Overcoming brain non-stationarity: adaptive RLS classification for stable BCIs based on auditory evoked potentials
Journal of Neural Engineering · 01.08.2026 · 23 (4) · 046023
DOI: 10.1088/1741-2552/ae863e ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Neural Engineering, online erschienen am 15.07.2026. Verfasst von Dovilė Kurmanavičiūtė und 4 weiteren Autor:innen. Beteiligte Einrichtung: Department of Neuroscience and Biomedical Engineering, Aalto University, P.O. Box 12200, FI-00076 Aalto, Finland. Hauptthemen laut MEDLINE: Brain-Computer Interfaces, Evoked Potentials, Auditory, Electroencephalography, Brain. Die Arbeit nennt 72 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Business Finland.
Abstract (Originalsprache)
Objective. Brain–computer interfaces (BCIs) based on selective auditory attention aim to restore communication by decoding selective attention from auditory evoked potentials. Clinical translation of such BCIs requires maintaining sufficient decoding performance despite brain-state non-stationarity. Approach. We compared classifiers across four evaluation settings: offline baseline classifiers using shuffled 5-fold cross-validation; a causal classifier using a chronological 20%/80% calibration/test split; simulated real-time deployment with a static classifier calibrated on 20 trials; and simulated real-time deployment with an adaptive recursive least squares (RLS) classifier, evaluated within-subject and in a leave-one-subject-out (LOSO) setting. The analysis used 62-channel electroencephalography recorded from 25 healthy adults (18 retained after artifact rejection). Main results. The best offline baseline classifier, logistic regression with point-to-point features, achieved a mean ROC AUC of 0.75 and an estimated information transfer rate (ITR) of 2.46 bits min − 1 , derived from ROC AUC via a conservative heuristic. Under causal application, performance decreased to ROC AUC = 0.63 and ITR = 0.68 bits min − 1 . In simulated real-time deployment, static classification dropped further to ROC AUC = 0.51, whereas adaptive RLS improved ROC AUC to 0.68 and ITR from 0.14 bits min − 1 to 1.42 bits min − 1 ( p < 0.001 , Cohen’s d > 1.49 ). In the LOSO setting, RLS achieved ROC AUC = 0.57 and ITR = 0.86 bits min − 1 . The LOSO result further suggests that zero-calibration deployment is feasible, with personalization occurring trial-by-trial. Significance. Brain-state non-stationarity is a major driver of performance decline in auditory BCIs. Lightweight adaptive recalibration substantially restores real-time performance and supports the translational potential of ERP-based communication paradigms.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Neuroscience and Biomedical Engineering, Aalto University, P.O. Box 12200, FI-00076 Aalto, Finland.
- Aalto Neuroimaging Infrastructure, Aalto University, FI-00076 Aalto, Finland.
ORCID-Profile: Dovilė Kurmanavičiūtė, Matilda Makkonen, Ivan Zubarev, Olli-Pekka Kahilakoski, Lauri Parkkonen
Förderung
- Business Finland
Zitieren
APA
Kurmanavičiūtė, D., Makkonen, M., Zubarev, I., Kahilakoski, O. P., & Parkkonen, L. (2026). Overcoming brain non-stationarity: adaptive RLS classification for stable BCIs based on auditory evoked potentials. Journal of Neural Engineering, 23(4), 046023. https://doi.org/10.1088/1741-2552/ae863e
Vancouver
Kurmanavičiūtė D, Makkonen M, Zubarev I, Kahilakoski OP, Parkkonen L. Overcoming brain non-stationarity: adaptive RLS classification for stable BCIs based on auditory evoked potentials. Journal of Neural Engineering. 2026;23(4):046023. doi:10.1088/1741-2552/ae863e
BibTeX
@article{Kurmanaviit2026,
author = {Kurmanavičiūtė, Dovilė and Makkonen, Matilda and Zubarev, Ivan and Kahilakoski, Olli-Pekka and Parkkonen, Lauri},
title = {Overcoming brain non-stationarity: adaptive RLS classification for stable BCIs based on auditory evoked potentials},
journal = {Journal of Neural Engineering},
year = {2026},
volume = {23},
number = {4},
pages = {046023},
doi = {10.1088/1741-2552/ae863e}
}
EUVIMED