Application of compressive sensing for EEG source localization in Brain Computer Interfaces

Brain-Computer Interfaces (BCIs) provide a way to communicate without movement and can offer significant clinical benefits therefore. Electrical brain activity recorded using electroencephalography (EEG) can be automatically interpreted by supervised learning classifiers according to the descriptive features of the signal. Compressive sensing paradigm commonly used for array antenna design and signal processing can be used to solve the underdetermined EEG source localization problem in order to extract sparse cortical current topographies to be used as spatial features for classification. This paper investigates the performance of the novel feature extraction method based on sparse source localization.