Analysis of different discriminant measures on a penalized mix-norm classification method for ERP detection

VICTORIA PETERSON; HUGO LEONARDO RUFINER; RUBÉN DANIEL SPIES

Comodoro Rivadavia

Congreso; VI Congreso de Matemática Aplicada, Computacional e Industrial; 2017

ASAMACI

A brain-computer interface (BCI) system based on event related potentials (ERPs) consists mainly ofsolving a binary classification problem. Although the linear discriminant analysis (LDA) method is widely used forthis type of problems, it does not yield satisfactory performances when the number of features is large relative to thenumber of observations. In this article we present a generalized sparse discriminant analysis method and analyze theimpact of six different discriminant measures (used in the construction of certain anisotropy matrices) in classificationperformance. Numerical results indicate that the best measures for this type of ERP classification problems are thosebelonging to the Shannon-Entropy family