Smartwatches can recognise hand movements

Smartwatches can recognise a range of hand motions and identify what the wearer is doing, scientists have found, paving the way for novel health-related apps that could monitor activities such as brushing teeth or smoking a cigarette.

Researchers at Carnegie Mellon University in the US have used a standard smartwatch to figure out when a wearer was typing on a keyboard, washing dishes, petting a dog, pouring from a pitcher or cutting with scissors. By making a few changes to the watch's operating system, they were able to use its accelerometer to recognise hand motions and, in some cases, bio-acoustic sounds associated with 25 different hand activities at around 95 per cent accuracy.

Those 25 activities are just the beginning of what might be possible to detect. "We envision smartwatches as a unique beachhead on the body for capturing rich, everyday activities," said Chris Harrison, assistant professor at Carnegie Mellon. "A wide variety of apps could be made smarter and more context-sensitive if our devices knew the activity of our bodies and hands," Harrison said in a statement.