Live
- AI helps erase racist deed restrictions in California
- ATMIS completes third phase of troops' drawdown in Somalia
- PM Kisan Samman Nidhi scheme bringing smile to Nalanda farmers
- German economy forecast to lag eurozone growth until 2026
- CM Shinde orders stern action against hoarding of onions amid rising prices
- Protest rallies in Manipur against 'mass killing of 10 village volunteers'
- Open Network for Digital Commerce: Tirupati corporation to promote SHG groups products online marketing
- 4th T20I: India elect to bat first in series decider vs South Africa
- The Telangana Woman Sushma Thodety Shines in the UMB Pageant's ‘Mrs. India’ Competition
- Suspect arrested after firing shots near Israeli consulate in Istanbul
New method enables smartwatches to record your every move
Scientists have invented a new algorithm that empowers smartwatches to detect and record your every move, without being told beforehand what to look for.
London : Scientists have invented a new algorithm that empowers smartwatches to detect and record your every move, without being told beforehand what to look for.
Current smartwatches can recognise a limited number of particular activities, including yoga and running, but these are programmed in advance.
This new method, scheduled to be presented at International Symposium on Wearable Computers to be held in Hawaii from September 11-15 enables the technology to discover activities as they happen, not just simply when exercising, but also when brushing your teeth or cutting vegetables.
The algorithm can even track sedentary activity, for instance whether you are sitting or lying down."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 University of Sussex in Britain.
"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.
"Traditional models ' cluster' together bursts of activity to estimate what a person has been doing, and for how long.
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.
