Recruiting neural field theory for data augmentation in a motor imagery brain–computer interface
We introduce a novel approach to training data augmentation in brain–computer interfaces (BCIs) using neural field theory (NFT) applied to EEG data from motor imagery tasks. BCIs often suffer from limited accuracy due to a limited amount of training data. To address this, we leveraged a corticothala...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2024-04-01
|
| Series: | Frontiers in Robotics and AI |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/frobt.2024.1362735/full |
| _version_ | 1797203114848157696 |
|---|---|
| author | Daniel Polyakov Daniel Polyakov Peter A. Robinson Eli J. Muller Oren Shriki Oren Shriki |
| author_facet | Daniel Polyakov Daniel Polyakov Peter A. Robinson Eli J. Muller Oren Shriki Oren Shriki |
| author_sort | Daniel Polyakov |
| collection | DOAJ |
| description | We introduce a novel approach to training data augmentation in brain–computer interfaces (BCIs) using neural field theory (NFT) applied to EEG data from motor imagery tasks. BCIs often suffer from limited accuracy due to a limited amount of training data. To address this, we leveraged a corticothalamic NFT model to generate artificial EEG time series as supplemental training data. We employed the BCI competition IV ‘2a’ dataset to evaluate this augmentation technique. For each individual, we fitted the model to common spatial patterns of each motor imagery class, jittered the fitted parameters, and generated time series for data augmentation. Our method led to significant accuracy improvements of over 2% in classifying the “total power” feature, but not in the case of the “Higuchi fractal dimension” feature. This suggests that the fit NFT model may more favorably represent one feature than the other. These findings pave the way for further exploration of NFT-based data augmentation, highlighting the benefits of biophysically accurate artificial data. |
| first_indexed | 2024-04-24T08:14:11Z |
| format | Article |
| id | doaj.art-a611c5f185da4ef8bf12cbcc2c704c3a |
| institution | Directory Open Access Journal |
| issn | 2296-9144 |
| language | English |
| last_indexed | 2024-04-24T08:14:11Z |
| publishDate | 2024-04-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Robotics and AI |
| spelling | doaj.art-a611c5f185da4ef8bf12cbcc2c704c3a2024-04-17T04:34:40ZengFrontiers Media S.A.Frontiers in Robotics and AI2296-91442024-04-011110.3389/frobt.2024.13627351362735Recruiting neural field theory for data augmentation in a motor imagery brain–computer interfaceDaniel Polyakov0Daniel Polyakov1Peter A. Robinson2Eli J. Muller3Oren Shriki4Oren Shriki5Department of Cognitive and Brain Sciences, Ben-Gurion University of the Negev, Be’er Sheva, IsraelAgricultural, Biological, Cognitive Robotics Initiative, Ben-Gurion University of the Negev, Be’er Sheva, IsraelSchool of Physics, The University of Sydney, Sydney, NSW, AustraliaBrain and Mind Centre, The University of Sydney, Sydney, NSW, AustraliaDepartment of Cognitive and Brain Sciences, Ben-Gurion University of the Negev, Be’er Sheva, IsraelAgricultural, Biological, Cognitive Robotics Initiative, Ben-Gurion University of the Negev, Be’er Sheva, IsraelWe introduce a novel approach to training data augmentation in brain–computer interfaces (BCIs) using neural field theory (NFT) applied to EEG data from motor imagery tasks. BCIs often suffer from limited accuracy due to a limited amount of training data. To address this, we leveraged a corticothalamic NFT model to generate artificial EEG time series as supplemental training data. We employed the BCI competition IV ‘2a’ dataset to evaluate this augmentation technique. For each individual, we fitted the model to common spatial patterns of each motor imagery class, jittered the fitted parameters, and generated time series for data augmentation. Our method led to significant accuracy improvements of over 2% in classifying the “total power” feature, but not in the case of the “Higuchi fractal dimension” feature. This suggests that the fit NFT model may more favorably represent one feature than the other. These findings pave the way for further exploration of NFT-based data augmentation, highlighting the benefits of biophysically accurate artificial data.https://www.frontiersin.org/articles/10.3389/frobt.2024.1362735/fullbrain-computer interface (BCI)EEGmotor imagerydata augmentationneural field theorycommon spatial pattern (CSP) |
| spellingShingle | Daniel Polyakov Daniel Polyakov Peter A. Robinson Eli J. Muller Oren Shriki Oren Shriki Recruiting neural field theory for data augmentation in a motor imagery brain–computer interface Frontiers in Robotics and AI brain-computer interface (BCI) EEG motor imagery data augmentation neural field theory common spatial pattern (CSP) |
| title | Recruiting neural field theory for data augmentation in a motor imagery brain–computer interface |
| title_full | Recruiting neural field theory for data augmentation in a motor imagery brain–computer interface |
| title_fullStr | Recruiting neural field theory for data augmentation in a motor imagery brain–computer interface |
| title_full_unstemmed | Recruiting neural field theory for data augmentation in a motor imagery brain–computer interface |
| title_short | Recruiting neural field theory for data augmentation in a motor imagery brain–computer interface |
| title_sort | recruiting neural field theory for data augmentation in a motor imagery brain computer interface |
| topic | brain-computer interface (BCI) EEG motor imagery data augmentation neural field theory common spatial pattern (CSP) |
| url | https://www.frontiersin.org/articles/10.3389/frobt.2024.1362735/full |
| work_keys_str_mv | AT danielpolyakov recruitingneuralfieldtheoryfordataaugmentationinamotorimagerybraincomputerinterface AT danielpolyakov recruitingneuralfieldtheoryfordataaugmentationinamotorimagerybraincomputerinterface AT peterarobinson recruitingneuralfieldtheoryfordataaugmentationinamotorimagerybraincomputerinterface AT elijmuller recruitingneuralfieldtheoryfordataaugmentationinamotorimagerybraincomputerinterface AT orenshriki recruitingneuralfieldtheoryfordataaugmentationinamotorimagerybraincomputerinterface AT orenshriki recruitingneuralfieldtheoryfordataaugmentationinamotorimagerybraincomputerinterface |