Common Spatial Pattern Patches - an Optimized Filter Ensemble for Adaptive Brain-Computer Interfaces
Laplacian filters are widely used in neuroscience. In the context of Brain- Computer Interfacing (BCI), they might be preferred to data-driven approaches such as Common Spatial Patterns (CSP) in a variety of scenarios as e.g. when no or few user data is available or a calibration session with a multi-channel recording is not possible, which is the case in various applications. In this manuscript we propose the use of an ensemble of local CSP patches (CSPP) which can be considered as a compromise between Laplacian filters and CSP. Our CSPP only needs a very few number of trials to be optimized and significantly outperforms Laplacian filters in all settings studied. Additionally, CSPP also outperforms multi-channel CSP and a regularized version of CSP even when only very little calibration data is available, acting as a CSP regularizer without the need of additional hyperparameters and at a very low cost: 2-5 minutes of data recording, i.e. 10 times less than CSP.