Scientists Can Decode Brain Signals in Real time

A recently published study in PLOS Computational Biology, says that brain signals can be decoded in real time with full accuracy. The study was done by the neuroscientists from the University of Washington. Researchers attached electrodes to the temporal lobes of seven epilepsy patients for roughly one week — the implants were part of a program that aimed to locate the sources of these patients’ seizures, but while the electrodes were active, the patients also participated in this brain-wave study.

Rajesh Rao, one of the computational neuroscientists at the University of Washington, said, ‘Clinically, you could think of our result as a proof of concept toward building a communication mechanism for patients who are paralyzed or have had a stroke and are completely locked-in.’

The ability to view a two-dimensional image on a page or computer screen, and then transform that image into something our minds can immediately recognize, is a neurological process that remains mysterious to scientists. Researchers exposed the patients to an entirely new set of pictures after training the software. Without previous exposure to these new images, the computer was able to predict with 96 percent accuracy when a test subject was seeing a house, a face, or a grey screen.

A series of houses and faces that appeared on a screen for 400 milliseconds at a time were viewed by the participants. They were told to look for the upside-down building. An algorithm tracked the brain waves of their temporal lobes, which deals in sensory input.

It is quite impressive that the program was able to pinpoint with roughly 96 percent accuracy which images the patients were looking at, in real time, by the end of the session. It knew whether the patient was seeing a house, a face or a gray screen within 20 milliseconds of actual perception.