Smartwatches can recognize hand movements
Washington, May 8 (PTI) Smartwatches can recognize a range of hand movements and identify what the wearer is doing, scientists have found, paving the way for new health-related apps that could monitor activities such as brush your teeth or smoke a cigarette.
Researchers at Carnegie Mellon University in the United States used a standard smartwatch to determine when a wearer was typing on a keyboard, washing dishes, stroking 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 recognize hand movements and, in some cases, bio-acoustic sounds associated with 25 different hand activities with an accuracy of about 95%.
These 25 activities are just the beginning of what can be detected.
“We envision smartwatches as a unique foothold on the body for capturing rich everyday activities,” said Chris Harrison, assistant professor at Carnegie Mellon.
“A wide variety of applications could be made smarter and more contextual if our devices knew about the activity of our bodies and hands,” Harrison said in a statement.
Just as smartphones can now block texting while a user is driving, future devices that detect hand activity might learn not to interrupt someone while they are doing certain work with their hands, such as cutting off hands. vegetables or operate electrical equipment, a PhD student told Carnegie Mellon.
Hand activity detection also lends itself to health-related applications – monitoring activities such as brushing teeth, washing hands or smoking a cigarette.
Manual detection can also be used by applications that provide feedback to users learning a new skill, such as playing a musical instrument or undergoing physical rehabilitation.
Apps can alert users to typing habits that can lead to repetitive strain injuries (RSI) or assess the onset of motor impairments such as those associated with Parkinson’s disease.
The researchers began their exploration of detecting hand activity by recruiting 50 people to wear specially programmed smartwatches for nearly 1,000 hours while going about their daily activities.
Periodically, the watches recorded hand movement, hand orientation, and bio-acoustic information, then prompted the wearer to describe hand activity – shaving, clapping, scratching, putting on lipstick. , etc.
Over 80 manual activities have been labeled in this way, providing a unique data set.
For now, users must wear the smartwatch on their active arm, rather than the passive (non-dominant) arm where people typically wear wristwatches, for the system to work. Future experiments will explore which events can be detected using the passive arm.
“The 25 manual activities we evaluated are only a small fraction of the ways we engage our arms and hands in the real world,” Laput said.
Future work is likely to focus on categories of activities – those associated with specific activities such as smoking cessation, elderly care or typing. PTI MHN MHN
Warning :- This story has not been edited by Outlook staff and is auto-generated from news agency feeds. Source: PTI