Local transform processing of single-trial evoked potential
Pavel Kisilev, Y.Y. Zeevi, Hillel Pratt · 2003
An algorithm for estimation and reconstruction of Evoked Potentials (EP), masked by EEG activity and additional sources of clutter and noise is proposed. The local Karhunen-Loeve (LKL) basis, derived from the noisy EP signal, is used for optimal signal representation. The vector space of the noisy signal is decomposed by the LKL transform into two complementary orthogonal subspaces. The EP signal is estimated by modifying the signal subspace components with a Wiener gain function.