markub3327/HAR-Transformer
Transformer for Human Activity Recognition
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.
Stars
77
Forks
17
Language
Jupyter Notebook
License
MIT
Category
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.
Higher-rated alternatives
OxWearables/stepcount
Improved Step Counting via Foundation Models for Wrist-Worn Accelerometers
OxWearables/actinet
An activity classification model based on self-supervised learning for wrist-worn accelerometer data.
aqibsaeed/Human-Activity-Recognition-using-CNN
Convolutional Neural Network for Human Activity Recognition in Tensorflow
felixchenfy/Realtime-Action-Recognition
Apply ML to the skeletons from OpenPose; 9 actions; multiple people. (WARNING: I'm sorry that...
guillaume-chevalier/LSTM-Human-Activity-Recognition
Human Activity Recognition example using TensorFlow on smartphone sensors dataset and an LSTM...