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.”
The Latest on: Activity-recognition systems
- Valencell Benchmark Wrist 1.2 (BW 1.2)on June 21, 2020 at 5:01 pm
Valencell's Benchmark™ Wrist Sensor System is the next-generation biometric wearable sensor technology that helps you quickly develop your own biometric products. The modular design brings together ...
- Oppo showcases potential future Camera technology at CVPR 2020on June 18, 2020 at 1:15 am
The technology that got Oppo the awards includes perceptual extreme super-resolution technology, visual localization, and human activity recognition in videos. Oppo’s Research team was tasked to ...
- Gesture recognition using a bioinspired learning architecture that integrates visual data with somatosensory data from stretchable sensorson June 8, 2020 at 8:07 am
Gesture recognition using machine-learning methods is valuable in the development of advanced cybernetics, robotics and healthcare systems, and typically relies on images or videos. To improve ...
- Venu Govindarajuon June 4, 2020 at 5:00 pm
Venu Govindaraju, SUNY Distinguished Professor of Computer Science ... His seminal work in handwriting recognition was at the core of the first handwritten address interpretation system used by the US ...
- June 2014 Snapshots: Critter cams, IR imaging for F1 racing, document scanning, web inspection, activity recognition algorithmon June 3, 2020 at 5:00 pm
FLIR Systems to provide IR technologies to racing team FLIR ... www.uci.edu) have developed an activity recognition algorithm that uses techniques from natural language processing to enable computers ...
- Implication of JAK1/STAT3/SOCS3 Pathway in Aging of Cerebellum of Male Rat: Histological and Molecular studyon June 1, 2020 at 2:32 am
The cerebellum is a fundamental part of the brain that is responsible for movement and awareness activities, such as training of motor activity, recognition of time and fine movements 1.
- Army research advances state-of-the-art cybersecurity methodson May 28, 2020 at 10:16 am
They can enable cybersecurity applications for threat detection and prevention and enhanced situational awareness, and can also accurately be used for human activity recognition and motion ...
- Jump-start your next IoT design with the SensorTile, our tiny Bluetooth multi-sensor development module - Webinaron May 27, 2020 at 5:00 pm
AutoDevKit: A New Way to a Proof-of-Concept for Automotive Applications in Minutes ...
- Sentri360 by Everguard.ai Unveils New Platform for Worker Safety and Monitoring as Industries Reopen Amidst COVID-19 Pandemicon May 27, 2020 at 5:00 pm
This full understanding allows the system to intervene intelligently, ensuring workers adhere to new guidelines while also preventing industrial accidents in real time." With a feature suite ...
- Dr Feng Chenon May 13, 2020 at 12:31 pm
Human Activity Recognition (HAR) is the backbone of AAL systems in order to detect Activities of Daily Living (ADL) and provide timely, context-aware assistance. Existing SH based AAL systems ...
via Google News and Bing News