Learning of Brain Connectivity Features for EEG-based Person Identification

The brain activity observed on multiple EEG electrodes is influenced by volume conductance and functional connectivity of a person performing a task. When the task is a biometric test, EEG signals represent the unique 'brain print' which is genetically defined by the functional connectivity that is represented by interactions between the electrodes, whilst the conductance component causes trivial correlations in EEG signals. Orthogonalisation using autoregressive modelling minimises the conductance component, and the connectivity features can be then extracted from the residuals. However, the results cannot be reliable for high-dimensional EEG data recorded via a multi-electrode system. The proposed method shows that the dimensionality can be significantly reduced if baselines that are required for estimating the residuals can be modelled by using EEG electrodes that make important contribution to the functional connectivity. The results show that the required models can be learnt by Machine Learning techniques which are capable of providing the maximal performance in the case of multidimensional EEG data. The study which has been conducted on a EEG benchmark including 109 participants shows a significant improvement of the identification accuracy.

[1]  E.J. Candes,et al.  An Introduction To Compressive Sampling , 2008, IEEE Signal Processing Magazine.

[2]  Partha Pratim Roy,et al.  A Novel framework of EEG-based user identification by analyzing music-listening behavior , 2017, Multimedia Tools and Applications.

[3]  Longchun Wang,et al.  PDMS-Based Low Cost Flexible Dry Electrode for Long-Term EEG Measurement , 2012, IEEE Sensors Journal.

[4]  Jeffrey M. Hausdorff,et al.  Physionet: Components of a New Research Resource for Complex Physiologic Signals". Circu-lation Vol , 2000 .

[5]  Chin-Teng Lin,et al.  Brain Computer Interface-based Smart Environmental Control System , 2012, 2012 Eighth International Conference on Intelligent Information Hiding and Multimedia Signal Processing.

[6]  Gordon Pipa,et al.  Transfer entropy—a model-free measure of effective connectivity for the neurosciences , 2010, Journal of Computational Neuroscience.

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

[8]  A.P. Vinod,et al.  Toward EEG-Based Biometric Systems: The Great Potential of Brain-Wave-Based Biometrics , 2017, IEEE Systems, Man, and Cybernetics Magazine.

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

[10]  Carsten Maple,et al.  Comparing Robustness of Pairwise and Multiclass Neural-Network Systems for Face Recognition , 2007, EURASIP J. Adv. Signal Process..

[11]  Xinwei Chen,et al.  A Compact Filtering Antenna With Flat Gain Response Within the Passband , 2013, IEEE Antennas and Wireless Propagation Letters.

[12]  A Zwanenburg,et al.  Functional connectivity in preterm infants derived from EEG coherence analysis. , 2014, European journal of paediatric neurology : EJPN : official journal of the European Paediatric Neurology Society.

[13]  Mel Slater,et al.  Virtual Smart Home Controlled by Thoughts , 2009, 2009 18th IEEE International Workshops on Enabling Technologies: Infrastructures for Collaborative Enterprises.

[14]  Sigfredo Fuentes,et al.  Integration of non-invasive biometrics with sensory analysis techniques to assess acceptability of beer by consumers , 2019, Physiology & Behavior.

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

[16]  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.

[17]  G. Comi,et al.  IFCN standards for digital recording of clinical EEG. The International Federation of Clinical Neurophysiology. , 1998, Electroencephalography and clinical neurophysiology. Supplement.

[18]  Damien A. Fair,et al.  Connectotyping: Model Based Fingerprinting of the Functional Connectome , 2014, PloS one.

[19]  Ramaswamy Palaniappan,et al.  Method of identifying individuals using VEP signals and neural network , 2004 .

[20]  Giulio Tononi,et al.  Estimation of Cortical Connectivity From EEG Using State-Space Models , 2010, IEEE Transactions on Biomedical Engineering.

[21]  Robert P. W. Duin,et al.  Support Vector Data Description , 2004, Machine Learning.

[22]  Minho Lee,et al.  Deep learning with support vector data description , 2015, Neurocomputing.

[23]  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).

[24]  Heung-Il Suk,et al.  Individual Identification Using Cognitive Electroencephalographic Neurodynamics , 2017, IEEE Transactions on Information Forensics and Security.

[25]  Vitaly Schetinin,et al.  Feature Extraction with GMDH-Type Neural Networks for EEG-Based Person Identification , 2017, Int. J. Neural Syst..

[26]  M. Teplan.  FUNDAMENTALS OF EEG MEASUREMENT , 2002 .

[27]  Wanli Ma,et al.  A study on the stability of EEG signals for user authentication , 2015, 2015 7th International IEEE/EMBS Conference on Neural Engineering (NER).

[28]  Sherif N. Abbas,et al.  A new multi-level approach to EEG based human authentication using eye blinking , 2016, Pattern Recognit. Lett..

[29]  N. Birbaumer,et al.  BCI2000: a general-purpose brain-computer interface (BCI) system , 2004, IEEE Transactions on Biomedical Engineering.

[30]  Wenyao Xu,et al.  Multichannel EEG-based biometric using improved RBF neural networks , 2015, 2015 IEEE Signal Processing in Medicine and Biology Symposium (SPMB).

[31]  Andreas Fischer,et al.  Pairwise support vector machines and their application to large scale problems , 2012, J. Mach. Learn. Res..

[32]  C. Stam,et al.  Phase lag index: Assessment of functional connectivity from multi channel EEG and MEG with diminished bias from common sources , 2007, Human brain mapping.

[33]  Pascal Vincent,et al.  Representation Learning: A Review and New Perspectives , 2012, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[34]  Yvonne Höller,et al.  Real movement vs. motor imagery in healthy subjects. , 2013, International journal of psychophysiology : official journal of the International Organization of Psychophysiology.

[35]  Gérard Dreyfus,et al.  Pairwise Neural Network Classifiers with Probabilistic Outputs , 1994, NIPS.

[36]  B. Chemin,et al.  EEG time-warping to study non-strictly-periodic EEG signals related to the production of rhythmic movements , 2018, Journal of Neuroscience Methods.

[37]  Mark W. Woolrich,et al.  Measuring functional connectivity in MEG: A multivariate approach insensitive to linear source leakage , 2012, NeuroImage.

[38]  Chee-Ming Ting,et al.  Modeling Effective Connectivity in High-Dimensional Cortical Source Signals , 2016, IEEE Journal of Selected Topics in Signal Processing.

[39]  Vitaly Schetinin,et al.  Learning polynomial neural networks of a near-optimal connectivity for detecting abnormal patterns in biometric data , 2016, 2016 SAI Computing Conference (SAI).