Fine-Tuning EEG Channel Utilization for Emotionally Stimulated Biometric Authentication

Biometric authentication relies on distinct biological traits of individuals to validate their identity, enhancing security measures. However, variations in an individual’s emotional state can impact the reliability of the biometric system. In this study, we propose a novel pipeline to ev...

Full description

Saved in:
Bibliographic Details
Main Authors: Chetan Rakshe, Christy Bobby Thomas, Mohanavelu Kalathe, Vanteemar S. Sreeraj, Ganesan Venkatasubramanian, Deepesh Kumar, A. Amalin Prince, Jac Fredo Agastinose Ronickom
Format: Article
Language:English
Published: IEEE 2025-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/10876141/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850189786647625728
author Chetan Rakshe
Christy Bobby Thomas
Mohanavelu Kalathe
Vanteemar S. Sreeraj
Ganesan Venkatasubramanian
Deepesh Kumar
A. Amalin Prince
Jac Fredo Agastinose Ronickom
author_facet Chetan Rakshe
Christy Bobby Thomas
Mohanavelu Kalathe
Vanteemar S. Sreeraj
Ganesan Venkatasubramanian
Deepesh Kumar
A. Amalin Prince
Jac Fredo Agastinose Ronickom
author_sort Chetan Rakshe
collection DOAJ
description Biometric authentication relies on distinct biological traits of individuals to validate their identity, enhancing security measures. However, variations in an individual’s emotional state can impact the reliability of the biometric system. In this study, we propose a novel pipeline to evaluate electroencephalography (EEG)-based biometric system across different emotional states and optimize critical brain regions using machine learning algorithms. EEG signals from the DEAP dataset were classified into four emotional states: HAHV, HALV, LALV, and LAHV. We extracted a comprehensive set of statistical, time, frequency, entropy, fractal, spectral, and shape features from each channel. Machine learning classifiers, including Random Forest, Gradient Boosting, Extreme Gradient Boosting, LightGBM, CatBoost, and Bagging, were used for participant authentication. Our results revealed that the CatBoost classifier performed well across all stimuli with average accuracies of 84%, 85%, 86%, and 83% for HAHV, HALV, LALV, and LAHV, respectively. We found that features from channels FC1, Fz, C4 & Pz, and FC1 significantly contributed to EEG authentication on stimuli such as HAHV, HALV, LALV, and LAHV, respectively. Features such as skewness and the theta-to-alpha frequency band ratio consistently performed well across stimuli, demonstrating EEG signals’ potential for robust biometric authentication by addressing emotional variations.
format Article
id doaj-art-fa0fe7a1a4ec438cad7013c19fe97eb4
institution OA Journals
issn 2169-3536
language English
publishDate 2025-01-01
publisher IEEE
record_format Article
series IEEE Access
spelling doaj-art-fa0fe7a1a4ec438cad7013c19fe97eb42025-08-20T02:15:32ZengIEEEIEEE Access2169-35362025-01-0113275372754910.1109/ACCESS.2025.353950210876141Fine-Tuning EEG Channel Utilization for Emotionally Stimulated Biometric AuthenticationChetan Rakshe0https://orcid.org/0000-0003-3354-4998Christy Bobby Thomas1https://orcid.org/0000-0002-7691-8120Mohanavelu Kalathe2https://orcid.org/0000-0002-0840-0346Vanteemar S. Sreeraj3Ganesan Venkatasubramanian4https://orcid.org/0000-0002-0949-898XDeepesh Kumar5https://orcid.org/0000-0002-5572-3391A. Amalin Prince6https://orcid.org/0000-0002-4471-9979Jac Fredo Agastinose Ronickom7https://orcid.org/0000-0001-5759-6632Computational Neuroscience and Biology Laboratory, School of Biomedical Engineering, Indian Institute of Technology (BHU), Varanasi, IndiaDepartment of Electronic and Communication Engineering, M. S. Ramaiah University of Applied Sciences, Bengaluru, IndiaDefence Bio-Engineering and Electro Medical Laboratory, DRDO, Ministry of Defence, Bangalore, IndiaNational Institute of Mental Health and Neurosciences (NIMHANS), Bengaluru, IndiaTranslational