iantangc/SelfHAR
Improving Human Activity Recognition through Self-training with Unlabeled Data
This project helps researchers and practitioners in human activity recognition (HAR) to more accurately classify human activities from mobile sensor data. It takes both a small amount of labeled sensor data and a large amount of unlabeled sensor data as input, and outputs a more robust activity recognition model. This is for anyone building or improving systems that automatically detect activities like walking, running, or sitting from device data.
No commits in the last 6 months.
Use this if you need to build a highly accurate human activity recognition model but have limited access to expensively labeled sensor data, alongside a wealth of readily available unlabeled sensor data.
Not ideal if you have ample labeled data for your specific activities and use case, or if you are not working with mobile sensor data for activity recognition.
Stars
42
Forks
15
Language
Python
License
GPL-3.0
Category
Last pushed
Jul 13, 2021
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/iantangc/SelfHAR"
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...