markub3327/HAR-Transformer

Transformer for Human Activity Recognition

44
/ 100
Emerging

This project helps you accurately identify continuous human activities from wearable sensor data, even when multiple activities occur sequentially within a single timeframe. It takes raw time-series sensor readings (like accelerometry or gyroscope data) and outputs the specific activity being performed at each moment. This is useful for researchers in fields like sports science, elder care, or fitness tracking who need detailed activity breakdowns.

No commits in the last 6 months.

Use this if you need to precisely recognize a sequence of human activities from wearable sensor data.

Not ideal if your activity recognition needs are simple and you only need to classify a single activity for an entire data segment.

wearable-tech activity-tracking sensor-data-analysis human-behavior sports-science
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 9 / 25
Maturity 16 / 25
Community 19 / 25

How are scores calculated?

Stars

77

Forks

17

Language

Jupyter Notebook

License

MIT

Last pushed

Jan 18, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/markub3327/HAR-Transformer"

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