Effect of power feature covariance shift on BCI spatial-filtering techniques: A comparative study

•This study investigates the performance of several spatial-filtering approaches on calibration and test set acquired 30 min after the calibration, mimicking the real BCI scenarios.•EEG extracted feature covariance shifts lead to the BCI model accuracy deterioration, even after 30 min of a break.•FBCSP and FBSCPT showed to be more robust to feature covariance shift largely maintaining the original performance characterized by moderately high accuracy (>70%).•Stationary Subspace Analysis preprocessing improved the models’ performance and also reduced the gap between calibration and test set observed BCI model accuracies. The input data distributions of EEG-based BCI systems can change during intra-session transitions due to nonstationarity caused by features covariate shifts, thus compromising BCI performance. We aimed to identify the most robust spatial filtering approach, among most used methods, testing them on calibration dataset, and test dataset recorded 30 min afterwards. In addition, we also investigated if their performance improved after application of Stationary Subspace Analysis (SSA). We have recorded, in 17 healthy subjects, the calibration set at the beginning of the upper limb motor imagery BCI experiment and testing set separately 30 min afterwards. Both the calibration and test data were pre-processed and the BCI models were produced by using several spatial filtering approaches on the calibration set. Those models were subsequently evaluated on a test set. The differences between the accuracy estimated by cross-validation on the calibration dataset and the accuracy on the test dataset were investigated. The same procedure was performed with, and without SSA pre-processing step. A significant reduction in accuracy on the test dataset was observed for CSP, SPoC and SpecRCSP approaches. For SLap and SpecCSP only a slight decreasing trend was observed, while FBCSP and FBCSPT largely maintained moderately high median accuracy >70%. In the case of application of SSA pre-processing, the differences between accuracy observed on calibration and test dataset were reduced. In addition, accuracy values both on calibration and test set were slightly higher in case of SSA pre-processing and also in this case FBCSP and FBCSPT presented slightly better performance compared to other methods. The intrinsic signal nonstationarity characteristics, caused by covariance shifts of power features, reduced the accuracy of BCI model, therefore, suggesting that thi