Psychiatry Laboratory, National Institute of Mental Health and Neurosciences (NIMHANS), Bengaluru, IndiaComputational Neuroscience and Biology Laboratory, School of Biomedical Engineering, Indian Institute of Technology (BHU), Varanasi, IndiaDepartment of Electrical and Electronics Engineering, BITS Pilani, K K Birla Goa Campus, Zuarinagar, Goa, IndiaComputational Neuroscience and Biology Laboratory, School of Biomedical Engineering, Indian Institute of Technology (BHU), Varanasi, IndiaBiometric authentication relies on distinct biological traits of individuals to validate their identity, enhancing security measures. However, variations in an individual’s emotional state can impact the reliability of the biometric system. In this study, we propose a novel pipeline to evaluate electroencephalography (EEG)-based biometric system across different emotional states and optimize critical brain regions using machine learning algorithms. EEG signals from the DEAP dataset were classified into four emotional states: HAHV, HALV, LALV, and LAHV. We extracted a comprehensive set of statistical, time, frequency, entropy, fractal, spectral, and shape features from each channel. Machine learning classifiers, including Random Forest, Gradient Boosting, Extreme Gradient Boosting, LightGBM, CatBoost, and Bagging, were used for participant authentication. Our results revealed that the CatBoost classifier performed well across all stimuli with average accuracies of 84%, 85%, 86%, and 83% for HAHV, HALV, LALV, and LAHV, respectively. We found that features from channels FC1, Fz, C4 & Pz, and FC1 significantly contributed to EEG authentication on stimuli such as HAHV, HALV, LALV, and LAHV, respectively. Features such as skewness and the theta-to-alpha frequency band ratio consistently performed well across stimuli, demonstrating EEG signals’ potential for robust biometric authentication by addressing emotional variations.https://ieeexplore.ieee.org/document/10876141/Biometricelectroencephalographyemotionsbrain locationmachine learning
spellingShingle Chetan Rakshe
Christy Bobby Thomas
Mohanavelu Kalathe
Vanteemar S. Sreeraj
Ganesan Venkatasubramanian
Deepesh Kumar
A. Amalin Prince
Jac Fredo Agastinose Ronickom
Fine-Tuning EEG Channel Utilization for Emotionally Stimulated Biometric Authentication
IEEE Access
Biometric
electroencephalography
emotions
brain location
machine learning
title Fine-Tuning EEG Channel Utilization for Emotionally Stimulated Biometric Authentication
title_full Fine-Tuning EEG Channel Utilization for Emotionally Stimulated Biometric Authentication
title_fullStr Fine-Tuning EEG Channel Utilization for Emotionally Stimulated Biometric Authentication
title_full_unstemmed Fine-Tuning EEG Channel Utilization for Emotionally Stimulated Biometric Authentication
title_short Fine-Tuning EEG Channel Utilization for Emotionally Stimulated Biometric Authentication
title_sort fine tuning eeg channel utilization for emotionally stimulated biometric authentication
topic Biometric
electroencephalography
emotions
brain location
machine learning
url https://ieeexplore.ieee.org/document/10876141/
work_keys_str_mv AT chetanrakshe finetuningeegchannelutilizationforemotionallystimulatedbiometricauthentication
AT christybobbythomas finetuningeegchannelutilizationforemotionallystimulatedbiometricauthentication
AT mohanavelukalathe finetuningeegchannelutilizationforemotionallystimulatedbiometricauthentication
AT vanteemarssreeraj finetuningeegchannelutilizationforemotionallystimulatedbiometricauthentication
AT ganesanvenkatasubramanian finetuningeegchannelutilizationforemotionallystimulatedbiometricauthentication
AT deepeshkumar finetuningeegchannelutilizationforemotionallystimulatedbiometricauthentication
AT aamalinprince finetuningeegchannelutilizationforemotionallystimulatedbiometricauthentication
AT jacfredoagastinoseronickom finetuningeegchannelutilizationforemotionallystimulatedbiometricauthentication