Continuously correcting BCI technique improves precision

Stanford‘s Krishna Shenoy has developed a more precise brain-controlled cursor for a virtual keyboard using a technique that continuously corrects brain readings.

An algorithm analyzes the measured electrical signals that a prosthetic device obtained from sampled neurons. It adjusts  the signals so that the sample’s dynamics were more like baseline brain dynamics.

The thought-controlled keypad would allow a person with paralysis or ALS to run an electronic wheelchair and use a computer or tablet. Today an eye-tracking system is used to direct cursors, or a “head mouse, ” which tracks the movement of the head.  Both are fatiguing, and  neither provides the natural and intuitive control of readings taken directly from the brain.

Stanford University video detailing single trial dynamics of motor cortex and their applications to brain-machine-interfaces:

This video includes two clips. In the first, flashing targets on a virtual keypad are hit by monkeys (not shown) using their hands. The second clip also shows targets being hit. But this time, the motion is directed by an experimental device that taps into the monkey’s brain. This device discerns their intention to hit the target and translates this thought into an electronic command that controls a virtual cursor. In the first clip the monkeys hit 10 targets in 9.9 second with their hands. It takes 11.4 seconds to hit 10 targets using the thought-control device.


Posted

in

, ,

by

Tags: