A new study by a team of researchers from Carnegie Mellon University (CMU) and University of Pittsburgh (Pitt) will contribute to significantly improve and stabilize BCIs, i.e. the brain-computer interfaces. The algorithm examined by scholars is able to stabilize interface adaptations to neural signals. The research results have been published in Nature Biomedical Engineering.
What are brain-computer interfaces?
Many people who have suffered injuries or suffer from debilitating diseases of the nervous system partially or totally lose the ability to control muscle movements. Many of them are no longer able to walk, drive or play music on their own. They may still think in their minds about how to do the actions, but their body is not responding.
Brain-computer interfaces are devices that allow direct communication between a brain and a computer. In the context of neuroengineering, the role played by BCIs is to provide functional support and assistance to people with motor disabilities to control prosthetic limbs, computer cursors or to perform other types of activities using their minds.
For more informations read also Elon Musk: brain-machine interface functioning within a year
The problem of instability in registrations
One of the biggest problems interfaces encounter in the clinical setting is the instability of neural recordings. Over time, the signals collected by the device may vary and this variability can affect the adaptation of the interface, causing the individual to lose the ability to control their BCI.
Whenever this loss of control occurs, the individual must undergo a recalibration process to restore the connection between the mental commands and the activities performed. Generally, it is a procedure that requires the intervention of 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,” says William Bishop, who was previously a Ph.D. student and postdoctoral fellow in the Department of Machine Learning at CMU and is now a fellow at Janelia 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.”
The study of a new algorithm
The research team is studying a machine learning algorithm that accounts for the variability of the signals but that allows the person using the BCI to continue to control the device anyway. The researchers developed it after discovering that the activity of the neural population takes place in a low-dimensional “neural manifold”. Starting from this discovery, scholars can stabilize neural activity to maintain good neural device performance even in the presence of unstable recordings.
“When we say ‘stabilization,’ what we mean is that our neural signals are unstable, possibly because we’re recording from different neurons across time,” explains Alan Degenhart, a postdoctoral researcher in electrical and computer engineering at CMU. “We 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.”
For more informations read also Machine Learning Methodologies in BCI
The previous methods
This is not the first study attempting to solve the problem of brain-computer interfaces recalibration, a problem that has been pending for a long time. Previous studies have proposed self-recalibration procedures but have faced the problem of how to manage instabilities. The novelty of this research is the possibility of recovery of the neural interface also following catastrophic instabilities because it is not based on collaboration and the correct execution of the actions by the subject during recalibration.
“Let’s say that the instability were so large such that the subject were no longer able to control the BCI,” explains Byron Yu, a professor of electrical and computer engineering and biomedical engineering at CMU. “Existing self-recalibration procedures are likely to struggle in that scenario, whereas in our method, we’ve demonstrated it can in many cases recover from those catastrophic instabilities.”
“Neural recording instabilities are not well characterized, but it’s a very large problem,” says Emily Oby, a postdoctoral researcher in neurobiology at Pitt. “There’s not a lot of literature we can point to, but anecdotally, a lot of the labs that do clinical research with BCI have to deal with this issue quite frequently. This work has the potential to greatly improve the clinical viability of BCIs, and to help stabilize other neural interfaces.”