New algorithm allows smartwatches to track your every move
Researchers develop algorithm that enables smartwatches to track you beyond basic movements and exercising.tech Updated: Sep 04, 2017 13:11 IST
Activity trackers on current smartwatches are restricted to recognising certain activities such as yoga and running. Scientists have now developed a new algorithm that that enables smartwatches to track your each and every move, be it brushing your teeth or cooking. The new algorithm is expected to make smartwatches a better assistant for users.
The new method, developed by researchers from University of Sussex in the UK, enables the technology to discover activities as they happen, not just simply when exercising, but also when brushing your teeth or cutting vegetables.
Traditional models “cluster” together bursts of activity to estimate what a person has been doing, and for how long, researchers said.
For example, a series of continuous steps may be clustered into a walk. Where they falter is that they do not account for pauses or interruptions in the activity, and, so, a walk interrupted with two short stops would be clustered into three separate walks.
The new algorithm tracks ongoing activity, paying close attention to transitioning, as well as the activity itself. In the example above, it assumes that the walk will continue following the short pauses, and therefore holds the data while it waits.
“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 Hristijan Gjoreski of the University of Sussex.
“Here we present a new machine-learning approach that detects new human activities as they happen in real time, and which outperforms competing approaches,” Gjoreski said.
Future smartwatches will be able to better analyse and understand our activities by automatically discovering when we engage in some new type of activity.
“This new method for activity discovery paints a far richer, more accurate, picture of daily human life,” said Daniel Roggen of University of Sussex.
“As well as for fitness and lifestyle trackers, this can be used in health care scenarios and in fields such as consumer behaviour research,” he added.