Introducing a Combination of ICA-EMD to Suppress Muscle and Ocular Artifacts in EEG Signals

This paper presents a combination of Independent Component Analysis (ICA) with Empirical Mode Decomposition (EMD) to suppress muscle and ocular artifacts in electroencephalographic (EEG) signals: By means of ICA, the EEG signals are decomposed into independent components. To avoid the suppression of artifactual components still containing physiological information, EMD is applied to decompose the components in Intrinsic Mode Functions (IMFs). The IMFs with mainly muscle artifacts are removed, and a new data set of independent components without muscle artifacts is generated. From this set, the components containing ocular artifacts are suppressed and clean data are reconstructed. In this way, the muscle and ocular artifacts are better suppressed than using pure ICA, or pure EMD. The performance of the proposed combination is applied to a semi-simulated data set, and three real EEG data sets from healthy subjects contaminated with both artifacts.