[ad_1]
New research coming out of Carnegie Mellon University (CMU) and the University of Pittsburgh (Pitt) will dramatically improve and stabilize brain-computer interfaces.
The investigation was published in Biomedical Engineering of Nature, with the article entitled “A stabilized brain-computer interface based on the alignment of multiple neural nets”.
Brain-Computer Interfaces (BCI)
Brain-computer interfaces (BCI) are devices capable of enabling disabled people to control prosthetic limbs, computer curses, or other interfaces using their minds.
One of the biggest challenges associated with the use of BCI in a clinical setting is that neural records can be unstable. The individual controlling the BCI may lose control due to variations in the signals picked up by the BCI.
Every time this loss of control occurs, the individual must go through a recalibration process. The individual has to re-establish the connection between his mental commands and the tasks being performed, and another human technician often has to be present.
William Bishop is a member of the Janelia Farm Research campus. He was previously a doctoral student and a postdoctoral fellow in the CMU Machine Learning Department.
“Imagine if every time we wanted to use our cell phone, in order for it to work properly, we had to somehow calibrate the screen so that it knew which part of the screen we were aiming at,” Bishop says. “The current state of BCI technology is something like this. Just in order for these BCI devices to work, users have to do this recalibration frequently. That is extremely inconvenient for users as well as for technicians who maintain the devices. “
New machine learning algorithm
The researchers presented a new machine learning algorithm capable of accounting for variable signals. The individual can maintain control of the BCI even when instabilities are present. The researchers developed this after discovering that the activity of the neural population takes place in a low-dimensional “neural variety”.
Alan Degenhart is a postdoctoral researcher in electrical and computer engineering at CMU.
“When we say ‘stabilization’, what we mean is that our neural signals are unstable, possibly because we are recording from different neurons over time,” says Degenhart. “We have discovered a way to take different populations of neurons over time and use their information to essentially reveal a common picture of the computation that is occurring in the brain, thus keeping the BCI calibrated despite neuronal instabilities.”
Previous methods
Previous approaches to self-calibration methods have also faced challenges related to instability. Unlike other methods, this does not depend on the good performance of the subject during the recalibration process.
Byron Yu is a professor of electrical and computer engineering and biomedical engineering at CMU.
“Let’s say the instability was so great that the subject could no longer control the BCI,” Yu explains. “Existing self-calibration procedures are likely to have difficulties in that scenario, whereas in our method, we have shown that in many cases you can recover from those catastrophic instabilities.”
Emily Oby, a postdoctoral researcher in neurobiology at Pitt, also spoke on the subject of instability.
“Neural recording instabilities are not well characterized, but it is a very big problem,” says Oby. “There is not much literature that we can point to, but anecdotally, many of the laboratories that conduct clinical research with BCI have to deal with this problem quite frequently. This work has the potential to greatly improve the clinical viability of BCI and help to stabilize other neural interfaces. “
The document also included authors Steve Chase, professor of biomedical engineering and the Institute of Neuroscience at CMU, along with Aaron Batists, associate professor of bioengineering at Pitt, and Elizabeth Tyler-Kabara, associate professor of neurological surgery at Pitt.
The research was funded by the Craig H Neilsen Foundation, the National Institutes of Health, the DSF Charitable Foundation, the National Science Foundation, the Pennsylvania Department of Health Research, and the Simons Foundation.
