Source Data Selection for Brain-Computer Interfaces based on Simple Features
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866929552132931584 |
|---|---|
| author | Heskebeck, Frida Bergeling, Carolina Bernhardsson, Bo |
| author_facet | Heskebeck, Frida Bergeling, Carolina Bernhardsson, Bo |
| contents | This paper demonstrates that simple features available during the calibration of a brain-computer interface can be utilized for source data selection to improve the performance of the brain-computer interface for a new target user through transfer learning. To support this, a public motor imagery dataset is used for analysis, and a method called the Transfer Performance Predictor method is presented. The simple features are based on the covariance matrices of the data and the Riemannian distance between them. The Transfer Performance Predictor method outperforms other source data selection methods as it selects source data that gives a better transfer learning performance for the target users. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2410_02360 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Source Data Selection for Brain-Computer Interfaces based on Simple Features Heskebeck, Frida Bergeling, Carolina Bernhardsson, Bo Human-Computer Interaction Machine Learning This paper demonstrates that simple features available during the calibration of a brain-computer interface can be utilized for source data selection to improve the performance of the brain-computer interface for a new target user through transfer learning. To support this, a public motor imagery dataset is used for analysis, and a method called the Transfer Performance Predictor method is presented. The simple features are based on the covariance matrices of the data and the Riemannian distance between them. The Transfer Performance Predictor method outperforms other source data selection methods as it selects source data that gives a better transfer learning performance for the target users. |
| title | Source Data Selection for Brain-Computer Interfaces based on Simple Features |
| topic | Human-Computer Interaction Machine Learning |
| url | https://arxiv.org/abs/2410.02360 |