(Subscribe to our Today's Cache newsletter for a quick snapshot of top 5 tech stories. Click here to subscribe for free.)
A new device uses wearable biosensors and artificial intelligence (AI) to recognise hand gestures from electrical signals in the forearm.
Developed by a team of international researchers, the device can potentially help control prosthetic limbs using electrical signal. The team detailed their work in a paper titled ‘A wearable biosensing system with in-sensor adaptive machine learning for hand gesture recognition’, published in the journal Nature Electronics .
Also read | A portable brain-monitoring device to tackle mental health issues
The biosensing device has a flexible armband to detect electrical signals from 64 points on the forearm. It also has an AI-powered electrical chip to correlate with signal patterns detected in the forearm with specific hand gestures.
The algorithm has been taught to recognise 21 unique hand gestures, including thumbs-up, fist, flat hand, holding up individual fingers and counting numbers, a University of California Berkley, release noted.
“When you want your hand muscles to contract, your brain sends electrical signals through neurons in your neck and shoulders to muscle fibres in your arms and hands. Essentially, what the electrodes in the cuff are sensing is this electrical field,” Ali Moin, a doctoral student at UC Berkeley, explained in a release.
Also Read | A wearable that can track facial expressions while wearing masks
The training process involves wearing the cuff and performing specific hand gestures, one at a time, to help AI learn. According to the researchers, a new type of advanced AI used in the device, can also update itself with new information.
“Reading hand gestures is one way of improving human-computer interaction. And, while there are other ways of doing that, by, for instance, using cameras and computer vision, this is a good solution that also maintains an individual’s privacy,” Moin noted.
As the electronic chip does all the processing locally, it reduces the computing time, and also does not transmit a user’s personal data to other devices in close proximity, the release stated.
Also Read | AI-controlled sensors can improve patient outcomes in smart hospitals, Stanford says
“Most of these technologies already exist elsewhere, but what’s unique about this device is that it integrates the biosensing, signal processing and interpretation, and artificial intelligence into one system that is relatively small and flexible and has a low power budget,” Jan Rabaey, Professor of Electrical Engineering at UC Berkeley and lead author of the paper, said.
The device still needs to be developed for use in commercial products.
