Abstract
Calibration of motor imagery (MI) brain-computer interface (BCI) systems in stroke patients is
challenging due to limited voluntary movement and variable imagery ability. We propose mirror-box (MB) training as a physiologically grounded pretraining strategy to induce contralateral sensorimotor activation and extract subject-specific oscillatory components for MI detection. Electroencephalography (EEG) was recorded during six MB sessions in a chronic post-stroke participant. Parallel Factor Analysis (PARAFAC) was applied to decompose multi-channel EEG into spatial, temporal, and spectral components. Trial-pair normalization relative to the corresponding rest segment was used to enhance detection of
task-related modulation. Distinct mu and beta sensorimotor rhythms were identified, showing significant desynchronization during observation and movement compared to rest. An individualized linear discriminant analysis classifier achieved 98.8% ±0.6% accuracy in discriminating rest from motor engagement. These findings support MB pretraining as a robust strategy for physiologically informed MI-BCI calibration and future BCI Head-Mounted Display rehabilitation applications.
Go back