Appropriate Normalisation for Selective Eigen Rate Method in Separating Principal Components of VEP and EEG in BCI

Here we give proof to the best suitable normalization method for the Selective Eigen Rate (SER) a novel technique, that is used in selecting only the higher rate of principal components (PCs) for using them in Principal Component Analysis (PCA) while separating Visual Evoked Potential (VEP) from electroencephalogram (EEG) signals, to enable single trial analysis. SER technique is designed and implemented to overcome heavy electroencephalogram (EEG) contamination in VEP signals. Normalisation of the eigen values which are obtained as a result of PCA is an important part for PC selection process in SER technique. In order to derive the maximum signal to noise ratio (SNR) from artificial VEP signals contaminated by EEG, three distinct normalisation methods were constructed and tested here. The best methods of normalisation suitable for the SER method is found and tested with added factors of noise in multiples of 2, 5 and 10 times. Assessment on the performance of this effective normalisation technique shows that application of SER with the proposed normalisation technique on contaminated signals outperformed the other normalisation techniques and existing PCA methods like Kaiser (KSR) and Residual Power (RP) and Spectral Power Ratio (SPR) in selecting the PCs. The SER adopting our proposed normalisation technique yields in an average positive SNR of 97.83 dB for higher noise levels while RP KSR and SPR gave less values of SNR in the same noise levels. Key words— Principal components, P3, Signal to noise ratio, Single trial, Spectral Power ratio, Selective Eigen Rate, Visual Evoked Potential