Identifying Visual Evoked Potential (VEP) Electrodes Setting for Person Authentication

Over recent years, person authentication using Electroencephalograms (EEG) signals has become more significant to researchers due to its uniqueness and security. EEG signals such as Visual Evoked Potential (VEP) had been used in the past literature for person authentication purposes. However, different sets of electrode channels were used in various VEP research. There is no consensus on the selection of EEG electrodes, particularly in person authentication research. Thus, this paper aims to investigate the best set of electrode channels for person authentication using VEP. Feature extraction methods such as coherence, cross-correlation and mean of amplitude were used for the purpose of classification. The performance measurement were based on the accuracy and area under ROC curve (AUC) values using Fuzzy-Rough Nearest Neighbour (FRNN) classifier proposed in our earlier work. An Anderson-Darling test in MATLAB was carried out to test the normality distribution of the results and the Wilcoxon sign-ranked test was used to perform statistical test. The results show that the set of eight channels from the occipital area perform better compared to the set of three channels and nine channels. The future research work will focus on investigating the performance of each parietal occipital and midline channels to obtain the best reduced set.

[1]  T. W. Anderson,et al.  Asymptotic Theory of Certain "Goodness of Fit" Criteria Based on Stochastic Processes , 1952 .

[2]  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.

[3]  Julie Thorpe,et al.  Pass-thoughts: authenticating with our minds , 2005, NSPW '05.

[4]  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.

[5]  C.R. Hema,et al.  Brain signatures: A modality for biometric authentication , 2008, 2008 International Conference on Electronic Design.

[6]  Michael Bach,et al.  ISCEV standard for clinical visual evoked potentials (2009 update) , 2010, Documenta Ophthalmologica.

[7]  Ramaswamy Palaniappan,et al.  Biometric Paradigm Using Visual Evoked Potential , 2009 .

[8]  Arash Habibi Lashkari,et al.  Shoulder Surfing attack in graphical password authentication , 2009, ArXiv.

[9]  James A. Hanley,et al.  Normal Approximations to the Distributions of the Wilcoxon Statistics: Accurate to What N? Graphical Insights , 2010 .

[10]  Jian-feng Hu,et al.  Biometric System Based on EEG Signals by Feature Combination , 2010, 2010 International Conference on Measuring Technology and Mechatronics Automation.

[11]  André Zúquete,et al.  Biometric Authentication using Brain Responses to Visual Stimuli , 2010, BIOSIGNALS.

[12]  Chris Cornelis,et al.  Fuzzy-rough nearest neighbour classification and prediction , 2011, Theor. Comput. Sci..

[13]  Kun Li,et al.  Advances and Challenges in Signal Analysis for Single Trial P300-BCI , 2011, HCI.

[14]  F. Tenore,et al.  Low-cost electroencephalogram (EEG) based authentication , 2011, 2011 5th International IEEE/EMBS Conference on Neural Engineering.

[15]  Benjamin W. Heumann.  An Object-Based Classification of Mangroves Using a Hybrid Decision Tree - Support Vector Machine Approach , 2011, Remote. Sens..

[16]  Vojkan Mihajlovic,et al.  To What Extent can Dry and Water-based EEG Electrodes Replace Conductive Gel Ones? - A Steady State Visual Evoked Potential Brain-computer Interface Case Study , 2011, BIODEVICES.

[17]  Tegpreet Kaur Neela,et al.  A framework for Authentication using Fingerprint and Electroencephalogram as Biometrics Modalities , 2012 .

[18]  Christoffer Kjeldgaard Petersen.  Development of a Mobile EEG-Based Feature Extraction and Classification System for Biometric Authentication , 2012 .

[19]  Ivan Svogor,et al.  Two factor authentication using EEG augmented passwords , 2012, Proceedings of the ITI 2012 34th International Conference on Information Technology Interfaces.

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

[21]  Yin Fen Low,et al.  Fuzzy-Rough Nearest Neighbour classifier for person authentication using EEG signals , 2013, 2013 International Conference on Fuzzy Theory and Its Applications (iFUZZY).

[22]  Pinki Kumari,et al.  BRAINWAVE BASED AUTHENTICATION SYSTEM : RESEARCH ISSUES AND CHALLENGES , 2014 .

[23]  Azah Kamilah Muda,et al.  Comparing Features Extraction Methods for Person Authentication Using EEG Signals , 2015 .