1l1-NORM REGULARIZATION FOR SPARSE REPRESENTATION AND P300 WAVE DETECTION IN BRAIN-COMPUTER INTERFACES

VICTORIA PETERSON; HUGO RUFINER; RUBEN SPIES

Tandil

Congreso; V Congreso de Matemática Aplicada, Computacional e Industrial; 2015

A Brain-Computer Interface (BCI) is a system which provides direct communication between the mind of a person and the outside world by using only brain activity (EEG). A common EEG-BCI paradigm is based on the so called Event-Related Potentials (ERP) which are responses of the brain to some external stimuli. One of the main components of ERP signals is an enhanced positive-going component called P300 wave. The l1-normminimization has been widely used due to its sparsity-inducing property, convenient convexity and great success in several applications. In this work we propose a sparse representation and posterior classification of ERPs signals by means of an ad-hoc spatio-temporal dictionary composed of bidimensional Gaussian elements. The classification is based on minimizing the residual between a test sample and its estimation.