New brain-sensing technology invented by Stanford University neurosurgeons has been used to enable monkeys to transcribe passages from the works of Shakespeare and a prominent national newspaper at a rate of up to 12 words per minute, the school announced on Monday.
In a pilot experiment, the technology developed by electrical engineering professor Krishna Shenoy and postdoctoral fellow Paul Nuyujukian enabled the primates to replicate sections from Hamlet and the New York Times by directly reading their brain signals, then using the data it collected to direct a cursor over a keyboard, the researchers explained in a press release.
Previous versions of the technology, which was created to help people with movement disorders communicate, had been somewhat successful but what “slow and imprecise,” the scientists said. The latest experiments were designed to test improvements seeking to improve the accuracy and speed of the brain scanning interface, and thus far, they are optimistic about the results.
“Our results demonstrate that this interface may have great promise for use in people. It enables a typing rate sufficient for a meaningful conversation,” explained Nuyujukian, who plans to join Stanford’s faculty as an assistant professor of bioengineering in 2017. The Institute of Electrical and Electronics Engineers has published a paper detailing his team’s work.
Device could make it easier for paralyzed people to communicate
While most currently available technology in this field either tracks the movements of the eyes or individual facial muscles, such devices are limited and require a level of muscular control that some individuals simply do not have, the study authors explained. However, directly monitoring brain signals could eliminate such issues, making communication much easier.
The device that Shenoy and Nuyujukian are working on uses a multi-electrode array implanted in the brain to directly read signals from the regions of the brain that typically directs movements of the hand and arm, and uses algorithms to transmit that information directly to a computer mouse. Those algorithms are what the Stanford researchers say they have been working to improve.
The interface used in the experiments was “exactly what a human would use,” Nuyujukian said, and while individual components of it had already been tested, the new study marks the first time that the team has measured the typing rate that was possible using the technology. As it turns out, the improved algorithms allowed the animals to time three times more quickly than was possible using other brain-to-computer interfaces, according to the study authors.
However, they also note that the monkeys being used to test the technology had been specifically trained to type letters corresponding to what appeared on a screen in front of them. People using the system would likely type more slowly and would be unlikely to achieve the 12 words/minute threshold, as they would stop to think about what they wanted to say or how certain words would be spelled. Nonetheless, Nuyujukian touted the technology as a significant advancement.
“We cannot quantify is the cognitive load of figuring out what words you are trying to say,” he explained in a statement. “Also understand that we’re not using auto completion here like your smartphone does where it guesses your words for you.” However, he noted that the technology could eventually be linked with the same kind of word-completion technology used by popular smartphones or tablets to further increase typing speeds.
—–
Image credit: Thinkstock
Comments