Multimodal EEG and Keystroke Dynamics Based Biometric System Using Machine Learning Algorithms

<p dir="ltr">Electroencephalography (EEG) based biometric systems are gaining attention for their anti-spoofing capability but lack accuracy due to signal variability at different psychological and physiological conditions. On the other hand, keystroke dynamics-based systems achieve...

وصف كامل

محفوظ في:
التفاصيل البيبلوغرافية
المؤلف الرئيسي: Arafat Rahman (8065562) (author)
مؤلفون آخرون: Muhammad E. H. Chowdhury (14150526) (author), Amith Khandakar (14151981) (author), Serkan Kiranyaz (3762058) (author), Kh Shahriya Zaman (16891365) (author), Mamun Bin Ibne Reaz (16875933) (author), Mohammad Tariqul Islam (7854059) (author), Maymouna Ezeddin (16891368) (author), Muhammad Abdul Kadir (16869963) (author)
منشور في: 2021
الموضوعات:
الوسوم: إضافة وسم
لا توجد وسوم, كن أول من يضع وسما على هذه التسجيلة!
_version_ 1864513560269291520
author Arafat Rahman (8065562)
author2 Muhammad E. H. Chowdhury (14150526)
Amith Khandakar (14151981)
Serkan Kiranyaz (3762058)
Kh Shahriya Zaman (16891365)
Mamun Bin Ibne Reaz (16875933)
Mohammad Tariqul Islam (7854059)
Maymouna Ezeddin (16891368)
Muhammad Abdul Kadir (16869963)
author2_role author
author
author
author
author
author
author
author
author_facet Arafat Rahman (8065562)
Muhammad E. H. Chowdhury (14150526)
Amith Khandakar (14151981)
Serkan Kiranyaz (3762058)
Kh Shahriya Zaman (16891365)
Mamun Bin Ibne Reaz (16875933)
Mohammad Tariqul Islam (7854059)
Maymouna Ezeddin (16891368)
Muhammad Abdul Kadir (16869963)
author_role author
dc.creator.none.fl_str_mv Arafat Rahman (8065562)
Muhammad E. H. Chowdhury (14150526)
Amith Khandakar (14151981)
Serkan Kiranyaz (3762058)
Kh Shahriya Zaman (16891365)
Mamun Bin Ibne Reaz (16875933)
Mohammad Tariqul Islam (7854059)
Maymouna Ezeddin (16891368)
Muhammad Abdul Kadir (16869963)
dc.date.none.fl_str_mv 2021-06-28T00:00:00Z
dc.identifier.none.fl_str_mv 10.1109/access.2021.3092840
dc.relation.none.fl_str_mv https://figshare.com/articles/journal_contribution/Multimodal_EEG_and_Keystroke_Dynamics_Based_Biometric_System_Using_Machine_Learning_Algorithms/24042312
dc.rights.none.fl_str_mv CC BY 4.0
info:eu-repo/semantics/openAccess
dc.subject.none.fl_str_mv Biological sciences
Bioinformatics and computational biology
Engineering
Biomedical engineering
Information and computing sciences
Data management and data science
Machine learning
Electroencephalography
Authentication
Biometrics (access control)
Feature extraction
Machine learning
Headphones
Brain modeling
Biometric system
Electroencephalography (EEG)
Keystroke dynamics
Identification
Multimodal system
dc.title.none.fl_str_mv Multimodal EEG and Keystroke Dynamics Based Biometric System Using Machine Learning Algorithms
dc.type.none.fl_str_mv Text
Journal contribution
info:eu-repo/semantics/publishedVersion
text
contribution to journal
description <p dir="ltr">Electroencephalography (EEG) based biometric systems are gaining attention for their anti-spoofing capability but lack accuracy due to signal variability at different psychological and physiological conditions. On the other hand, keystroke dynamics-based systems achieve very high accuracy but have low anti-spoofing capability. To address these issues, a novel multimodal biometric system combining EEG and keystroke dynamics is proposed in this paper. A dataset was created by acquiring both keystroke dynamics and EEG signals simultaneously from 10 users. Each user participated in 500 trials at 10 different sessions (days) to replicate real-life signal variability. A machine learning classification pipeline is developed using multi-domain feature extraction (time, frequency, time-frequency), feature selection (Gini impurity), classifier design, and score level fusion. Different classifiers were trained, validated, and tested for two different classification experiments - personalized and generalized. For identification and authentication, 99.9% and 99.6% accuracies are achieved, respectively for the Random Forest classifier in 5 fold cross-validation. These results outperform the individual modalities with a significant margin (~5%). We also developed a binary template matching-based algorithm, which gives 93.64% accuracy 6X faster. The proposed method can be considered secure and reliable for any kind of biometric identification and authentication.</p><h2>Other Information</h2><p dir="ltr">Published in: IEEE Access<br>License: <a href="https://creativecommons.org/licenses/by/4.0/legalcode" target="_blank">https://creativecommons.org/licenses/by/4.0/</a><br>See article on publisher's website: <a href="https://dx.doi.org/10.1109/access.2021.3092840" target="_blank">https://dx.doi.org/10.1109/access.2021.3092840</a></p>
eu_rights_str_mv openAccess
id Manara2_0d5f04b8ff598862300fb66aad324aef
identifier_str_mv 10.1109/access.2021.3092840
