Simultaneous classification of motor imagery and SSVEP EEG signals

increased demands for applications of brain computer interface (BCI) have led to growing attention towards their more practical paradigm design. BCIs can provide motor control for spinal cord injured patients. BCIs based on motor imagery (MI) and steady-state visual evoked potentials (SSVEP) tasks are two well-established tasks that have been studied extensively. These two tasks can be combined in order for the users to realize more sophisticated paradigms. In this paper, a novel system is introduced for simultaneous classification of the MI and SSVEP tasks. It is an effort to inspire BCI systems that are more practical, especially for effective communication during more complex tasks. In this study, subjects performed MI and SSVEP tasks both individually and simultaneously (combining both tasks) and the electroencephalographic (EEG) data were recorded across three conditions. Subjects focused on one of the three flickering visual stimuli (SSVEP), imagined moving the left or right hand (MI), or performed neither of the tasks. Accuracy and subjective measures were assessed to investigate the capability of the system to detect the correct task, and subsequently perform the corresponding classification method. The results suggested that with the proposed methodology, the user may control the combination of the two tasks while the accuracy of task recognition and signal processing is minimally impacted.