Smart watches are increasingly becoming their own, instead of simply accessories that are based on the functionality of other devices and are reflected in them. However, there are some scenarios in which it would be useful for our smart watches to work more closely with the objects around us, whether it is knowing what we are doing on our smartphones, exercising when we type on a keyboard, or even something so mundane. like understanding when we use a cheese grater or wash our hands under the tap.
To solve this problem, researchers at Carnegie Mellon University discovered a way to capture the manual activity of farmers in smartwatch users. "The results could make the experience of using a smart watch more powerful and context-aware."
"For so long, smart watches have only been able to track whole-body activities, such as walking, running, biking. and sleep, "Chris Harrison, director of the Future Interfaces Group (FIG) at Carnegie Mellon, told Digital Trends," But with smartwatches on the wrist, we always suspect that they could also track what the hands do, like writing, writing, eating, drinking, scratching, [and more] This opens a new world of recognition of high fidelity activities that was not possible before ".
In an article presented this week at the ACM CHI 2019 conference in Glasgow, Scotland, researchers describe how they could achieve these fine-grained hand activity data by overclocking the built-in accelerometer of the 4kHz smart watch. By combining the data collected from volunteers with the correct machine learning algorithms, the system can determine which of the 25 manual activities is performed at a given time, with 95.2% accuracy.
"That's the best part: [it requires] There's no extra hardware," Harrison continues. "Your smart watch already has everything you need to unlock this type of tracking. It could be enabled on devices with little more than a software update. "
Harrison and co-author Gierad Laput describe a number of different potential applications, for example, when tracking when you're typing, your smart watch might recommend regular breaks. You can keep track of the drinks you drink, reminding you to stay hydrated, similarly, it could be used to track the frequency and time a person eats, something that could be used for the rudimentary calorie count. , could detect when a person plays with their hands and use this as a proxy for anxiety to build systems that respond better to their mood.
"If we can feel what your hands are doing, you could" unlock a set of compelling applications that are more caring, more accommodating, and that can lead people to lead a better life It's healthy, "said Harrison.