The implants used are part of a long-standing research collaboration called BrainGate or brain computer interface (BCI) which uses artificial intelligence (AI) to interpret neural activity signals generated during handwriting.
The experiment was conducted on T5 who has been paralyzed from the neck down since 2007 after a traffic accident. During the experiment, T5 concentrated as if he was writing, thinking about making letters with an imaginary pen and paper.
READ: Scientists Develop Anti-Bacterial Bandage from Duren’s Skin
Electrode implanted in his motor cortex recorded signals of his brain activity which were then interpreted by an algorithm running on an external computer. It then decodes the T5’s imaginary pen trajectory, which mentally traces the 26 letters of the alphabet and some basic punctuation marks.
“This new system uses the rich neural activity recorded by intracortical electrodes and the power of language models. When applied to neurally decoded letters, it can create fast and accurate text,” said study first author Frank Willett, a neuroprosthetician. researchers from Stanford University as quoted Science Alert, Tuesday (9/11/2021).
Here, the T5 demonstrates the capabilities of a virtual handwriting system for people who have almost lost all independent physical movement. In testing, the man was able to achieve a writing speed of 90 characters per minute or about 18 words per minute, with an accuracy of about 94 percent.
That speed is almost equivalent to the typing speed of smartphone users, which is about 115 characters or 23 words per minute, the researchers said. “We’ve learned that the brain retains its ability to prescribe subtle movements after the body loses its ability to perform those movements,” says Willett.
– .
