Many people who have suffered debilitating injuries or illnesses to their nervous system sometimes lose the ability to control their muscle movements. Many are no longer able to walk, drive, or play music of their own accord. They can still imagine how to do the actions, but their body no longer follows through.
This is where brain-computer interface systems come in as they assist in translating what the paralyzed or otherwise debilitated person thinks into certain actions. However, these systems are sometimes a burden as they experience unstable readjustments between simple tasks and don't always operate smoothly.
Now, a team of researchers from Carnegie Mellon University (CMU) and the University of Pittsburgh (Pitt) in the U.S. is looking into an algorithm that stabilizes these adjustments between brain-computer interface systems. The aim is to help improve the lives of amputees who use neural prosthetics.
Their findings were published in Nature Biomedical Engineering.
Readjusting brain-computer interfaces
The team's hope is to improve brain-computer interfaces to the point when they no longer need to be recalibrated during or between experiments.
Brain-computer interfaces (BCI) are devices that assist people who suffer from motor disabilities such as paralysis, by controlling prosthetic limbs, computer cursors, or other interfaces by using their minds. There currently exist instabilities in these neural recordings, which means that after a while the person using the BCI can no longer control it, and it needs to be recalibrated by a technician.
"Imagine if every time we wanted to use our cell phone, to get it to work correctly, we had to somehow calibrate the screen so it knew what part of the screen we were pointing at," said William Bishop, fellow at Janelia Farm Research Campus. "The current state of the art in BCI technology is sort of like that. Just to get these BCI devices to work, users have to do this frequent recalibration. So that's extremely inconvenient for the users, as well as the technicians, maintaining the devices."
What the team is working on is a machine learning algorithm that takes in these varying signals and enables the person using the BCI to continue controlling the device. The team is looking to stabilize these shifts in signals in BCIs.
Alan Degenhart, a postdoctoral researcher in electrical and computer engineering at CMU explained that they "have figured out a way to take different populations of neurons across time and use their information to essentially reveal a common picture of the computation that's going on in the brain, thereby keeping the BCI calibrated despite neural instabilities."
These types of self-recalibration procedures have been a long-sought goal in the field of neural prosthetics, and the team’s method is able to recover automatically from instabilities without requiring the user to pause to recalibrate the system by themselves. It would vastly improve the lives of BCI users.