Spatio-Spectral CCA (SS-CCA): A novel approach for frequency recognition in SSVEP-based BCI.

BACKGROUND: Steady-state visually evoked potentials (SSVEP) are one of the most important paradigms in the BCI Domain. Among the best methods for detecting frequency in the SSVEP-based BCI is the Canonical Correlation Analysis (CCA), which calculates canonical correlation between two sets of multidimensional variables, the electroencephalogram (EEG) and reference signals. Despite its efficiency and widespread application, CCA algorithm has some limitations. One major limitation of CCA is to only consider the spatial domain information of the signal. NEW METHOD: However, regarding frequency of signal as another critical feature of the signals, combining both spatial and frequency domain information can significantly improve the performance of frequency recognition. Although several previous studies about CCA algorithm, could improve its performance, they have not addressed CCA algorithm's limitation. To address this concern, in the current study, we presented Spatio-Spectral CCA (SS-CCA) algorithm, which is inspired from Common Spatio-Spectral Patterns (CSSP) algorithm. In the SS-CCA algorithm, we added a time delay to the EEG signal, in order to simultaneously optimize spatial and frequency information and obtain the canonical variables. Accordingly, for correlation coefficient's calculations, more information from EEG signal is utilized. RESULTS: Finally, SS-CCA algorithm which is used as the base model of Filter Bank CCA (FBCCA), and Filter Bank SS-CCA algorithms, can help increase the frequency recognition performance. In order to evaluate the proposed method, 35-subject benchmark dataset were used. Proposed algorithm yielded mean accuracy 98.33 across all subjects. COMPARISON WITH EXISTING METHODS: Our classification accuracy and Information Transfer Rate (ITR) results showed that the performance of the above-mentioned method improves in comparison to the CCA. CONCLUSIONS: In conclusion, using the proposed SS-CCA algorithm instead of the CCA, in all our experiments the CCA-based methods were improved.

Ensemble Regularized Common Spatio-Spectral Pattern (ensemble RCSSP) model for motor imagery-based EEG signal classification.

The Brain-Computer interface system provides a communication path among the brain and computer, and recently, it is the subject of increasing attention. One of the most common paradigms of BCI systems is motor imagery. Currently, to classify motor imagery EEG signals, Common Spatial Patterns (CSP) are extensively used. Generally, the recorded motor imagery EEG signals in BCI are noisy, non-stationary, thus significantly reducing the BCI system's performance. It is shown that the CSP algorithm has a good performance in the classification of various types of motor imagery data. However, once the number of trials is low, or the data are noisy, overfitting will probably occur, which precludes extracting an appropriate spatial filter. Another drawback of the CSP is that it only extracts spatial-based filters. Therefore, the current study attempts to decrease the probability of overfitting in the CSP algorithm by presenting an improved method called Ensemble Regularized Common Spatio-Spectral Pattern (Ensemble RCSSP). Compared with other CSP and improved versions of CSP algorithms, our proposed models indicate a better accuracy, robustness, and reliability for motor imagery EEG data. The performance of the proposed Ensemble RCSSP has been tested for BCI Competition IV, Dataset 1, and BCI Competition III, Dataset Iva. Compared with other methods, performance is improved, and on average, the accuracy for all subjects is reached to 82.64% and 86.91% for the first and second datasets, respectively.