Currently I am involved in constructing an EEG-Based BCI.

The goal of the BCI is to control which light in a series of lightbulbs lights up. The plan is to use different images (i.e. a flower versus a tiger) to elicit different neuron response that will show up on the EEG. The light bulb will light up in any order these images are given (tiger -> flower -> mountain -> sky -> white noise -> bright red...etc.)

Does anyone know if there has ever been a successful realization of such system? Please provide me with a link to it.


This article by Bobrov et. al seems to be similar to what you are looking for. They were able to classify (at above chance performance) whether subjects were imagining houses or faces. The training protocol is particularly interesting: they started by showing subjects pictures, but then used a feedback process of showing the subjects the output of the classifier while they were imagining the images to try and improve the subjects' 'imagination' of the images.

| improve this answer | |

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.