EEG-based left-hand/right-hand/rest motor imagery task classification

This paper presents an EEG-based Brain-Computer Interface (BCI) designed for classification of motor imagery tasks. Apart from the imagined right-hand / left-hand movements, a third class - the resting (idle) state - is also included. The classification is based on Linear Discriminant Analysis (LDA) and Common Spatial Patterns (CSP) filtering of the band-limited EEG signal acquired from 10 electrodes placed over the motor cortex area. The system, planned for integration with a virtual reality (VR) environment and designed for future neurorehabilitation applications is tested on an experimental database comprising 52 subjects. The observed variability be-tween individual participants and selected subgroups is further analysed with statistical tools, revealing significant differences with respect to gender, age and individual motor imagery task classes.