On the Size of the Universal Dictionaries Used in EEG P300 Spelling Paradigm Based on Compressed Sensing
Monica Fira, Liviu Goraş · 2017
In this work we discuss, analyze and compare results regarding a new compression method for electroencephalographic signals aimed at P300 detection spelling paradigm based on the concept of compressed sensing (CS). The method uses a universal mega-dictionary which has been found not to be patient-specific. The impact of the size dictionary on the results is analyzed and optimal dimensions of the proposed dictionary (in terms of computing time vs. resulting compromise reconstruction) are determined.