A Personalized User Authentication System Based on EEG Signals
Conventional biometrics have been employed in high-security user-authentication systems for over 20 years now. However, some of these modalities face low-security issues in common practice. Brainwave-based user authentication has emerged as a promising alternative method, as it overcomes some of the...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-09-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/22/18/6929 |
| _version_ | 1797482576916512768 |
|---|---|
| author | Christos Stergiadis Vasiliki-Despoina Kostaridou Simos Veloudis Dimitrios Kazis Manousos A. Klados |
| author_facet | Christos Stergiadis Vasiliki-Despoina Kostaridou Simos Veloudis Dimitrios Kazis Manousos A. Klados |
| author_sort | Christos Stergiadis |
| collection | DOAJ |
| description | Conventional biometrics have been employed in high-security user-authentication systems for over 20 years now. However, some of these modalities face low-security issues in common practice. Brainwave-based user authentication has emerged as a promising alternative method, as it overcomes some of these drawbacks and allows for continuous user authentication. In the present study, we address the problem of individual user variability, by proposing a data-driven Electroencephalography (EEG)-based authentication method. We introduce machine learning techniques, in order to reveal the optimal classification algorithm that best fits the data of each individual user, in a fast and efficient manner. A set of 15 power spectral features (delta, theta, lower alpha, higher alpha, and alpha) is extracted from three EEG channels. The results show that our approach can reliably grant or deny access to the user (mean accuracy of 95.6%), while at the same time poses a viable option for real-time applications, as the total time of the training procedure was kept under one minute. |
| first_indexed | 2024-03-09T22:34:23Z |
| format | Article |
| id | doaj.art-fc0bf482a8794da790c7b1d86a2a3321 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-09T22:34:23Z |
| publishDate | 2022-09-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-fc0bf482a8794da790c7b1d86a2a33212023-11-23T18:51:36ZengMDPI AGSensors1424-82202022-09-012218692910.3390/s22186929A Personalized User Authentication System Based on EEG SignalsChristos Stergiadis0Vasiliki-Despoina Kostaridou1Simos Veloudis2Dimitrios Kazis3Manousos A. Klados4Department of Psychology, City College, University of York Europe Campus, 54622 Thessaloniki, GreeceDepartment of Psychology, City College, University of York Europe Campus, 54622 Thessaloniki, GreeceDepartment of Computer Science, City College, University of York Europe Campus, 54622 Thessaloniki, Greece3rd Department of Neurology, Aristotle University of Thessaloniki, Exochi, 57010 Thessaloniki, GreeceDepartment of Psychology, City College, University of York Europe Campus, 54622 Thessaloniki, GreeceConventional biometrics have been employed in high-security user-authentication systems for over 20 years now. However, some of these modalities face low-security issues in common practice. Brainwave-based user authentication has emerged as a promising alternative method, as it overcomes some of these drawbacks and allows for continuous user authentication. In the present study, we address the problem of individual user variability, by proposing a data-driven Electroencephalography (EEG)-based authentication method. We introduce machine learning techniques, in order to reveal the optimal classification algorithm that best fits the data of each individual user, in a fast and efficient manner. A set of 15 power spectral features (delta, theta, lower alpha, higher alpha, and alpha) is extracted from three EEG channels. The results show that our approach can reliably grant or deny access to the user (mean accuracy of 95.6%), while at the same time poses a viable option for real-time applications, as the total time of the training procedure was kept under one minute.https://www.mdpi.com/1424-8220/22/18/6929biometricsEEGsecurityuser authenticationmachine learningapplied neuroscience |
| spellingShingle | Christos Stergiadis Vasiliki-Despoina Kostaridou Simos Veloudis Dimitrios Kazis Manousos A. Klados A Personalized User Authentication System Based on EEG Signals Sensors biometrics EEG security user authentication machine learning applied neuroscience |
| title | A Personalized User Authentication System Based on EEG Signals |
| title_full | A Personalized User Authentication System Based on EEG Signals |
| title_fullStr | A Personalized User Authentication System Based on EEG Signals |
| title_full_unstemmed | A Personalized User Authentication System Based on EEG Signals |
| title_short | A Personalized User Authentication System Based on EEG Signals |
| title_sort | personalized user authentication system based on eeg signals |
| topic | biometrics EEG security user authentication machine learning applied neuroscience |
| url | https://www.mdpi.com/1424-8220/22/18/6929 |
| work_keys_str_mv | AT christosstergiadis apersonalizeduserauthenticationsystembasedoneegsignals AT vasilikidespoinakostaridou apersonalizeduserauthenticationsystembasedoneegsignals AT simosveloudis apersonalizeduserauthenticationsystembasedoneegsignals AT dimitrioskazis apersonalizeduserauthenticationsystembasedoneegsignals AT manousosaklados apersonalizeduserauthenticationsystembasedoneegsignals AT christosstergiadis personalizeduserauthenticationsystembasedoneegsignals AT vasilikidespoinakostaridou personalizeduserauthenticationsystembasedoneegsignals AT simosveloudis personalizeduserauthenticationsystembasedoneegsignals AT dimitrioskazis personalizeduserauthenticationsystembasedoneegsignals AT manousosaklados personalizeduserauthenticationsystembasedoneegsignals |