Automatic stimuli classification from ERP data for augmented communication via Brain-Computer Interfaces

Brain-computer interfaces (BCIs) are systems initially designed to compensate for motor disabilities affecting people whose control of the muscular system is compromised. However, recent developments open the BCIs market to a wide range of medical and non-medical applications. This raises the need for systems capable of interpreting more and more stimuli, even from different sensory domains. In this work, we design a machine-learning system able to fit both application domains accurately recognizing visual and auditory stimuli starting from the event-related potentials (ERPs) they generate. The obtained results are promising and some practical and realization aspects are discussed.