EEG-based biometric authentication using gamma band power during rest state
Electroencephalography (EEG), one of the most effective noninvasive methods for recording brain’s electrical activity, has widely been employed in the diagnosis of brain diseases for a few decades. Recently, the promising biometric potential of EEG, for developing person identification and authentic...
| Main Authors: | , |
|---|---|
| Other Authors: | |
| Format: | Journal Article |
| Language: | English |
| Published: |
2020
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/10356/141535 |
| _version_ | 1826125692529541120 |
|---|---|
| author | Thomas, Kavitha P. Vinod, Achutavarrier Prasad |
| author2 | School of Computer Science and Engineering |
| author_facet | School of Computer Science and Engineering Thomas, Kavitha P. Vinod, Achutavarrier Prasad |
| author_sort | Thomas, Kavitha P. |
| collection | NTU |
| description | Electroencephalography (EEG), one of the most effective noninvasive methods for recording brain’s electrical activity, has widely been employed in the diagnosis of brain diseases for a few decades. Recently, the promising biometric potential of EEG, for developing person identification and authentication systems, has also been explored. This paper presents the superior performance of power spectral density (PSD) features of gamma band (30–50 Hz) in biometric authentication, compared to delta, theta, alpha and beta band of EEG signals during rest state. The proposed authentication technique based on simple cross-correlation values of PSD features extracted from 19 EEG channels during eyes closed and eyes open rest state conditions among 109 subjects offers an equal error rate (EER) of 0.0196 which is better than the state-of-the-art method employing eigenvector centrality features extracted from gamma band of 64 EEG channels of the same dataset. The obtained results are promising, but further investigation is essential for exploring the subject-specific neural dynamics and stability of gamma waves and for optimizing the results. |
| first_indexed | 2024-10-01T06:40:31Z |
| format | Journal Article |
| id | ntu-10356/141535 |
| institution | Nanyang Technological University |
| language | English |
| last_indexed | 2024-10-01T06:40:31Z |
| publishDate | 2020 |
| record_format | dspace |
| spelling | ntu-10356/1415352020-06-09T03:26:41Z EEG-based biometric authentication using gamma band power during rest state Thomas, Kavitha P. Vinod, Achutavarrier Prasad School of Computer Science and Engineering Engineering::Computer science and engineering Biometric EEG Electroencephalography (EEG), one of the most effective noninvasive methods for recording brain’s electrical activity, has widely been employed in the diagnosis of brain diseases for a few decades. Recently, the promising biometric potential of EEG, for developing person identification and authentication systems, has also been explored. This paper presents the superior performance of power spectral density (PSD) features of gamma band (30–50 Hz) in biometric authentication, compared to delta, theta, alpha and beta band of EEG signals during rest state. The proposed authentication technique based on simple cross-correlation values of PSD features extracted from 19 EEG channels during eyes closed and eyes open rest state conditions among 109 subjects offers an equal error rate (EER) of 0.0196 which is better than the state-of-the-art method employing eigenvector centrality features extracted from gamma band of 64 EEG channels of the same dataset. The obtained results are promising, but further investigation is essential for exploring the subject-specific neural dynamics and stability of gamma waves and for optimizing the results. 2020-06-09T03:26:41Z 2020-06-09T03:26:41Z 2017 Journal Article Thomas, K. P., & Vinod, A. P. (2018). EEG-based biometric authentication using gamma band power during rest state. Circuits, Systems, and Signal Processing, 37(1), 277-289. doi:10.1007/s00034-017-0551-4 0278-081X https://hdl.handle.net/10356/141535 10.1007/s00034-017-0551-4 2-s2.0-85040028622 1 37 277 289 en Circuits, Systems, and Signal Processing © 2017 Springer Science+Business Media New York. All rights reserved. |
| spellingShingle | Engineering::Computer science and engineering Biometric EEG Thomas, Kavitha P. Vinod, Achutavarrier Prasad EEG-based biometric authentication using gamma band power during rest state |
| title | EEG-based biometric authentication using gamma band power during rest state |
| title_full | EEG-based biometric authentication using gamma band power during rest state |
| title_fullStr | EEG-based biometric authentication using gamma band power during rest state |
| title_full_unstemmed | EEG-based biometric authentication using gamma band power during rest state |
| title_short | EEG-based biometric authentication using gamma band power during rest state |
| title_sort | eeg based biometric authentication using gamma band power during rest state |
| topic | Engineering::Computer science and engineering Biometric EEG |
| url | https://hdl.handle.net/10356/141535 |
| work_keys_str_mv | AT thomaskavithap eegbasedbiometricauthenticationusinggammabandpowerduringreststate AT vinodachutavarrierprasad eegbasedbiometricauthenticationusinggammabandpowerduringreststate |