Reliable identification of mental tasks using time-embedded EEG and sequential evidence accumulation.

Abstract

Eleven channels of EEG were recorded from a subject performing four mental tasks. A time-embedded representation of the untransformed EEG samples was constructed. Classification of the time-embedded samples was performed by linear and quadratic discriminant analysis and by an artificial neural network. A classifier's output for consecutive samples is combined to increase reliability. A new performance measure is defined as the number of correct selections that would be made by a brain-computer interface (BCI) user of the system, accounting for the need for an incorrect selection to be followed by a correct one to 'delete' the previous selection. A best result of 0.32 correct selections s(-1) (about 3 s per BCI decision) was obtained with a neural network using a time-embedding dimension of 50.