Application of Kalman Filtering in the Detection of Evoked Potentials

A method is proposed for de-noising and extracting non-stationary electroencephalogram (EEG) signals. Kalman filtering is an optimal recursive data processing algorithm. In this paper Kalman filtering is used to estimate evoked potentials (EP) from large background noise of electroencephalogram (EEG). The Waveforms of before filtering and after filtering is simulated and compared. The results show that the method can extract EP from the stationary random noise signals, and the filtering effect is more satisfied.