Have you imagined a situation of typing on a computer without a keyboard, playing a video game without a controller, or driving a car without a wheel? A new device developed by engineers at the University of California, Berkeley, that can recognize hand gestures based on electrical signals detected in the forearm. The system, which conglomerates wearable biosensors with artificial intelligence (AI), could one day be used to control prosthetics or to interact with almost any type of electronic device.
Ali Moin, who helped design the device as a doctoral student in UC Berkeley’s Department of Electrical Engineering and Computer Sciences mentioned that “Prosthetics are one important application of this technology, but besides that, it also offers a very intuitive way of communicating with computers”. He also mentioned that “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 is the co-first author of a new paper describing the device, that appeared online on Dec. 21 in the journal Nature Electronics. To create the hand gesture recognition system, initially, the team conjoined with Ana Arias, a professor of electrical engineering at UC Berkeley, to design a flexible armband that can read the electrical signals at 64 different points on the forearm. The electrical signals are fed into an electrical chip, which is programmed with an AI algorithm that is capable of associating these signal patterns in the forearm with particular hand gestures.
The team succeeded in teaching the algorithm to identify 21 individual hand gestures, which comprises of a thumbs-up, a fist, a flat hand, holding up individual fingers, and counting numbers. The algorithm has to initially “learn” how electrical signals in the arm correspond with individual hand gestures. For this, each user has to wear the cuff while making the hand gestures one by one.
The new device makes use of a type of advanced AI called a hyperdimensional computing algorithm. This algorithm is capable of updating itself with new information. If the electrical signals linked to a particular hand gesture changes due to the user’s arm getting sweat, or when they raise their arm above their head, the algorithm can incorporate this new information into its model.
Another benefit of the device is that all of its computing occurs on a local chip. No personal data are transmitted to a nearby computer or any other device. This ensures privacy in personal biological data and also speeds up the computational time. The Donald O. Pedersen Distinguished Professor of Electrical Engineering at UC Berkeley and senior author of the paper Jan Rabaey said that “When Amazon or Apple creates their algorithms, they run a bunch of software in the cloud that creates the model, and then the model gets downloaded onto your device”. He also adds to this that the major problem is that we get stuck with a particular model. He mentions that they have used a process where the learning is done on the device itself which was a fast procedure and the procedure needs to be done only once rest will be learned by the device itself. With a few tweaks, this device will turn out to be a commercial product Rabaey said. The unique factor about this device is that it conglomerates biosensing, signal processing and interpretation, and artificial intelligence into one system. The system is comparatively small, flexible with an affordable budget.
Reference:
Also read an interesting article concerning the digital world:- https://shasthrasnehi.com/5g-refining-the-digital-world/
Author
