Beamforming in noninvasive Brain–Computer interfaces (2009)
Open in webOpen in zoteroOpen pdf
1 Abstract
Spatial filtering (SF) constitutes an integral part of building EEG-based brain-computer interfaces (BCIs). Algorithms frequently used for SF, such as common spatial patterns (CSPs) and independent component analysis, require labeled training data for identifying filters that provide information on a subject’s intention, which renders these algorithms susceptible to overfitting on artifactual EEG components. In this study, beamforming is employed to construct spatial filters that extract EEG sources originating within predefined regions of interest within the brain. In this way, neurophysiological knowledge on which brain regions are relevant for a certain experimental paradigm can be utilized to construct unsupervised spatial filters that are robust against artifactual EEG components. Beamforming is experimentally compared with CSP and Laplacian spatial filtering (LP) in a two-class motor-imagery paradigm. It is demonstrated that beamforming outperforms CSP and LP on noisy datasets, while CSP and beamforming perform almost equally well on datasets with few artifactual trials. It is concluded that beamforming constitutes an alternative method for SF that might be particularly useful for BCIs used in clinical settings, i.e., in an environment where artifact-free datasets are difficult to obtain.
2 NOTES
This paper proposes using beamforming to filter the signal. The idea is that they will select and region of interest (ROI) and try to extract the signal from this are while removing the noise from outside. Therefore they can define the covariance of the EEG recordings as: . Beamforming is then trying to make a weighted combination of the electrodes that behave like a ‘virtual sensor’ focusing on a particular region of the brain. This is very similar to what CSP does, but instead of trying to minimize variance for one class versus another class, in here it is one brain region (ROI) versus the other brain region (Out). Their results are indeed better on average than CSP and Laplace Filtering, but that is not relevant here, to be honest, their idea is. Overall it is a very interesting paper, maybe a little dated though.