New brain decoding device controls prosthetic attachments much better than before

September 10, 2020
New brain decoding device controls prosthetic attachments much better than before

Brain-computer interfaces (BRI) are devices that can be implanted in the brain, where electrical signals serve as control inputs for other devices, such as prosthetic limbs. Scientists from the University of California, San Francisco (UCSF), US, have developed a first-of-a-kind plug-and-play device using BCIs to reliably translate brain activity into action.

Unlike a typical machine learning algorithm for a BCI that needs to be reset every day, the UCSF scientists configured the new algorithm to better itself each day on an ongoing basis. It eventually meant that the paralysed user would be able to plug in and begin using it – to great effect – right away.

“The BCI field has made great progress in recent years, but because existing systems have had to be reset and recalibrated each day, they haven’t been able to tap into the brain’s natural learning processes. It’s like asking someone to learn to ride a bike over and over again from scratch,” said Karunesh Ganguly, a practicing neurologist with UCSF Health.

The BCI used in these experiments was essentially a pad of electrodes around the size of a Post-it note, surgically implanted on the surface of the brain. The users’ brains were optimising their activity to control the BCI, without the need for daily recalibration.

“We found that we could further improve learning [between brain and computer] by making sure that the algorithm wasn’t updating faster than the brain could follow – a rate of about once every 10 seconds,” Ganguly added.

In time, the scientists found they could actually switch off the algorithm’s auto-updating feature and the user could simply plug in and start using it each day. Even without any daily calibration, the performance did not decline over a 44-day period of use, with the user also able go several days without using it and only experience a small decline in performance.


Category: Features, Technology & Devices

Comments are closed.