Quantifying Event-Related (De)Synchronization Variability for Brain-Computer Interface: A Unified and Interpretable Framework
Abstract
Objective: Brain-Computer Interfaces (BCIs) enable the control of external devices by decoding user intentions from electroencephalography (EEG). However, substantial EEG variability within and between users remains a major challenge. To better understand this variability, we propose interpretable metrics that independently quantify temporal, spatial, and frequency variability in BCIrelated brain activity within and between users. Methods: We propose a framework to quantify variability by extracting EEG features and defining variability as their dispersion around their centroid using appropriate distance functions. Using two motor imagery BCI datasets (N = 133 users), we investigated the relationship between BCI performance and the variability metrics through within-user and crossuser classification experiments. Results: Negative correlations of −0.2 to −0.4 were observed across most conditions, suggesting that lower variability is associated with higher BCI performance. Moreover, the metrics revealed differences in robustness to variability between the deep learning and Riemannian-based classifiers, with the former showing weaker correlations. Conclusion: The results demonstrate the effectiveness of the proposed variability metrics and suggest that reducing variability may improve BCI performance while revealing differences in the sensitivity of classification models to different types of variability. Significance: The framework quantifies temporal, spatial, and frequency variability at multiple hierarchical levels (within-trial, between-trial, and between-trial-group), providing interpretable measures to better understand EEG variability and support more robust BCIs. It could also be used to characterize dataset variability, evaluate classifier sensitivity, incorporate variability into objective functions, and provide variability-based user feedback.
Related
- Interplay among neural synchronization, excitability, variability, and sequentiality across time scales in rhythmic bursting
- Quantifying the variability in the survival of Campylobacter jejuni strains on broiler fillets under refrigerated conditions
- HRV-GUI: A MATLAB Graphical User Interface for Heart Rate Variability Analysis and Validation Using Human, Rodent, and Clinical Diabetic Gastroparesis Data
- Quantifying Assay Confidence in Barrier Organ-on-Chip Systems: A Monte Carlo Assay-Readiness Framework for Detecting Modest Permeability Shifts
- A Dynamic State‐Based Framework for Quantifying Triadic Autonomic Synchrony During Group Decision‐Making
BibTeX
@misc{kojima2026quantifying,
title = {{Quantifying Event-Related (De)Synchronization Variability for Brain-Computer Interface: A Unified and Interpretable Framework}},
author = {Simon Kojima and Fabien Lotte},
howpublished = {HAL},
year = {2026},
month = sep,
eprint = {2607.21119},
archivePrefix = {arXiv},
url = {https://hal.science/hal-05701353v2},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - Quantifying Event-Related (De)Synchronization Variability for Brain-Computer Interface: A Unified and Interpretable Framework
AU - Simon Kojima
AU - Fabien Lotte
PY - 2026
DA - 2026/09/28
PB - HAL
UR - https://hal.science/hal-05701353v2
AB - Objective: Brain-Computer Interfaces (BCIs) enable the control of external devices by decoding user intentions from electroencephalography (EEG). However, substantial EEG variability within and between users remains a major challenge. To better understand this variability, we propose interpretable metrics that independently quantify temporal, spatial, and frequency variability in BCIrelated brain activity within and between users. Methods: We propose a framework to quantify variability by extracting EEG features and defining variability as their dispersion around their centroid using appropriate distance functions. Using two motor imagery BCI datasets (N = 133 users), we investigated the relationship between BCI performance and the variability metrics through within-user and crossuser classification experiments. Results: Negative correlations of −0.2 to −0.4 were observed across most conditions, suggesting that lower variability is associated with higher BCI performance. Moreover, the metrics revealed differences in robustness to variability between the deep learning and Riemannian-based classifiers, with the former showing weaker correlations. Conclusion: The results demonstrate the effectiveness of the proposed variability metrics and suggest that reducing variability may improve BCI performance while revealing differences in the sensitivity of classification models to different types of variability. Significance: The framework quantifies temporal, spatial, and frequency variability at multiple hierarchical levels (within-trial, between-trial, and between-trial-group), providing interpretable measures to better understand EEG variability and support more robust BCIs. It could also be used to characterize dataset variability, evaluate classifier sensitivity, incorporate variability into objective functions, and provide variability-based user feedback.
ER -