Chronic Study on Brainwave Authentication in a Real-Life Setting: An LSTM-Based Bagging Approach
With the advent of the digital age, concern about how to secure authorized access to sensitive data is increasing. Besides traditional authentication methods, there is an interest in biometric traits such as fingerprints, the iris, facial characteristics, and, recently, brainwaves, primarily based o...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-10-01
|
| Series: | Biosensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2079-6374/11/10/404 |
| _version_ | 1797515179420811264 |
|---|---|
| author | Liuyin Yang Arno Libert Marc M. Van Hulle |
| author_facet | Liuyin Yang Arno Libert Marc M. Van Hulle |
| author_sort | Liuyin Yang |
| collection | DOAJ |
| description | With the advent of the digital age, concern about how to secure authorized access to sensitive data is increasing. Besides traditional authentication methods, there is an interest in biometric traits such as fingerprints, the iris, facial characteristics, and, recently, brainwaves, primarily based on electroencephalography (EEG). Current work on EEG-based authentication focuses on acute recordings in laboratory settings using high-end equipment, typically equipped with 64 channels and operating at a high sampling rate. In this work, we validated the feasibility of EEG-based authentication in a real-world, out-of-laboratory setting using a commercial dry-electrode EEG headset and chronic recordings on a population of 15 healthy people. We used an LSTM-based network with bootstrap aggregating (bagging) to decode our recordings in response to a multitask scheme consisting of performed and imagined motor tasks, and showed that it improved the performance of the standard LSTM approach. We achieved an authentication accuracy, false acceptance rate (FAR), and false rejection rate (FRR) of 92.6%, 2.5%, and 5.0% for the performed motor task; 92.5%, 2.6%, and 4.9% for the imagined motor task; and 93.0%, 1.9%, and 5.1% for the combined tasks, respectively. We recommend the proposed method for time- and data-limited scenarios. |
| first_indexed | 2024-03-10T06:41:52Z |
| format | Article |
| id | doaj.art-dabe983afc764aaea7e4ef52f115c767 |
| institution | Directory Open Access Journal |
| issn | 2079-6374 |
| language | English |
| last_indexed | 2024-03-10T06:41:52Z |
| publishDate | 2021-10-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Biosensors |
| spelling | doaj.art-dabe983afc764aaea7e4ef52f115c7672023-11-22T17:36:14ZengMDPI AGBiosensors2079-63742021-10-01111040410.3390/bios11100404Chronic Study on Brainwave Authentication in a Real-Life Setting: An LSTM-Based Bagging ApproachLiuyin Yang0Arno Libert1Marc M. Van Hulle2Department of Neuropsychology and Physiology, KU Leuven, 3000 Leuven, BelgiumDepartment of Neuropsychology and Physiology, KU Leuven, 3000 Leuven, BelgiumDepartment of Neuropsychology and Physiology, KU Leuven, 3000 Leuven, BelgiumWith the advent of the digital age, concern about how to secure authorized access to sensitive data is increasing. Besides traditional authentication methods, there is an interest in biometric traits such as fingerprints, the iris, facial characteristics, and, recently, brainwaves, primarily based on electroencephalography (EEG). Current work on EEG-based authentication focuses on acute recordings in laboratory settings using high-end equipment, typically equipped with 64 channels and operating at a high sampling rate. In this work, we validated the feasibility of EEG-based authentication in a real-world, out-of-laboratory setting using a commercial dry-electrode EEG headset and chronic recordings on a population of 15 healthy people. We used an LSTM-based network with bootstrap aggregating (bagging) to decode our recordings in response to a multitask scheme consisting of performed and imagined motor tasks, and showed that it improved the performance of the standard LSTM approach. We achieved an authentication accuracy, false acceptance rate (FAR), and false rejection rate (FRR) of 92.6%, 2.5%, and 5.0% for the performed motor task; 92.5%, 2.6%, and 4.9% for the imagined motor task; and 93.0%, 1.9%, and 5.1% for the combined tasks, respectively. We recommend the proposed method for time- and data-limited scenarios.https://www.mdpi.com/2079-6374/11/10/404EEG-based authenticationmultitask authenticationreal-world settingEEG headset |
| spellingShingle | Liuyin Yang Arno Libert Marc M. Van Hulle Chronic Study on Brainwave Authentication in a Real-Life Setting: An LSTM-Based Bagging Approach Biosensors EEG-based authentication multitask authentication real-world setting EEG headset |
| title | Chronic Study on Brainwave Authentication in a Real-Life Setting: An LSTM-Based Bagging Approach |
| title_full | Chronic Study on Brainwave Authentication in a Real-Life Setting: An LSTM-Based Bagging Approach |
| title_fullStr | Chronic Study on Brainwave Authentication in a Real-Life Setting: An LSTM-Based Bagging Approach |
| title_full_unstemmed | Chronic Study on Brainwave Authentication in a Real-Life Setting: An LSTM-Based Bagging Approach |
| title_short | Chronic Study on Brainwave Authentication in a Real-Life Setting: An LSTM-Based Bagging Approach |
| title_sort | chronic study on brainwave authentication in a real life setting an lstm based bagging approach |
| topic | EEG-based authentication multitask authentication real-world setting EEG headset |
| url | https://www.mdpi.com/2079-6374/11/10/404 |
| work_keys_str_mv | AT liuyinyang chronicstudyonbrainwaveauthenticationinareallifesettinganlstmbasedbaggingapproach AT arnolibert chronicstudyonbrainwaveauthenticationinareallifesettinganlstmbasedbaggingapproach AT marcmvanhulle chronicstudyonbrainwaveauthenticationinareallifesettinganlstmbasedbaggingapproach |