Scientists have developed a brain-computer interface (BCI) that successfully recognizes brain activities associated with handwriting individual letters, using this to generate text on the screen.
Describing their work ,the study’s authors find that the system was tested on one paralyzed patient, who was able to type 90 characters per minute simply by imagining that he was writing by hand. This set a new world record in typing speed using the brain-computer interface.
The study participant was a 65-year-old man who was paralyzed from the neck down after a spinal cord injury in 2007. A decade later, he had two electrodes inserted into a part of his brain called the motor cortex, which coordinates movement. Using this system, he could type 40 characters per minute visualizing the hand movements needed to maneuver the cursor and click on the letters displayed on the screen.
At the time, this was the fastest typing rate achieved by any BCI, but the results of this latest study more than doubled that record.
“This approach has allowed a person with paralysis to compose sentences at a speed almost comparable to able-bodied adults of the same age typing on a smartphone,” senior study author James Henderson said in a statement. “The goal is to restore the ability to communicate with text.”
Although he could not really move his hand, the respondent was instructed to imagine a notebook and pencil in front of him and to concentrate on writing individual letters. The brain associated with these movements was captured by electrodes and inserted into an algorithm, which was then able to learn a specific neural signature that refers to each letter of the alphabet.
Although decoding brain activity behind such fine movements may sound more challenging than deciphering activities associated with basic actions such as moving the cursor in a straight line, researchers report that it is in fact the opposite.
“We have learned that complex movements that involve changing speed and curved paths, such as handwriting, can be more easily and quickly interpreted by the artificial intelligence algorithms we use than simple intended movements such as moving the cursor in a straight path at a constant speed,” said study lead author Francis Villett.
This is because each letter evokes an extremely unique pattern of neural activity, which makes them easily recognizable.