A team of scientists at the University of Sussex has developed a new algorithm that enables smart watches to detect and learn every move you make – all without being told what to look for.
Currently, regular smart watches can recognize a limited number of activities, such as running or yoga. However, as with most machines, these activities need to be programmed in advance.
The new method works differently – it enables the technology to discover activities as they happen, without being told beforehand what to look for. But that’s not all – the activities that the technology can discover are not limited to exercises only – you brushing your teeth or cutting veggies counts too. In fact, the new algorithm can even track sedentary activity!
Here is what Dr. Hristijan Gjoreski of the University of Sussex said has to say about the new technology: “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. Here we present a new machine-learning approach that detects new human activities as they happen in real time, and which outperforms competing approaches.”
All in all, it appears infinitely better smart watches await us in the not-so-distant future.
Source:
University of Sussex via ScienceDaily (https://www.sciencedaily.com/releases/2017/09/170904093430.htm)
The Wonderful World of Algorithms 