Scientists at the University of Sussex in the UK have developed a new algorithm that enables wearables to automatically detect and record new movements of the user.
Current wearables and smartwatches on the market have to be manually notified about activities other than walking, and even then they are limited to activities such as running and cycling.
According to Post-Doctoral Research Fellow of Engineering and Design at the University of Sussex, Dr Hristijan Gjoreski, the new algorithm enables wearables to track a variety of activities as they happen outside of exercising, such as when the user is brushing their teeth or cutting vegetables. The algorithm can also track sedentary activity, such as if the user is lying down or sitting.
“Current activity-recognition systems usually fail because they are limited to recognising a predefined set of activities, whereas of course human activities are not limited and change with time,” said Dr Gjoreski.
“Here we present a new machine-learning approach that detects new human activities as they happen in real-time, and which outperforms competing approaches,” continued Dr Gjoreski.
According to the scientists, wearable technology generally tracks the user’s acvity in clusters and estimates what they had been doing, and for how long. The issue with this is that they are unable to account for pauses or interruptions in the activity.
The new algorithm overcomes this by tracking on-going activity, paying close attention to transitioning, as well as the activity itself. This is an important development because it creates data that is more accurate and usable, not only in helping users manage their fitness levels, but also when wearables are used in a clinical setting to monitor patients.
“Future smartwatches will be able to better analyse and understand our activities by automatically discovering when we engage in some new type of activity,” said Head of the Sensor Research Technology Group at the University of Sussex, Dr Daniel Roggen.
“This new method for activity discovery paints a far richer, more accurate, picture of daily human life. As well as for fitness and lifestyle trackers, this can be used in healthcare scenarios and in fields such as consumer behaviour research,” concluded Dr Roggen.