A Comparison Study of Canonical Correlation Analysis Based Methods for Detecting Steady-State Visual Evoked Potentials

Abstract

Canonical correlation analysis (CCA) has been widely used in the detection of the steady-state visual evoked potentials (SSVEPs) in brain-computer interfaces (BCIs). The standard CCA method, which uses sinusoidal signals as reference signals, was first proposed for SSVEP detection without calibration. However, the detection performance can be deteriorated by the interference from the spontaneous EEG activities. Recently, various extended methods have been developed to incorporate individual EEG calibration data in CCA to improve the detection performance. Although advantages of the extended CCA methods have been demonstrated in separate studies, a comprehensive comparison between these methods is still missing. This study performed a comparison of the existing CCA-based SSVEP detection methods using a 12-class SSVEP dataset recorded from 10 subjects in a simulated online BCI experiment. Classification accuracy and information transfer rate (ITR) were used for performance evaluation. The results suggest that individual calibration data can significantly improve the detection performance. Furthermore, the results showed that the combination method based on the standard CCA and the individual template based CCA (IT-CCA) achieved the highest performance.

Combining the Benefits of CCA and SVMs for SSVEP-based BCIs in Real-world Conditions

“…For the proposed as well as the existing methods in this paper, we utilized a leave-one-session-out cross validation scenario, similar to [11], where in each fold, the trials of the s − 1 sessions were used as calibration data (EEG cal ) and the trials of the s t h session for testing (EEG t est ).…”

“…The proposed method combines the benefits of CCA, ITs and SVMs, More specifically, we use the combination of the ITs (ITs ( f n , j)) and the artificially generated sine-cosine signals (R( f n )) as it was shown to perform best in [11] (all these signals will be mentioned as reference signals from now on). In more detail, let us define the set of reference signals for the stimulating frequency f n as RS f n (j), j = 1, .…”

“…the standard CCA [8]), generated artificial sine-cosine signals at the stimulating frequencies as reference signals, and selected the frequency that provided the maximum correlation coefficients with the user's signal. Extending the standard CCA method, in [2,11,16] calibration data from the user were utilized so as to generate subjectspecific reference signals. More specifically, the authors of [16] proposed to optimize the sine-cosine reference signals by maximizing their correlation with the calibration data.…”

“…the average ITs) from the calibration data as a reference signal instead of the artificially generated sine-cosine signals. Extending this idea, the authors of [11] proposed to combine the ITs from [2] with the artificial templates from standard CCA, by maximizing the correlation between the correlation weights of the user's signal, the best performing IT and the artificial templates.…”

“…Furthermore, this allows a number of modifications to be incorporated in the algorithm so as to accommodate for personalized self-paced BCI applications and the adaptation of the methodology in real world conditions. More specifically, besides the artificially generated template signals [11]. In addition, leveraging the fact that SVM-based classifiers produce a score that indicates its confidence for the label of the testing trial, we propose to set a minimum threshold of confidence that can be used as an early stopping criterion (i.e.…”