Simple SSVEP detection using spectrum intensity ratio and threshold

In recent years, Steady-State Visual Evoked Potential (SSVEP) is often used as a basis for Brain Computer Interface (BCI) [1]. The feature extraction is significant problem to achieve the SSVEP based BCI. Various signal processing and classification techniques are proposed to extract SSVEP from Electroencephalograph (EEG). We introduced a spectrum intensity ratio as a simple characterization and separation of SSVEP. However, it is difficult to classify an unseeing state of subjects. In addition, the comparison with conventional method is not tried yet. In this paper, we adopt a classification using threshold to reject the unseeing state.