network_acronym_str Manara2
network_name_str Manara2
oai_identifier_str oai:figshare.com:article/24042312
publishDate 2021
repository.mail.fl_str_mv
repository.name.fl_str_mv
repository_id_str
rights_invalid_str_mv CC BY 4.0
spelling Multimodal EEG and Keystroke Dynamics Based Biometric System Using Machine Learning AlgorithmsArafat Rahman (8065562)Muhammad E. H. Chowdhury (14150526)Amith Khandakar (14151981)Serkan Kiranyaz (3762058)Kh Shahriya Zaman (16891365)Mamun Bin Ibne Reaz (16875933)Mohammad Tariqul Islam (7854059)Maymouna Ezeddin (16891368)Muhammad Abdul Kadir (16869963)Biological sciencesBioinformatics and computational biologyEngineeringBiomedical engineeringInformation and computing sciencesData management and data scienceMachine learningElectroencephalographyAuthenticationBiometrics (access control)Feature extractionMachine learningHeadphonesBrain modelingBiometric systemElectroencephalography (EEG)Keystroke dynamicsIdentificationMultimodal system<p dir="ltr">Electroencephalography (EEG) based biometric systems are gaining attention for their anti-spoofing capability but lack accuracy due to signal variability at different psychological and physiological conditions. On the other hand, keystroke dynamics-based systems achieve very high accuracy but have low anti-spoofing capability. To address these issues, a novel multimodal biometric system combining EEG and keystroke dynamics is proposed in this paper. A dataset was created by acquiring both keystroke dynamics and EEG signals simultaneously from 10 users. Each user participated in 500 trials at 10 different sessions (days) to replicate real-life signal variability. A machine learning classification pipeline is developed using multi-domain feature extraction (time, frequency, time-frequency), feature selection (Gini impurity), classifier design, and score level fusion. Different classifiers were trained, validated, and tested for two different classification experiments - personalized and generalized. For identification and authentication, 99.9% and 99.6% accuracies are achieved, respectively for the Random Forest classifier in 5 fold cross-validation. These results outperform the individual modalities with a significant margin (~5%). We also developed a binary template matching-based algorithm, which gives 93.64% accuracy 6X faster. The proposed method can be considered secure and reliable for any kind of biometric identification and authentication.</p><h2>Other Information</h2><p dir="ltr">Published in: IEEE Access<br>License: <a href="https://creativecommons.org/licenses/by/4.0/legalcode" target="_blank">https://creativecommons.org/licenses/by/4.0/</a><br>See article on publisher's website: <a href="https://dx.doi.org/10.1109/access.2021.3092840" target="_blank">https://dx.doi.org/10.1109/access.2021.3092840</a></p>2021-06-28T00:00:00ZTextJournal contributioninfo:eu-repo/semantics/publishedVersiontextcontribution to journal10.1109/access.2021.3092840https://figshare.com/articles/journal_contribution/Multimodal_EEG_and_Keystroke_Dynamics_Based_Biometric_System_Using_Machine_Learning_Algorithms/24042312CC BY 4.0info:eu-repo/semantics/openAccessoai:figshare.com:article/240423122021-06-28T00:00:00Z
spellingShingle Multimodal EEG and Keystroke Dynamics Based Biometric System Using Machine Learning Algorithms
Arafat Rahman (8065562)
Biological sciences
Bioinformatics and computational biology
Engineering
Biomedical engineering
Information and computing sciences
Data management and data science
Machine learning
Electroencephalography
Authentication
Biometrics (access control)
Feature extraction
Machine learning
Headphones
Brain modeling
Biometric system
Electroencephalography (EEG)
Keystroke dynamics
Identification
Multimodal system
status_str publishedVersion
title Multimodal EEG and Keystroke Dynamics Based Biometric System Using Machine Learning Algorithms
title_full Multimodal EEG and Keystroke Dynamics Based Biometric System Using Machine Learning Algorithms
title_fullStr Multimodal EEG and Keystroke Dynamics Based Biometric System Using Machine Learning Algorithms
title_full_unstemmed Multimodal EEG and Keystroke Dynamics Based Biometric System Using Machine Learning Algorithms
title_short Multimodal EEG and Keystroke Dynamics Based Biometric System Using Machine Learning Algorithms
title_sort Multimodal EEG and Keystroke Dynamics Based Biometric System Using Machine Learning Algorithms
topic Biological sciences
Bioinformatics and computational biology
Engineering
Biomedical engineering
Information and computing sciences
Data management and data science
Machine learning
Electroencephalography
Authentication
Biometrics (access control)
Feature extraction
Machine learning
Headphones
Brain modeling
Biometric system
Electroencephalography (EEG)
Keystroke dynamics
Identification
Multimodal system