AUTOMATIC REMOVAL OF SPARSE ARTIFACTS IN ELECTROENCEPHALOGRAM
Petr Tichavský, Miroslav Zima, Vladimı́r Krajča · 2011
In this paper we propose a method to identify and remove artifacts, that have a relatively short duration, from complex EEG data. The method is based on the application of an ICA algorithm to three non-overlapping partitions of a given data, selection of sparse independent components, removal of the component, and the combination of three resultant signal reconstructions in one final reconstruction. The method can be further enhanced by applying wavelet de-noising of the separated artifact components.