https://github.com/nkluge-correa/skateboarding-trick-classifier

This repository contains accelerometry signals from a skateboard mounted with an accelerometer/recorder. The accelerometer was used to record several skateboarding maneuvers from 5 different classes.
https://github.com/nkluge-correa/skateboarding-trick-classifier

machine-learning skateboarding sports

Last synced: 3 months ago
JSON representation

This repository contains accelerometry signals from a skateboard mounted with an accelerometer/recorder. The accelerometer was used to record several skateboarding maneuvers from 5 different classes.

• Host: GitHub
• URL: https://github.com/nkluge-correa/skateboarding-trick-classifier
• Owner: Nkluge-correa
• License: apache-2.0
• Created: 2021-10-28T00:51:35.000Z (over 3 years ago)
• Default Branch: master
• Last Pushed: 2024-01-30T01:10:12.000Z (over 1 year ago)
• Last Synced: 2025-01-24T23:29:32.998Z (5 months ago)
• Topics: machine-learning, skateboarding, sports
• Language: Jupyter Notebook
• Homepage: https://www.scielo.br/j/reng/a/sgsxHt4HffBYxDhqj9QD3dS/abstract/?lang=en
• Size: 19.3 MB
• Stars: 2
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

        


# Development of a skateboarding trick classifier using accelerometry and machine learning

[Paper](https://www.scielo.br/j/reng/a/sgsxHt4HffBYxDhqj9QD3dS/abstract/?lang=en) | [Data](https://github.com/Nkluge-correa/skateboarding-trick-classifier/tree/master/data) | [Models](https://github.com/Nkluge-correa/skateboarding-trick-classifier/tree/master/skateboarding_models)

[![DOI](https://zenodo.org/badge/422018559.svg)](https://zenodo.org/doi/10.5281/zenodo.6989815)





This repository contains _accelerometry signals_ from a skateboard mounted with an accelerometer/recorder. The accelerometer was used to record several skateboarding maneuvers from 5 different classes. To solve the classification task we trained a neural network with our dataset. We trained both a flat-dense and a recurrent network (LSTM). Ensemble models for the 'flat-dense' and 'rnn' architectures were also trained. The dataset can be found in the `data` folder and models in the `skateboarding_models` folder. You can also follow the procedure with our `Skateboarding_Trick_Classifier` notebook.

## Cite as 🤗

---

```latex

@article{correa2017development,

  title={Development of a skateboarding trick classifier using accelerometry and machine learning},

  author={Corr{\^e}a, Nicholas Kluge and Lima, J{\'u}lio C{\'e}sar Marques de and Russomano, Thais and Santos, Marlise Araujo dos},

  journal={Research on Biomedical Engineering},

  volume={33},

  pages={362--369},

  year={2017},

  publisher={SciELO Brasil}

}

```

## License

Contents of this repository are licensed under the Apache License, Version 2.0. See the [LICENSE](LICENSE) file for more details.