ActiNet: an open-source tool for activity intensity classification of wrist-worn accelerometry using self-supervised deep learning
Researchers have developed ActiNet, an open-source deep learning tool designed to classify physical activity intensity from wrist-worn accelerometer data. The model outperformed existing methods in accuracy, providing a more reliable tool for large-scale epidemiological health studies.
Why it matters
Improved activity recognition models are essential for accurately tracking the relationship between physical movement and long-term health outcomes in public health research.
Scientific Reports ( 2026 ) Cite this article
We’re sharing this article early to provide faster access to peer-reviewed, accepted research. It is citable and carries a permanent DOI. This version is subject to further edits and will be replaced automatically by the final Version of Record. All legal disclaimers apply.
Get smarter about the news
Sign up free for a feed built around what you actually care about, Dive Deeper research on any story, and the full text of every article.
Create free accountAlready have an account? Sign in