Categories
Hackster.io

Wearable Brain-Machine Interface Could Help the Disabled Control Wheelchairs Wirelessly

Brain-machine interface technologies are growing and hold promise for those with neurological disorders and those who are disabled. Flexible electronics are continuously being adopted for use in the medical field, and a new class of materials combined with a deep learning algorithm has allowed researchers at Georgia Tech to design a new BMI platform that could help disabled people wirelessly control an electric wheelchair.

The BMI captures and processes EEG signals and sends them to a tablet, where it can then be used to control electric wheelchairs. (📷: Georgia Tech)

“By providing a fully portable, wireless brain-machine interface (BMI), the wearable system could offer an improvement over conventional electroencephalography (EEG) for measuring signals from visually evoked potentials in the human brain. The system’s ability to measure EEG signals for BMI has been evaluated with six human subjects, but has not been studied with disabled individuals.”

The BMI platform is comprised of three main parts- highly-flexible hair-mounted electrodes that make direct contact with the wearer’s scalp through the hair, an ultra-thin skin-like printed nanomembrane electrode, and flexible electronics with integrated Bluetooth telemetry unit. The platform functions by recording the EEG signals from the brain and processes that information using the flexible circuitry, and then wirelessly transmits that data over to a tablet (up to 15 meters away), which could then be used to control an electric wheelchair.

The printed electrodes adhere directly to the skin without the need for tape or adhesives. (📷: Georgia Tech)

Like all electronics, the BMI generates noise due to the low-signal amplitude, which is similar to ‘electronic noise’ in the body. The platform relies on the accurate measurement of the EEG signals and deals with the variances of the human brain, so to root-out any electrical noise, the researchers created a deep-learning neural network algorithm to identify where the best position for the electrodes are placed, which reduces the number of electrodes needed. The engineers are currently looking at ways to improve those electrodes, and making the platform more useful for motor-impaired individuals.

Go to Source
Author: Cabe Atwell

By admin

I'm awesome! What else would I say about myself.