In my master thesis, I developed a Brain-Computer Interface (BCI) for people who suffer from locked-in syndrome, which is a condition in where a person loses the ability to control muscles and communicate. The brain mostly functions though.

Fortunately, with today’s technology, it is possible to help these people by either using a webcam or reading what is going on within the brain, by looking at electrical activity along the scalp. I decided to create a solution based on brain activity, as it turned out to be more stable than eye tracking.

My solution is a text writing application, where the person selects letters or words by looking at them. The attached article at the bottom of this post explains most technical details related to the project, so I won’t get into that.

Performance

Nine healthy test subjects age 23-33 participated in tests where they wrote full sentences in Danish and in English. The best performing subject could almost write 9 characters per minute while the worst performing subject was down at 3 characters per minute. Compared to not being able to communicate at all, this is quite impressive 🙂

Award winning project

The project was very well recieved both by the audience at the Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC’13) and at home. In Denmark, I received the annual “E-Kandidat” prize by the Society of Engineers (IDA) for the project. \o/

      

Download
DTU BCI Speller: An SSVEP-based Spelling System with Dictionary Support