Performance Improvement of Motor-Imagery BCI Using Multi-Mental Tasks

抄録

We studied a motor-imagery brain-computer interface (MI-BCI). An MI-BCI is an interface that allows a computer to be operated by changes in brain activity that occurs when the operator imagines moving a body part. For example, with MI-BCI it is possible to assign left-hand motor-imagery to power an ON/OFF command. One of the problems with MI-BCI is its low performance, especially since MI-BCI has few commands. We aimed to improve the performance of MI-BCI by adding to the number of commands. Currently, MI-BCI has four commands based on “left hand,” “right hand,” “legs,” and “tongue” motor imagery. Therefore, we attempted to add to the number of MI-BCI commands by classifying eight kinds of brain motor-imagery activity: “no imagery,” “left hand,” “right hand,” “legs,” “both hands,” “left hand + legs,” “right hand + legs,” and “both hands + legs.” Motor imagery that involves multiple body parts, for example, “both hands,” is referred to as a multi-mental task. Multi-mental tasks involve a combination of simultaneous motor imagery, for example including the left and right hands and the legs. This makes it possible to increase the number of commands to 2^N (where N is the number of body parts). Eighteen healthy males in their twenties participated in this study. The use of multi-mental tasks enabled us to improve MI-BCI performance in two out of three subjects. Multi-mental tasks can be used to add choice to MI tasks. Performance improvements using an MI-BCI were made possible by choosing MI tasks associated with high accuracy.