dspanah/Human-Activity-Recognition-Keras-Android

Sensor-based human activity recognition from smartphone data in Keras with on-device inference

33
/ 100
Emerging

This project offers an Android application that uses smartphone sensor data to automatically identify common daily activities like biking, jogging, sitting, or walking. It takes raw movement data from your phone's sensors and classifies it into one of seven everyday activities. People interested in health tracking, fitness monitoring, or behavioral research could use this to automatically log physical activity.

No commits in the last 6 months.

Use this if you need to classify common human activities (biking, jogging, sitting, standing, walking, upstairs, downstairs) directly on an Android device using its built-in sensors.

Not ideal if you need to recognize a wider range of custom activities or require a solution for non-Android devices.

activity-tracking fitness-monitoring behavioral-science mobile-health sensor-data-analysis
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 7 / 25
Maturity 8 / 25
Community 18 / 25

How are scores calculated?

Stars

40

Forks

13

Language

Java

License

Last pushed

May 16, 2019

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/dspanah/Human-Activity-Recognition-Keras-Android"

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