A Novel Design of 4-Class BCI Using Two Binary Classifiers and Parallel Mental Tasks

摘要

A novel 4-class single-trial brain computer interface (BCI) basedon two (rather than four or more) binary linear discriminant analysis(LDA) classifiers is proposed, which is called a “parallel BCI.” Unlikeother BCIs where mental tasks are executed and classified in a serialway one after another, the parallel BCI uses properly designed parallelmental tasks that are executed on both sides of the subject bodysimultaneously, which is the main novelty of the BCI paradigm usedin our experiments. Each of the two binary classifiers only classifiesthe mental tasks executed on one side of the subject body, and theresults of the two binary classifiers are combined to give the resultof the 4-class BCI. Data was recorded in experiments with both realmovement and motor imagery in 3 able-bodied subjects. Artifactswere not detected or removed. Offline analysis has shown that, insome subjects, the parallel BCI can generate a higher accuracy than aconventional 4-class BCI, although both of them have used the samefeature selection and classification algorithms.