Independent component analysis for meaningful peaks detection in EEG signals
B. Azzerboni, Maurizio Ipsale, Fabio La Foresta, Francesco Carlo Morabito · 2005
The electroencephalogram (EEG) signal is a useful and well known tool able to represent the brain electrical activity. In the EEG interpretation some peak activities could be related to some particular pathologic conditions, such as epilepsy or any other neurological damage. However, in most cases, high values of EEG signal represent an artifact activity. By means of an appropriate algorithm, we can understand if an high signal value is an artifact activity or it represents an irregular neural activity caused by some cerebral damage. In this paper some techniques, i.e. Independent Component Analysis (ICA) and Principal Component Analysis (PCA), are implemented in order to identify in EEG signals only those components that contain almost all the artifact contribution and that it is necessary to remove in order to have an adequate knowledge of the brain activity. To obtain that, the compression ability of PCA is mixed with the statistical independence property of the ICA. The EEG mapping is used to have a visual measure of the algorithm goodness.