A Kernel Canonical Correlation Analysis Based Idle-State Detection Method for SSVEP-Based Brain-Computer Interfaces

Abstract

In this paper, we propose a kernel canonical correlation analysis (KCCA) based idle-state detection method for asynchronous steady-state visual evoked potential (SSVEP)-based brain-computer interface (BCI) systems. KCCA method can offer a flexible nonlinear solution to adequately extract nonlinear features of multi-electrode electroencephalogram signals. Based on this method, an ensemble KCCA coefficients feature model is proposed by weighting effectively multi-harmonic information and afterwards a threshold classification strategy for idle-state detection is presented. The weights of the model and optimal threshold are trained by the presented parameters learning scheme. Using our method, offline analysis was performed on 10 subjects with 8 fixed common electrodes. The results showed that the idle state could be detected with 95.9% average accuracy when SSVEP could be determined with 93.8% average accuracy. Further, the analysis verified the effectiveness and significant superiority of our method over other widely used ones.

Untitled

“…Many EEG signal acquisition devices contain these filters (hardware filtering). [17] 3-60 Hz [18] 3-100 Hz [21,22] 32-45 Hz [27] 3-40 Hz [41] 1-30 Hz [45] 3-45 Hz [48] 5-50 Hz [52,53] 3 For the CAR method, the average value of all electrodes is subtracted from the channel of interest to make the EEG recording nearly reference-free.…”

“…[6,46,67] KCCA Developed based on the traditional CCA method to project data into a high-dimension space. [45] Multiway CCA Uses the optimal reference signals after adjustment. However, it increases computation time.…”

“…CCA is a multivariable statistical method used when there are two sets of data which may have some underlying correlation [44]. A pair of linear transformations are found, and then the corresponding correlation of the two sets of data is maximized [45]. The authors in paper [46] stated that they are the first researchers to use CCA to recognize SSVEP.…”

“…However, standard CCA supposes that the two sets of data are linearly related. A kernel CCA (KCCA) method has thus been proposed [45]. It projects data into a high-dimension space, but the inner product of the new data can be still calculated using the original low-dimension data.…”

“…One study [6] showed that CCA outperforms traditional PSDA methods. Several studies [45,48,49] proposed improved CCA methods that achieved good results. However, these studies used only the maximum canonical correlation coefficient.…”