Explicit modelling of subject dependency in BCI decoding
This addresses the need for scalable and practical subject-adaptive BCIs, though it appears incremental as it builds on existing conditioning mechanisms and hyperparameter optimization strategies.
The paper tackles the problem of high inter-subject variability and limited labeled data in Brain-Computer Interfaces (BCIs) by proposing an end-to-end approach that explicitly models subject dependency using lightweight CNNs conditioned on subject identity, resulting in improved generalization and data-efficient calibration.
Brain-Computer Interfaces (BCIs) suffer from high inter-subject variability and limited labeled data, often requiring lengthy calibration phases. In this work, we present an end-to-end approach that explicitly models the subject dependency using lightweight convolutional neural networks (CNNs) conditioned on the subject's identity. Our method integrates hyperparameter optimization strategies that prioritize class imbalance and evaluates two conditioning mechanisms to adapt pre-trained models to unseen subjects with minimal calibration data. We benchmark three lightweight architectures on a time-modulated Event-Related Potentials (ERP) classification task, providing interpretable evaluation metrics and explainable visualizations of the learned representations. Results demonstrate improved generalization and data-efficient calibration, highlighting the scalability and practicality of subject-adaptive BCIs.