BrainBots: A Brain-controlled On-screen Assistive Keyboard

The project uses Steady State Visually Evoked Potential (SSVEP) to implement an on-screen assistive keyboard. SSVEP are signals that are natural responses to visual stimulation at specific frequencies. When the retina is excited by a visual stimulus, the brain generates electrical activity at the same (or multiples of) frequency of the visual stimulus. By flashing a finite set of areas on the screen, one can determine which area was of interest to the user by comparing the frequency of the brain’s electrical activity, and hence use it for taking an action (e.g. keyboard character selection). The keyboard's efficiency is improved using the autocomplete feature. The system is also able to predict the user's intent using a Natural Language Processing (NLP) technique and feeding the result to a customizable set of bots that assist the user by providing means to interact with people/services, control external applications, and by directly answering user’s question

Demo

https://www.youtube.com/watch?v=yBker7B0X1A