Multimodal EEG and Keystroke Dynamics Based Biometric System Using Machine Learning Algorithms
Authors:
- Arafat RahmanARArafat Rahman
- Muhammad E. H. ChowdhuryMuhammad E. H. Chowdhury
- Amith KhandakarAKAmith Khandakar
- Serkan KiranyazSKSerkan Kiranyaz
- Mamun Bin Ibne ReazMamun Bin Ibne Reaz
- Mohammad Tariqul IslamMIMohammad Tariqul Islam
- Maymouna EzeddinMEMaymouna Ezeddin
- Muhammad Abdul KadirMKMuhammad Abdul Kadir
Open Access
- 28 June 2021
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 9, 94625-94643
Abstract
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.Keywords
All Related Versions
Funding Information
- Qatar National Research Fund (NPRP12S-0227-190164, UREP23-027-2-012)
This publication has 31 references indexed in Scilit:
- CEREBRE: A Novel Method for Very High Accuracy Event-Related Potential Biometric IdentificationIEEE Transactions on Information Forensics and Security, 2016
- Towards EEG biometrics: pattern matching approaches for user identification2015
- Electronic Citizen Identities and Strong AuthenticationLecture Notes in Computer Science, 2015
- An EEG-Based Biometric System Using Eigenvector Centrality in Resting State Brain NetworksIEEE Signal Processing Letters, 2014
- HeartCode: A novel binary ECG-based template2014
- Design of a Hamming-distance classifier for ECG biometrics2013
- Improvement of EEG Signal Acquisition: An Electrical Aspect for State of the Art of Front EndComputational Intelligence and Neuroscience, 2010
- Matplotlib: A 2D Graphics EnvironmentComputing in Science & Engineering, 2007
- Classification of EEG signals using the wavelet transform2002
- EEG analysis based on time domain propertiesElectroencephalography and Clinical Neurophysiology, 1970