EEG Based Biometric Identification Using Correlation and MLPNN Models

T Waili,M. Othman,N. S. H. Mohd Nor,Md Gapar Md Johar,K. A. Sidek,H. Yaacob

doi:10.3991/ijoe.v15i10.10880

Abstract

<p class="0abstract">This study investigates the capability of electroencephalogram (EEG) signals to be used for biometric identification. In the context of biometric, recently, researchers have been focusing more on biomedical signals to substitute the biometric modalities that are being used nowadays as the signals obtained from our bodies is considered more secure and privacy-compliant. The EEG signals of 6 subjects were collected where the subjects were required to undergo two baseline experiments which are, eyes open (EO) and eyes closed (EC). The signals were processed using a 2nd order Butterworth filter to eliminate the unwanted noise in the signals. Then, Daubechies (db8) wavelet was applied to the signals in the feature extraction stage and from there, Power Spectral Density (PSD) of alpha and beta waves was computed. Finally, the correlation model and Multilayer Perceptron Neural Network (MLPNN) was applied to classify the EEG signals of each subject. Correlation model has yielded great significant difference of coefficient between autocorrelation and cross-correlation where it gives the coefficient value of 1 for autocorrelation and the coefficient value of less than 0.35 for cross-correlation. On the other hand, the MLPNN model gives an accuracy of 75.8% and 71.5% for classification during EO and EC baseline condition respectively. Therefore, these results support the usability of EEG signals in biometric recognition.</p>

Highlights

Biometrics is means to recognize individuals based on the high basis of one or more physical or behavioural criteria’s such as fingerprint, retinal pattern and deoxyribonucleic acid (DNA) [1]
Only the EEG signals from electrode C3 of three subjects are shown which are categorized into eyes open (EO) and eyes closed (EC)
Only correlation coefficient values from electrode C3 are depicted which are categorized into EO and EC

Summary

Introduction

Biometrics is means to recognize individuals based on the high basis of one or more physical or behavioural criteria’s such as fingerprint, retinal pattern and DNA [1]. The biometric system is fundamentally a pattern recognition system that operates constructed on three main stages which are enrollment stage - acquiring an individual’s biometric data, excerpting a feature set from the secured data and matching the feature set with the template set in the gallery. This offers a substitute to username and password as well as smart cards [1]. The use of EEG signals in biometric recognition has spark interest of researchers in this area because of the ability to give excellent results as this signal is much closer to human brain which controls our actions and reactions

Objectives

Methods

Results

Conclusion