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.

Validating the effect of muscle artifact suppression in localizing focal epilepsy.

Source localization of an epileptic seizure is becoming an important diagnostic tool in pre-surgical evaluation of epileptic patients. However, for localizing the epileptogenic zone precisely, the epileptic activity needs to be isolated from other activities that are not related to the epileptic source. In this study, we aim at an investigation of the effect of muscle artifact suppression by using a low-pass filter (LPF), independent component analysis (ICA), and a combination of ICA-LPF prior to source localization in focal epilepsy.

DBS artifact suppression using a time-frequency domain filter.

Electroencephalogram (EEG) is a useful tool for brain research. However, during Deep-Brain Stimulation (DBS), there are large artifacts that obscure the physiological EEG signals. In this paper, we aim at suppressing the DBS artifacts by means of a time-frequency-domain filter.

Muscle artifact suppression using independent-component analysis and state-space modeling.

In this paper, we aim at suppressing the muscle artifacts present in electroencephalographic (EEG) signals with a technique based on a combination of Independent Component Analysis (ICA) and State-Space Modeling (SSM). The novel algorithm uses ICA to provide an initial model for SSM which is further optimized by the maximum-likelihood approach. This model is fitted to artifact-free data.