Scientists at the University of Sussex have invented a new algorithm that enables 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 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 lying or sitting down.
Dr Hristijan Gjoreski of the University of Sussex said: “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.
“Here we present a new machine-learning approach that detects new human activities as they happen in real time, and which outperforms competing approaches.”
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.
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.
Dr Daniel Roggen, head of the Sensor Research Technology Group at the University of Sussex, will speak at the British Science Festival on 6 September in the event ‘In the era of wearable technologies’.
He added: “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.
“As well as for fitness and lifestyle trackers, this can be used in healthcare scenarios and in fields such as consumer behaviour research.”
Learn more: Algorithm unlocks smartwatches that learn your every move
The Latest on: Activity-recognition systems
[google_news title=”” keyword=”activity-recognition systems” num_posts=”10″ blurb_length=”0″ show_thumb=”left”]
- Global Sustainability Summit Concludes With Recognition Of Top Research And Startups In Sustainability - Middle East Business News And Informationon April 26, 2024 at 4:25 pm
Impactful academic research papers identifying net zero solutions recognized at special award ceremony. Award winners received s ...
- Locking up carbon for good: Easthampton inventor’s CO2 removal system turns biomass into biocharon April 26, 2024 at 1:07 pm
Like many people, Michael Garjian believes global warming is a pressing issue of our times.Unlike most, he’s putting his ideas for reducing carbon dioxide in the atmosphere into practice — and at the ...
- Understanding BeArt in One Article | Focused RWA Asset Issuance Platform, Galxe Prize Activity Launchedon April 26, 2024 at 5:25 am
As the crypto art craze sparked by NFTs gained acceptance, public recognition of it as an art form persists to this day, providing new directions for various derivative economies, including the ...
- Border agency eyes smartphone facial recognition system amid privacy concernson April 24, 2024 at 1:57 pm
The Canada Border Services Agency says the initiative would allow for a faster and more seamless travel experience.
- UNCW first in UNC System to win national nursing recognitionon April 24, 2024 at 12:42 pm
UNCW's online Master of Science in Nursing – Nurse Educator (MSN NE) program has become the first nursing program in the 17-school UNC System to receive national recognition with ...
- Secret army of women who broke Nazi codes get belated recognition for WWII workon April 23, 2024 at 1:56 pm
At least 77 students from the women-only college at Cambridge University were recruited to the code breaking station during World War II.
- Students honored at annual recognition ceremonyon April 23, 2024 at 2:00 am
The Honors Program of Wayne Community College focuses on academics, leadership, and service as integral components of a well-rounded education. Students must have a 3.5 GPA to be admitted to the ...
- Meta opens Quest operating system to third-party device makerson April 22, 2024 at 4:29 pm
Meta Platforms is sharing its Quest headset's operating system with rival device makers, including Microsoft , for the first time, it said on Monday, as it works to extend its influence over the ...
- The AI-Linked Systems in Threat Detection and Preventionon April 22, 2024 at 5:04 am
AI systems are super-powered guards that learn and watch for unusual activity in real-time, stopping attacks before they happen. By constantly learning, AI keeps us safe online, preventing cybercrime ...
- How facial recognition technology is reassuring worshippers in places of worshipon April 19, 2024 at 5:22 am
In a world where worship places serve as the beating heart of communities, their significance cannot be overstated. Regardless of the religion, sacred spaces are the basics of spiritual worship ...
via Google News and Bing News