mariusbock/dl-for-har
Improving Deep Learning for HAR with shallow LSTMs (best paper award), Bock et al., presented at ISWC 2021 (online)
This project helps researchers and engineers who develop systems that automatically detect human activities using sensor data from wearables. It provides a refined deep learning architecture that processes raw sensor data and outputs identified human activities, offering improved accuracy and faster training times compared to previous methods. The primary users are researchers or practitioners in human activity recognition.
No commits in the last 6 months.
Use this if you are building or evaluating human activity recognition models based on sensor data and want to achieve higher performance with reduced training time and computational resources.
Not ideal if you are working with non-sequential data, require a black-box solution without understanding the underlying architecture, or are not focused on sensor-based human activity recognition.
Stars
62
Forks
33
Language
Jupyter Notebook
License
MIT
Category
Last pushed
Mar 21, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/mariusbock/dl-for-har"
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...