Evaluation of feature extraction methods for motor imagery-based bcis in terms of robustness to slight changes of electrode locations

In this study, various feature extraction methods for motor-imagery-based BCI were evaluated in terms of robustness to slight changes in electrode locations. EEG signals were recorded from three reference electrodes (Fz, C3, and C4) and from six additional electrodes located close to the reference electrodes. The performance of four different feature extraction methods [power spectral density (PSD), phase locking value (PLV), a combination of PSD and PLV, and cross-correlation (CC)] were evaluated in terms of robustness to electrode location changes as well as regarding absolute classification accuracy. The quantitative evaluation results demonstrated that the use of either PSD- or CC-based features led to higher classification accuracy than the use of PLV-based features, whereas PSD-based features showed much higher sensitivity to changes in EEG electrode location than CC- or PLV-based features. There results suggest that CC can be a promising feature extraction method in motor-imagery-based BCI studies as it provides high classification accuracy along with being little affected by slight changes in the EEG electrode locations.