OxWearables/actinet

An activity classification model based on self-supervised learning for wrist-worn accelerometer data.

54
/ 100
Established

This tool helps researchers and health professionals analyze data from wrist-worn accelerometers to understand activity patterns. You input raw accelerometer data files (e.g., from AX3, ActiGraph, or GENEActiv devices), and it provides detailed time-series data and summary metrics, revealing how much time a person spends sleeping, being sedentary, or engaging in physical activity. This is ideal for public health researchers, sports scientists, or clinicians studying human movement.

Available on PyPI.

Use this if you need to transform raw accelerometer data from wearable devices into meaningful insights about sleep, sedentary behavior, and physical activity.

Not ideal if you need real-time activity monitoring or custom machine learning model development for very specific, niche activities not covered by general classifications.

wearable-data-analysis public-health-research activity-monitoring sleep-analysis human-behavior-studies
Maintenance 10 / 25
Adoption 5 / 25
Maturity 25 / 25
Community 14 / 25

How are scores calculated?

Stars

12

Forks

3

Language

Python

License

Last pushed

Mar 09, 2026

Commits (30d)

0

Dependencies

12

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/OxWearables/actinet"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.