of cancelable biometrics-based key generation using electroencephalograms , 2016, Comput. Secur..

[63]  Charles Wang,et al.  I Think, Therefore I Am: Usability and Security of Authentication Using Brainwaves , 2013, Financial Cryptography Workshops.

[64]  M. Hallett,et al.  Identifying true brain interaction from EEG data using the imaginary part of coherency , 2004, Clinical Neurophysiology.

[65]  H. Olesen,et al.  ID Proof on the Go: Development of a Mobile EEG-Based Biometric Authentication System , 2012, IEEE Vehicular Technology Magazine.

[66]  Clemens Brunner,et al.  BioSig: A Free and Open Source Software Library for BCI Research , 2008, Computer.

[67]  Isao Nakanishi,et al.  EEG based biometric authentication using new spectral features , 2009, 2009 International Symposium on Intelligent Signal Processing and Communication Systems (ISPACS).

[68]  Dharmendra Sharma,et al.  A Proposed Feature Extraction Method for EEG-based Person Identification , 2012 .

[69]  Alois Schlögl,et al.  A comparison of multivariate autoregressive estimators , 2006, Signal Process..

[70]  B. Porat,et al.  Digital Spectral Analysis with Applications. , 1988 .

[71]  Patrizio Campisi,et al.  On the Repeatability of EEG Features in a Biometric Recognition Framework using a Resting State Protocol , 2016, BIOSIGNALS.

[72]  R. Palaniappan,et al.  Leave-one-out Authentication of Persons Using 40 Hz EEG Oscillations , 2005, EUROCON 2005 - The International Conference on "Computer as a Tool".

[73]  José del R. Millán,et al.  Person Authentication Using Brainwaves (EEG) and Maximum A Posteriori Model Adaptation , 2007, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[74]  Danilo P. Mandic,et al.  EEG Based Biometric Framework for Automatic Identity Verification , 2007, J. VLSI Signal Process..

[75]  Heung-Il Suk,et al.  Person authentication from neural activity of face-specific visual self-representation , 2013, Pattern Recognit..

[76]  Ramaswamy Palaniappan,et al.  Two-Stage Biometric Authentication Method Using Thought Activity Brain Waves , 2008, Int. J. Neural Syst..

[77]  H H Stassen,et al.  Computerized recognition of persons by EEG spectral patterns. , 1980, Electroencephalography and clinical neurophysiology.

[78]  Kusuma Mohanchandra,et al.  Using Brain Waves as New Biometric Feature for Authenticating a Computer User in Real-Time , 2013 .

[79]  Fei Su,et al.  A biometric-based covert warning system using EEG , 2012, 2012 5th IAPR International Conference on Biometrics (ICB).

[80]  Jianfeng Hu,et al.  Method of Individual Identification Based on Electroencephalogram Analysis , 2009, 2009 International Conference on New Trends in Information and Service Science.

[81]  Katarzyna J. Blinowska,et al.  A new method of the description of the information flow in the brain structures , 1991, Biological Cybernetics.