IBM researchers have developed a first-of-a-kind”fingernail Detector” prototype that uses artificial intelligence and machine learning to monitor and
The wearablewireless device continuously measures how a individual’s fingernail bends and moves, and it is an integral indicator of grip power.
Although skin-based sensors can help capture things like movement, the health of muscles and neural cells, and can also reflect the intensity of a person’s emotional state, these may often lead to problems, including disease with older individuals.
But the new system utilizes signals from the fingernail bends such as the tactile feeling of temperature, pressure, surface textures.
“Our fingernails deform – bend and move – in stereotypic ways when we use them for grasping, grasping, and even flexing and extending our palms. This deformation is generally on the order of single digit microns rather than observable to the naked eye,” said Katsuyuki Sakuma, by IBM’s Thomas J. Watson Research Center in New York.
The new device, reported in the journal Scientific Reports, is composed of strain gauges attached to the fingernail along with a little computer that samples pressure values, collects accelerometer data and communicates using a smartwatch.
The watch also conducts machine learning models to speed bradykinesia, tremor, and dyskinesia that are all symptoms of Parkinson’s disease.
“By pushing computation to the end of our hands, we have found a new use for our claws by detecting and characterising their delicate moves,” Sakuma said.
“With the detector, we could derive health state insights and empower a new type of user interface. This work has also functioned as the inspiration for a new apparatus modelled on the arrangement of the fingertip that may one day assist quadriplegics communicate,” Sakuma noted.