ProsNet
A software package for developing classification models that predict physical behaviour postures.
Explore the docs »
🤔 About The Project
This respository contains the sotware package and models described in the publication:
A Machine Learning Classification Model for Monitoring the Daily Physical Behaviour of Lower-Limb Amputees" (Griffiths et al., 2021).
The code works with data export from the activPAL activtiy monitor palt.com
Here are the main uses for this software:
- Estimate physical behaviour postures from shank accelerometer data
- Process shank accelerometer data along with thigh accelerometer event data to create a labeled dataset for training:
- Machine learning classifiers from heuristic features
- Deep learning classifiers from windowed acceleration data
- Re-create the model development process used in Griffiths et al. (2021)
- Experiment with new model development
- Estimate non-wear periods from accelerometer data
See the example scripts for each of these use cases.
Built With
🚀 Getting Started
Test out the package and start processing data.
💻 Prerequisites
You need these pre-installed on your device to get started.
- Python: A useful resource for installing python - instructions
- Pipenv: A package management tool that automatically creates and manages a virtualenv for your projects, as well as adds/removes packages from your Pipfile as you install/uninstall packages. It also generates the ever-important Pipfile.lock, which is used to produce deterministic builds. This package can be installed using:
pip install pipenv
Installation
- Open your terminal/shell and navigate to the directory where you want to install this software
- Clone the repo
git clone https://github.com/Ben-Jamin-Griff/ProsNet.git
- Move into repo
cd ProsNet
- Install Python packages
pipenv install
🗺️ Exploring The Package
Make sure you completed the installation steps and then run the following command:
- Unix/maxOS
python3 examples/shallow_examples/example_1.py
- Windows
py examples\shallow_examples\example_1.py
This shows some of the basic functionality of the package. Look through the other examples or dive into the src
folder to see what's happening under the hood.
🤝 Contributing
Contributions are what make the open source community such an amazing place. Any contributions you make are greatly appreciated.
- Fork the Project
- Create your Feature Branch (
git checkout -b feature/AmazingFeature
) - Commit your Changes (
git commit -m 'Add some AmazingFeature'
) - Push to the Branch (
git push origin feature/AmazingFeature
) - Open a Pull Request
License
Distributed under the MIT License. See LICENSE
for more information.
Author
👤 Benjamin Griffiths