Open AccessEXTRACTION OF EOG ARTIFACT FROM MULTICHANNEL EEG SIGNAL USING MULTICHANNEL SINGULAR SPECTRUM ANALYSIS AND RLS ADAPTIVE NOISE CANCELER
Author(s) -
R. Rengalakshmi,
C.-P Paul
Publication year - 2017
Publication title -
zenodo (cern european organization for nuclear research)
Language(s) - English
DOI - 10.5281/zenodo.437981
Subject(s) - artifact (error) , electroencephalography , singular spectrum analysis , noise (video) , computer science , signal (programming language) , adaptive filter , speech recognition , extraction (chemistry) , pattern recognition (psychology) , electrooculography , artificial intelligence , psychology , eye movement , algorithm , neuroscience , singular value decomposition , chemistry , image (mathematics) , programming language , chromatography
Electroencephalogram (EEG) are the neurological signals which help in the study of various se are diseases. These are contaminated with various artifacts like electrooculogram (EOG). It is difficult to study and analysis of brain signals in the existence of artifact. Usually adaptive filter has been used to remove artifact in biomedical signals. An effective approach is proposed in this paper to remove ocular artifacts from the raw EEG recording. In proposed technique, carried out by multichannel singular spectrum analysis (MSSA) and recursive least square (RLS) adaptive filter. To validate the proposed algorithm some noisy simulated signals are used. The performance of the technique is also examined using synthetic EEG signals. In terms of mean absolute error (MAE) and relative root mean square error (RRMSE)