Subspace techniques for task-independent EEG person identification
© 2019 IEEE. There has been a growing interest in studying electroencephalography signals (EEG) as a possible biometric. The brain signals captured by EEG are rich and carry information related to the individual, tasks being performed, mental state, and other channel/measurement noise due to session...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Institute of Electrical and Electronics Engineers (IEEE)
2021
|
| Online Access: | https://hdl.handle.net/1721.1/138332 |
| _version_ | 1826206381487685632 |
|---|---|
| author | Kumar, Mari Ganesh Saranya, MS Narayanan, Shrikanth Sur, Mriganka Murthy, Hema A |
| author_facet | Kumar, Mari Ganesh Saranya, MS Narayanan, Shrikanth Sur, Mriganka Murthy, Hema A |
| author_sort | Kumar, Mari Ganesh |
| collection | MIT |
| description | © 2019 IEEE. There has been a growing interest in studying electroencephalography signals (EEG) as a possible biometric. The brain signals captured by EEG are rich and carry information related to the individual, tasks being performed, mental state, and other channel/measurement noise due to session variability and artifacts. To effectively extract person-specific signatures present in EEG, it is necessary to define a subspace that enhances the biometric information and suppresses other nuisance factors. i-vector and x-vector are state-of-art subspace techniques used in speaker recognition. In this paper, novel modifications are proposed for both frameworks to project person-specific signatures from multi-channel EEG into a subspace. The modified i-vector and x-vector systems outperform baseline i-vector and x-vector systems with an absolute improvement of 10.5% and 15.9%, respectively. |
| first_indexed | 2024-09-23T13:28:17Z |
| format | Article |
| id | mit-1721.1/138332 |
| institution | Massachusetts Institute of Technology |
| language | English |
| last_indexed | 2024-09-23T13:28:17Z |
| publishDate | 2021 |
| publisher | Institute of Electrical and Electronics Engineers (IEEE) |
| record_format | dspace |
| spelling | mit-1721.1/1383322021-12-07T03:16:45Z Subspace techniques for task-independent EEG person identification Kumar, Mari Ganesh Saranya, MS Narayanan, Shrikanth Sur, Mriganka Murthy, Hema A © 2019 IEEE. There has been a growing interest in studying electroencephalography signals (EEG) as a possible biometric. The brain signals captured by EEG are rich and carry information related to the individual, tasks being performed, mental state, and other channel/measurement noise due to session variability and artifacts. To effectively extract person-specific signatures present in EEG, it is necessary to define a subspace that enhances the biometric information and suppresses other nuisance factors. i-vector and x-vector are state-of-art subspace techniques used in speaker recognition. In this paper, novel modifications are proposed for both frameworks to project person-specific signatures from multi-channel EEG into a subspace. The modified i-vector and x-vector systems outperform baseline i-vector and x-vector systems with an absolute improvement of 10.5% and 15.9%, respectively. 2021-12-06T18:15:45Z 2021-12-06T18:15:45Z 2019 2021-12-06T18:12:12Z Article http://purl.org/eprint/type/ConferencePaper https://hdl.handle.net/1721.1/138332 Kumar, Mari Ganesh, Saranya, MS, Narayanan, Shrikanth, Sur, Mriganka and Murthy, Hema A. 2019. "Subspace techniques for task-independent EEG person identification." Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS, 2019. en 10.1109/EMBC.2019.8857426 Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS Creative Commons Attribution-Noncommercial-Share Alike http://creativecommons.org/licenses/by-nc-sa/4.0/ application/pdf Institute of Electrical and Electronics Engineers (IEEE) Other repository |
| spellingShingle | Kumar, Mari Ganesh Saranya, MS Narayanan, Shrikanth Sur, Mriganka Murthy, Hema A Subspace techniques for task-independent EEG person identification |
| title | Subspace techniques for task-independent EEG person identification |
| title_full | Subspace techniques for task-independent EEG person identification |
| title_fullStr | Subspace techniques for task-independent EEG person identification |
| title_full_unstemmed | Subspace techniques for task-independent EEG person identification |
| title_short | Subspace techniques for task-independent EEG person identification |
| title_sort | subspace techniques for task independent eeg person identification |
| url | https://hdl.handle.net/1721.1/138332 |
| work_keys_str_mv | AT kumarmariganesh subspacetechniquesfortaskindependenteegpersonidentification AT saranyams subspacetechniquesfortaskindependenteegpersonidentification AT narayananshrikanth subspacetechniquesfortaskindependenteegpersonidentification AT surmriganka subspacetechniquesfortaskindependenteegpersonidentification AT murthyhemaa subspacetechniquesfortaskindependenteegpersonidentification |