A feasibility study on using EEG for Biometric Trait Authentication System

The neuronal activity has a unique genetic signature that can be used for personal identification and authentication. Continuous authentication of individuals is required in the field involving high security, such as military services, intelligence organizations and secret agencies. Electroencephalo...

Full description

Bibliographic Details
Main Authors: Jeswani Devesh, Kumar Govarthan Parveen, Selvaraj Abirami, Bobby Thomas Christy, Thomas John, Agastinose Ronickom Jac Fredo
Format: Article
Language:English
Published: De Gruyter 2023-09-01
Series:Current Directions in Biomedical Engineering
Subjects:
Online Access:https://doi.org/10.1515/cdbme-2023-1173
_version_ 1797646337681915904
author Jeswani Devesh
Kumar Govarthan Parveen
Selvaraj Abirami
Bobby Thomas Christy
Thomas John
Agastinose Ronickom Jac Fredo
author_facet Jeswani Devesh
Kumar Govarthan Parveen
Selvaraj Abirami
Bobby Thomas Christy
Thomas John
Agastinose Ronickom Jac Fredo
author_sort Jeswani Devesh
collection DOAJ
description The neuronal activity has a unique genetic signature that can be used for personal identification and authentication. Continuous authentication of individuals is required in the field involving high security, such as military services, intelligence organizations and secret agencies. Electroencephalogram (EEG) based authentication method is favorable due to its uniqueness and the fact that it can be used even when the person is unconscious. In this study, we investigated the number of samples per subject required to reliably develop a biometric trait authentication system. Initially, we extracted the background EEG signals from the publicly available Temple University Hospital (TUH) database. A total of 46 statistical and frequency domain features were extracted from each EEG signal per subject. The classification was performed using the extreme Gradient Boosting (XGBoost) classifier. We varied the number of EEG signal segments per subject from 5 to 127 with an increment of 5 segments per trial. Finally, the performance parameters such as accuracy, sensitivity, specificity, precision and F-measure were obtained in each case for the biometric authentication system using the test data. Our model achieved the highest accuracy of 100% when more than 75 EEG signals per subject were considered for the analysis. We also identified alpha band power as the most efficient feature for authentication. Our results show that EEG signals can be effectively used for personal identification and authentication.
first_indexed 2024-03-11T15:01:13Z
format Article
id doaj.art-cbbc2abc51c743e784c93ecb16a32052
institution Directory Open Access Journal
issn 2364-5504
language English
last_indexed 2024-03-11T15:01:13Z
publishDate 2023-09-01
publisher De Gruyter
record_format Article
series Current Directions in Biomedical Engineering
spelling doaj.art-cbbc2abc51c743e784c93ecb16a320522023-10-30T07:58:13ZengDe GruyterCurrent Directions in Biomedical Engineering2364-55042023-09-019169069310.1515/cdbme-2023-1173A feasibility study on using EEG for Biometric Trait Authentication SystemJeswani Devesh0Kumar Govarthan Parveen1Selvaraj Abirami2Bobby Thomas Christy3Thomas John4Agastinose Ronickom Jac Fredo5School of Biomedical Engineering, Indian Institute of Technology (BHU), Varanasi, Uttar Pradesh, IndiaSchool of Biomedical Engineering, Indian Institute of Technology (BHU), Varanasi, Uttar Pradesh, IndiaSchool of Biomedical Engineering, Indian Institute of Technology (BHU), Varanasi, Uttar Pradesh, IndiaDepartment of Electronic and Communication Engineering, M.S. Ramaiah University of Applied Sciences, Bengaluru, IndiaMontreal Neurological Institute, McGill University, Quebec, CanadaSchool of Biomedical Engineering, Indian Institute of Technology (BHU), Varanasi, Uttar Pradesh, IndiaThe neuronal activity has a unique genetic signature that can be used for personal identification and authentication. Continuous authentication of individuals is required in the field involving high security, such as military services, intelligence organizations and secret agencies. Electroencephalogram (EEG) based authentication method is favorable due to its uniqueness and the fact that it can be used even when the person is unconscious. In this study, we investigated the number of samples per subject required to reliably develop a biometric trait authentication system. Initially, we extracted the background EEG signals from the publicly available Temple University Hospital (TUH) database. A total of 46 statistical and frequency domain features were extracted from each EEG signal per subject. The classification was performed using the extreme Gradient Boosting (XGBoost) classifier. We varied the number of EEG signal segments per subject from 5 to 127 with an increment of 5 segments per trial. Finally, the performance parameters such as accuracy, sensitivity, specificity, precision and F-measure were obtained in each case for the biometric authentication system using the test data. Our model achieved the highest accuracy of 100% when more than 75 EEG signals per subject were considered for the analysis. We also identified alpha band power as the most efficient feature for authentication. Our results show that EEG signals can be effectively used for personal identification and authentication.https://doi.org/10.1515/cdbme-2023-1173biometrics authenticationbiosignalelectroencephalographymachine learningxgboost
spellingShingle Jeswani Devesh
Kumar Govarthan Parveen
Selvaraj Abirami
Bobby Thomas Christy
Thomas John
Agastinose Ronickom Jac Fredo
A feasibility study on using EEG for Biometric Trait Authentication System
Current Directions in Biomedical Engineering
biometrics authentication
biosignal
electroencephalography
machine learning
xgboost
title A feasibility study on using EEG for Biometric Trait Authentication System
title_full A feasibility study on using EEG for Biometric Trait Authentication System
title_fullStr A feasibility study on using EEG for Biometric Trait Authentication System
title_full_unstemmed A feasibility study on using EEG for Biometric Trait Authentication System
title_short A feasibility study on using EEG for Biometric Trait Authentication System
title_sort feasibility study on using eeg for biometric trait authentication system
topic biometrics authentication
biosignal
electroencephalography
machine learning
xgboost
url https://doi.org/10.1515/cdbme-2023-1173
work_keys_str_mv AT jeswanidevesh afeasibilitystudyonusingeegforbiometrictraitauthenticationsystem
AT kumargovarthanparveen afeasibilitystudyonusingeegforbiometrictraitauthenticationsystem
AT selvarajabirami afeasibilitystudyonusingeegforbiometrictraitauthenticationsystem
AT bobbythomaschristy afeasibilitystudyonusingeegforbiometrictraitauthenticationsystem
AT thomasjohn afeasibilitystudyonusingeegforbiometrictraitauthenticationsystem
AT agastinoseronickomjacfredo afeasibilitystudyonusingeegforbiometrictraitauthenticationsystem
AT jeswanidevesh feasibilitystudyonusingeegforbiometrictraitauthenticationsystem
AT kumargovarthanparveen feasibilitystudyonusingeegforbiometrictraitauthenticationsystem
AT selvarajabirami feasibilitystudyonusingeegforbiometrictraitauthenticationsystem
AT bobbythomaschristy feasibilitystudyonusingeegforbiometrictraitauthenticationsystem
AT thomasjohn feasibilitystudyonusingeegforbiometrictraitauthenticationsystem
AT agastinoseronickomjacfredo feasibilitystudyonusingeegforbiometrictraitauthenticationsystem