Image source: Carnegie Mellon University's Human-Computer Interaction Institute (HCII)

Researchers show smartwatches can figure out exactly what you are up to all day

Wearables may present a future privacy nightmare. It has been shown that a simple software upgrade can allow companies to figure out exactly what sorts of activities a wearer is engaged in.

Essential readingTop fitness trackers and health gadgets

Smartwatches and fitness trackers are designed to be able to assess activities such as walking, running, biking, swimming and sleeping. However, a team of scientists at Carnegie Mellon University’s Human-Computer Interaction Institute (HCII) have demonstrated such devices can be made much more context sensitive.

They recruited 50 people over the course of two weeks to wear standard smartwatches and monitored them as they went about their daily activities. A special app on the watch gathered data churned out by the accelerometer and, in some cases, bio-acoustic sounds to make guesses on what type of activity the wearer was engaged in. The participants were then asked to describe the hand activity at that moment.

Using this technique, 25 different activities were recognized with more than 95% accuracy. They include typing on a keyboard, washing dishes, twisting a jar, petting a dog, brushing teeth, pouring from a pitcher and more. Altogether, some 80 hand activities were identified presenting a unique dataset.

This information could be utilized for a wide range of applications. For example, similar to how smartphones can block messages when a user is driving, smartwatches could prevent interruption when someone is chopping the veggies or handling power equipment.

Such information could also be used to help wean people off bad habits such as smoking, or to make sure they engage in healthy habits regularly such as washing their teeth. The possibilities are endless.

“Hand-sensing also might be used by apps that provide feedback to users who are learning a new skill, such as playing a musical instrument, or undergoing physical rehabilitation,” the study notes.

The constraint, of course, is that the user needs to wear the smartwatch on their dominant arm. People usually wear such devices on their passive arm which is less engaged in everyday activity.

“We envision smartwatches as a unique beachhead on the body for capturing rich, everyday activities,” said Chris Harrison, Assistant Professor in Human-Computer Interaction Institute (HCII) at Carnegie.

“A wide variety of apps could be made smarter and more context-sensitive if our devices knew the activity of our bodies and hands.”

This does, however, spark some privacy concerns. If watches get too clever they will know exactly what you are up to all day. And most people would not be too happy with that.

The paper is being presented this week at “CHI 2019”, the Association for Computing Machinery’s conference on human factors in computing systems in Scotland. Check out the video below – it makes interesting viewing.

Like this article? Subscribe to our monthly newsletter and never miss out!

Leave a Reply

Your email address will not be published.

This site uses Akismet to reduce spam. Learn how your comment data is processed.