Source Data Selection for Brain–Computer Interfaces Based on Simple Features
(2026) In IEEE Access 14. p.36191-36201- Abstract
Carefully selecting the source data is crucial to achieve high performance of transfer learning methods for brain–computer interfaces (BCIs). Especially so in settings where a large amount of source data is available, and finding the optimal source is not computationally feasible. This paper presents a novel method for source selection, the so-called Transfer Performance Predictor (TPP) method. The TPP method is based on computationally simple features, a choice made to enable real-time implementation and reduce calibration time. The presented method outperforms other comparable source selection methods in BCI settings where a large amount of source data is available. By using the TPP method, source selection can be performed quickly... (More)
Carefully selecting the source data is crucial to achieve high performance of transfer learning methods for brain–computer interfaces (BCIs). Especially so in settings where a large amount of source data is available, and finding the optimal source is not computationally feasible. This paper presents a novel method for source selection, the so-called Transfer Performance Predictor (TPP) method. The TPP method is based on computationally simple features, a choice made to enable real-time implementation and reduce calibration time. The presented method outperforms other comparable source selection methods in BCI settings where a large amount of source data is available. By using the TPP method, source selection can be performed quickly with good results for transfer learning performance, which means that the BCI calibration time can be reduced and a new target user can more quickly start using the BCI.
(Less)
- author
- Heskebeck, Frida
LU
; Bergeling, Carolina
LU
and Bernhardsson, Bo
LU
- organization
- publishing date
- 2026
- type
- Contribution to journal
- publication status
- published
- subject
- keywords
- Brain–computer interface, calibration, cross subject, machine learning, Riemannian geometry, source data selection, transfer learning
- in
- IEEE Access
- volume
- 14
- pages
- 11 pages
- publisher
- IEEE - Institute of Electrical and Electronics Engineers Inc.
- external identifiers
-
- scopus:105032130187
- ISSN
- 2169-3536
- DOI
- 10.1109/ACCESS.2026.3670905
- language
- English
- LU publication?
- yes
- id
- eac7ae52-e476-415b-a9a8-ef56000e31d4
- date added to LUP
- 2026-04-20 12:58:00
- date last changed
- 2026-04-20 12:58:34
@article{eac7ae52-e476-415b-a9a8-ef56000e31d4,
abstract = {{<p>Carefully selecting the source data is crucial to achieve high performance of transfer learning methods for brain–computer interfaces (BCIs). Especially so in settings where a large amount of source data is available, and finding the optimal source is not computationally feasible. This paper presents a novel method for source selection, the so-called Transfer Performance Predictor (TPP) method. The TPP method is based on computationally simple features, a choice made to enable real-time implementation and reduce calibration time. The presented method outperforms other comparable source selection methods in BCI settings where a large amount of source data is available. By using the TPP method, source selection can be performed quickly with good results for transfer learning performance, which means that the BCI calibration time can be reduced and a new target user can more quickly start using the BCI.</p>}},
author = {{Heskebeck, Frida and Bergeling, Carolina and Bernhardsson, Bo}},
issn = {{2169-3536}},
keywords = {{Brain–computer interface; calibration; cross subject; machine learning; Riemannian geometry; source data selection; transfer learning}},
language = {{eng}},
pages = {{36191--36201}},
publisher = {{IEEE - Institute of Electrical and Electronics Engineers Inc.}},
series = {{IEEE Access}},
title = {{Source Data Selection for Brain–Computer Interfaces Based on Simple Features}},
url = {{http://dx.doi.org/10.1109/ACCESS.2026.3670905}},
doi = {{10.1109/ACCESS.2026.3670905}},
volume = {{14}},
year = {{2026}},
}