A New Algorithm Will Allow Smartwatches to Learn and Monitor Your Every Move

Smartwatch Monitoring

Smartwatches range from simple fitness tracking wristbands to devices like the Apple Watch, which has a surprising range of functionality comparable even to smartphones. They have become a commonplace tool for business professionals, students, athletes, and so many more. But, as concerns continue to rise about privacy in an era of lightning-fast progress, are smartwatches getting too smart?

Scientists at the University of Sussex have developed an algorithm that takes smartwatches to the next level. It enables the device to both detect and record everything that you do, without instruction. Existing watches are programmed to detect only specific activities, like when you are running, doing yoga, even sitting still. But this algorithm bypasses such instruction.

Hristijan Gjoreski of the University of Sussex said in a press release, "Current activity-recognition systems usually fail because they are limited to recognizing a predefined set of activities, whereas of course human activities are not limited and change with time." He continued in stating that, "Here we present a new machine-learning approach that detects new human activities as they happen in real time, and which outperforms competing approaches."

A Richer Picture?

Gjoreski seems to be right. By eliminating the limits of defined activity as older models do, smartwatches would be able to better track and record human activity. This could have personal, scientific, and even medical benefits. As put by Daniel Roggen, head of the Sensor Research Technology Group at the University of Sussex, in the press release:

This is a major technological development and its impact could prove to be life-saving. But in the meantime, it is important to take a step back and wonder: When it is possible to track my every move, should I?