Blind Source Separation and Localization

Blind Source Separation techniques such as Independent Component Analysis (ICA), Principal Component Analysis (PCA), Factor Analysis (FA), Nonnegative Matrix Factorization (NMF), have been steadily gaining popularity in the last years to preprocess multivariate data sets, to disentangle information linearly mixed by volume conduction in the recorded data channels, and to perform or prepare for more general data mining. As with most factorization algorithms, the extracted components need to be interpreted before they can be used in further analyses. Unfortunately, this is often made difficult by several issues including inadequate data sampling (e.g., when recordings are too short and/or have too few channels), inadequate data pre-processing, algorithm deficiencies and noise. For this reason, a new framework, RELICA (REliable Independent Component Analysis) is being developed. RELICA allows to estimate the reliability of Independent Components and prevents retaining an unreliable component for further analysis. RELICA is being applied to EEG, EMG (reliable source localization) and many other multivariate datasets, and it is under continuous development.