Nature: The brain-computer interface can convert brain activity into text in real time!

Scientists are exploring ways to allow people with disabilities to exchange ideas with them.

PIXABAY

The brain-computer interface (BCI) enables people who have lost the ability to move or speak to resume communication.

Recently, researchers from Stanford University in the United States combined artificial intelligence (AI) software with brain-computer interface (BCI) equipment for the first time, and successfully developed an intracortical BCI that decodes neural activity in the motor cortex to try handwritten actions and uses cyclic nerves.

The research team worked with a participant in a clinical trial named BrainGate2.

Researchers found that because the peaks and valleys of neural activity vary with time, perhaps due to fluctuations in writing speed, neural activity seems to be strong and repeatable.

In order to determine whether the neural activity encodes the pen tip movement required to draw each shape, the researchers reconstructed each character by linearly decoding the pen tip speed from the experimental average neural activity.

Neural representation of handwriting

Second, the researchers used the non-linear dimensionality reduction method (t-SNE) to visualize the neural activity of each experiment in two dimensions (2D), and record the relevant information after giving the subject a "go" prompt.

The t-SNE method shows the tight clusters of neural activity of each character and a dominant motion encoding.

As a result, the researchers concluded that even after years of paralysis, the neural representation of handwriting in the motor cortex may still be powerful enough to be expressed through brain-computer interface technology.

Krishna Shenoy, a researcher at the Howard Hughes Medical Institute at Stanford University, co-author of the research report, said that with further development, this innovation will allow paralyzed people to type quickly without using their hands.

The next step for the team is to work with participants who cannot speak, such as those with amyotrophic lateral sclerosis, a degenerative neurological disease that causes loss of movement and language.

Jose Carmena, a neuroengineer at the University of California, Berkeley, said, "This technology and other similar technologies have the potential to help people with various disabilities.

Original source:

Francis R.