Independent Component Automatic Clustering and its application on multi-trails imaginary hand movement related EEG
ABSTRACT How to extract task-relevant components from spontaneous electroencephalogram background is an open problem in EEG signal analysis. An Independent Component Automatic Clustering (ICAC) method, which combined Independent Component Analysis (ICA) with automatic clustering, is developed in this paper. In ICAC, the ICA decomposed components were grouped into several clusters and sorted automatically. A majority of task-relevant components could be grouped into one cluster and be recognized easily, which can compensate the traditional ICA limitation of component sorting without any task specialized orders. We adopted this method on multi trails EEG signals during imaginary hand movement, results showed that ICAC can automatically extract task-relevant component and increase the Fisher Criterion (FC) separability significantly. Furthermore, we show that the residual mutual information between task-relevant components is not useless as previously regarded but very useful on components recognition.
Conference Paper: Automatic EEG artifact removal based on ICA and Hierarchical Clustering[Show abstract] [Hide abstract]
ABSTRACT: Electroencephalography (EEG) is the recording of electrical activity along the scalp produced by the firing of neurons within the brain. These activities can be decoded by signal processing techniques, however, they are typically influenced by extraneous interference, like muscle movements, eye blinks, eye movements, background noise, etc. Therefore, a preprocessing step to remove artifacts is extremely important. This paper presents an effective artifact removal algorithm, based on Independent Component Analysis (ICA) and Hierarchical Clustering. Our technique utilizes general temporal and spectral features and particular information about target Event-Related Potentials (ERPs) (e.g. the timing of N200 and P300 on inhibition task or the specific electrodes contributing to the ERPs) to separate ERPs and artifact activities. Our method considers templates for desired ERPs to select event-related components for signal reconstruction. In our experimental study, we show that our proposed method can effectively enhance the ERPs for all fifteen subjects in the study, even for those that barely display ERPs in the raw recordings.Acoustics, Speech and Signal Processing (ICASSP), 2012 IEEE International Conference on; 01/2012