Soft, Wireless Brain-Computer Interface Turns Your Thoughts Into Actions

Designed to transmit via Bluetooth, this prototype soft-circuit wireless EEG feeds a machine learning system to control things by thought.

A multi-institutional team of researchers, lead by the Georgia Institute of Technology, have showcased a soft wireless brain-machine interface that, they say, allows the wearer to simply imagine an action — such as controlling a wheelchair or moving a robotic arm — to have it take place.

"The major advantage of this system to the user, compared to what currently exists, is that it is soft and comfortable to wear," Woon-Hong Yeo, associate professor at the School of Mechanical Engineering at Georgia Tech, explained of the device the team has created, "and doesn't have any wires."

"This new brain-machine interface uses an entirely different paradigm, involving imagined motor actions, such as grasping with either hand, which frees the subject from having to look at too much stimuli," added lead author Musa Mahmood of the team's work.

The system relies on a soft-circuit electroencephalogram headset created by impregnating the material with supposedly-imperceptible microneedle electrodes. Compared to traditional EEG sensors, it's more comfortable, offers improved signal acquisition — and doesn't have wires dangling all over the place.

With data capture sorted, the team turned to a custom machine learning algorithm and a virtual reality component — providing visual cues to the users while interpreting their intentions and translating them into interactions in the virtual world — to make use of the data.

The compact EEG records across six channels, transmitting to a tablet via Bluetooth. (📹: Mahmood et al)

"The virtual prompts have proven to be very helpful," Yeo added. "They speed up and improve user engagement and accuracy. And we were able to record continuous, high-quality motor imagery activity."

The system has been tested successfully on four human subjects, but has not yet been tried on anyone with disabilities.

The work has been published under open-access terms in the journal Advanced Science.

Gareth Halfacree
Freelance journalist, technical author, hacker, tinkerer, erstwhile sysadmin. For hire: freelance@halfacree.co.uk.
Latest articles
Sponsored articles
Related articles
Latest articles
Read more
Related articles