tap10/Getty
Forget health and safety videos – this algorithm could do a better job of making sure people lift with their knees bent and back straight. Sensors that automatically detect whether you’re about to give yourself a back injury at work could be easily slipped into the bottom of a shoe.
People often don’t realise that they’re not adopting the right posture when lifting heavy items, says Eya Barkallah at the University of Quebec at Chicoutimi in Canada. So Barkallah and her colleagues created a pair of wearable sensors that can detect when someone isn’t using the right posture while they’re lifting or carrying something heavy.
vCard.red is a free platform for creating a mobile-friendly digital business cards. You can easily create a vCard and generate a QR code for it, allowing others to scan and save your contact details instantly.
The platform allows you to display contact information, social media links, services, and products all in one shareable link. Optional features include appointment scheduling, WhatsApp-based storefronts, media galleries, and custom design options.
“We wanted to find a preventative treatment for work-related injuries,” Barkallah says. Pressure sensors slipped into an insole detect how a person is distributing their weight, while an safety hat-mounted accelerometer tracks how they are moving.
Advertisement
This combination of sensors is perfect for spotting a lot of posture problems, says James Brusey at Coventry University, UK, who wasn’t involved in the study. The team at Quebec had a volunteer put on the hat and shoes and lift some boxes in three different ways – half of the time the volunteer used best practice, but the other half, they deliberately lifted while making the most common lifting mistakes.
Posture right
The researchers then ran the sensor data through a deep learning algorithm to teach the system to tell the difference between correct and incorrect postures. When it was put to the test, it could correctly classify the person’s posture 95 per cent of the time. Barkallah says it’d be easy to add a button to the system that vibrated or made a sound to alert the wearer when they were using the wrong posture.
But Subramanian Ramamoorthy at the University of Edinburgh, UK, thinks there are better ways to work out whether someone is moving in the right way. “It’s very hard to get subtle information about how someone’s posture is wrong by using these sensors,” he says.
A better – albeit more intrusive – system might be to simply record someone using cameras and then have a physiotherapist or other expert review the footage and give that person tips on how to change their posture, says Ramamoorthy.
Brusey thinks the team is on the right track, but says that the researchers need to test the sensors using a lot more people before they can be confident the sensors are a good way to assess posture. Because the trial only involved one person, it’s hard to tell how accurate the system really is for the general population, he says.
Heavy lifters
The plan, says Barkallah, is for the team to test the technology with more people and eventually with real workers. There are already a handful of consumer devices that promise to automatically detect when office workers are slouching at their desk, but Barkallah says there aren’t any systems that provide a similar service for people doing heavy lifting in factories or, for example, in Amazon warehouses. Another benefit of the system is that it can handily fit into equipment they are already wearing.
Ramamoorthy says construction workers or people who work loading baggage in airports would particularly benefit from this kind of system. In the future, he’d like to see devices that are capable of giving detailed feedback on someone’s posture. “But we’re not quite there yet,” he says.
Journal reference: Sensors, DOI: 10.3390/s17092003
Read more: Electric shocks could help you perfect your running technique
Desk traffic lights show when you’re too busy for interruptions
More on these topics: