Skip to Main Content
This paper describes the development and testing of a wavelet-like filter, named the SNAP, created from a neural activity simulation and used, in place of a wavelet, in a wavelet transform for improving EEG wavelet analysis, intended for brain-computer interfaces. The hypothesis is that an optimal wavelet can be approximated by deriving it from underlying components of the EEG. The SNAP was compared to standard wavelets by measuring Support Vector Machine-based EEG classification accuracy when using different wavelets/filters for EEG analysis. When classifying P300 evoked potentials, the error, as a function of the wavelet/filter used, ranged from 6.92% to 11.99%, almost twofold. Classification using the SNAP was more accurate than that with any of the six standard wavelets tested. Similarly, when differentiating between preparation for left- or right-hand movements, classification using the SNAP was more accurate (10.03% error) than for four out of five of the standard wavelets (9.54% to 12.00% error) and internationally competitive (7% error) on the 2001 NIPS competition test set. Phenomena shown only in maps of discriminatory EEG activity may explain why the SNAP appears to have promise for improving EEG wavelet analysis. It represents the initial exploration of a potential family of EEG-specific wavelets.