Towards a virtual 4-class synchronous BCI using motor prediction and one motor imagery

Multi-class EEG-based BCIs (brain-computer interfaces) usually use a set of different mental tasks to generate different commands. This study shows that, after training with a specially designed BCI paradigm using one motor imagery, humans can learn to predict the time course of band power features of the EEG signals. With this newly-obtained prediction skill, subjects can use only one motor imagery to select one of the four targets on screen in each trial that lasts 3.4 seconds on average, which is functionally analogous to a 4-class synchronous BCI.