期刊
APPLIED SCIENCES-BASEL
卷 12, 期 6, 页码 -出版社
MDPI
DOI: 10.3390/app12062918
关键词
brain-computer interface; event-related potential; beamforming; regularization
类别
资金
- special research fund of the KU Leuven [GPUDL/20/031, C24/18/098]
- Belgian Fund for Scientific Research-Flanders [1SC3419N, G0A4118N, G0A4321N, G0C1522N]
- European Union [857375]
- Hercules Foundation [AKUL 043]
This study introduces two regularized estimators to improve the performance of brain-computer interfaces (BCIs) and enhance the classification accuracy of EEG signals. Through validation and comparison with limited training data, the results show that these estimators perform well and structured regularization has advantages in terms of training time and memory usage.
Featured Application Brain-computer interfaces as assistive technology to restore communication capabilities for disabled patients. The usability of EEG-based visual brain-computer interfaces (BCIs) based on event-related potentials (ERPs) benefits from reducing the calibration time before BCI operation. Linear decoding models, such as the spatiotemporal beamformer model, yield state-of-the-art accuracy. Although the training time of this model is generally low, it can require a substantial amount of training data to reach functional performance. Hence, BCI calibration sessions should be sufficiently long to provide enough training data. This work introduces two regularized estimators for the beamformer weights. The first estimator uses cross-validated L2-regularization. The second estimator exploits prior information about the structure of the EEG by assuming Kronecker-Toeplitz-structured covariance. The performances of these estimators are validated and compared with the original spatiotemporal beamformer and a Riemannian-geometry-based decoder using a BCI dataset with P300-paradigm recordings for 21 subjects. Our results show that the introduced estimators are well-conditioned in the presence of limited training data and improve ERP classification accuracy for unseen data. Additionally, we show that structured regularization results in lower training times and memory usage, and a more interpretable classification model.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据