Unsupervised frequency-recognition method of SSVEPs using a filter bank implementation of binary subband CCA

Recently developed effective methods for detection commands of steady-state visual evoked potential (SSVEP)-based brain-computer interface (BCI) that need calibration for visual stimuli, which cause more time and fatigue prior to the use, as the number of commands increases. This paper develops a novel unsupervised method based on canonical correlation analysis (CCA) for accurate detection of stimulus frequency.

A novel unsupervised technique termed as binary subband CCA (BsCCA) is implemented in a multiband approach to enhance the frequency recognition performance of SSVEP. In BsCCA, two subbands are used and a CCA-based correlation coefficient is computed for the individual subbands. In addition, a reduced set of artificial reference signals is used to calculate CCA for the second subband. The analyzing SSVEP is decomposed into multiple subband and the BsCCA is implemented for each one. Then, the overall recognition score is determined by a weighted sum of the canonical correlation coefficients obtained from each band.

A 12-class SSVEP dataset (frequency range: 9.25-14.75 Hz with an interval of 0.5 Hz) for ten healthy subjects are used to evaluate the performance of the proposed method. The results suggest that BsCCA significantly improves the performance of SSVEP-based BCI compared to the state-of-the-art methods. The proposed method is an unsupervised approach with averaged information transfer rate (ITR) of 77.04 bits min^-1 across 10 subjects. The maximum individual ITR is 107.55 bits min^-1 for 12-class SSVEP dataset, whereas, the ITR of 69.29 and 69.44 bits min^-1 are achieved with CCA and NCCA respectively.

The statistical test shows that the proposed unsupervised method significantly improves the performance of the SSVEP-based BCI. It can be usable in real world applications.