guillaume-chevalier/LSTM-Human-Activity-Recognition
LSTM-based deep learning model that classifies six human activity types (walking, sitting, standing, etc.) from smartphone sensor data.
Not currently ranked — collecting fresh signals.
star history
This repository demonstrates using a Long Short-Term Memory (LSTM) Recurrent Neural Network to recognize human activities from smartphone sensor signals. The model takes raw accelerometer and gyroscope data as input and classifies movements into six categories without requiring manual feature engineering, unlike traditional signal processing approaches. The project uses TensorFlow as the deep learning framework and is implemented in Jupyter Notebooks.
Frequently asked
- What is guillaume-chevalier/LSTM-Human-Activity-Recognition?
- LSTM-based deep learning model that classifies six human activity types (walking, sitting, standing, etc.) from smartphone sensor data.
- Is LSTM-Human-Activity-Recognition open source?
- Yes — guillaume-chevalier/LSTM-Human-Activity-Recognition is open source, released under the MIT license.
- What language is LSTM-Human-Activity-Recognition written in?
- guillaume-chevalier/LSTM-Human-Activity-Recognition is primarily written in Jupyter Notebook.
- How popular is LSTM-Human-Activity-Recognition?
- guillaume-chevalier/LSTM-Human-Activity-Recognition has 3.5k stars on GitHub.
- Where can I find LSTM-Human-Activity-Recognition?
- guillaume-chevalier/LSTM-Human-Activity-Recognition is on GitHub at https://github.com/guillaume-chevalier/LSTM-Human-Activity-Recognition.