Adaptive filter and adaptive linear Fourier combined in processing of cognitive-event-related potential

This paper focuses on estimating the evoked potential (EP) signal, recorded from a human scalp, that occurs in response to an externally applied stimulus. A Fourier series model for time-varying EPs is chosen. The model parameters are estimated by a recursive least squares (RLS) adaptive procedure, enabling the estimator to efficiently track clinically significant alterations in the EP.