https://github.com/ciwooooo/handwriting-classification
A time series classification challange. The point is to classifiy whether a child's handwriting is affected by dysgraphia. the features represent the movements of a pen on a tablet the child wrote on.
https://github.com/ciwooooo/handwriting-classification
classification handwriting knn-classification machine-learning rocket time-series
Last synced: 4 months ago
JSON representation
A time series classification challange. The point is to classifiy whether a child's handwriting is affected by dysgraphia. the features represent the movements of a pen on a tablet the child wrote on.
- Host: GitHub
- URL: https://github.com/ciwooooo/handwriting-classification
- Owner: Ciwooooo
- Created: 2024-05-24T14:25:45.000Z (about 2 years ago)
- Default Branch: main
- Last Pushed: 2024-05-28T15:58:37.000Z (about 2 years ago)
- Last Synced: 2025-04-06T06:44:31.680Z (about 1 year ago)
- Topics: classification, handwriting, knn-classification, machine-learning, rocket, time-series
- Language: Jupyter Notebook
- Homepage:
- Size: 1.07 MB
- Stars: 0
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# Handwriting Classification Challange
This is a small time-series challenge I did during my master's. All credit for the challange idea goes to **Dr. Sharon Ong**, Department of Cognitive Science and Artificial Inteligence, Tilburg University.
**Update:** My implementation of Rocket managed to win 2nd place in the competition :)
The objective of this challange is to classify whether a child's handwriting is affected by dysgraphia. The data comes from the study by *Drotár and Dobeš, 2020* and is avaliable [here](https://github.com/peet292929/Dysgraphia-detection-through-machine-learning). It was collected using a using a WACOM Intuos Pro Large tablet.
The features are numeric and represent the below over time:
* pen movement in the x-direction,
* pen movement in the y-direction
* whether the pen was on the surface (1) or in the air (0)
* the pressure of the pen on the tablet surface
* the azimuth of the pen on the tablet surface
**References**
Drotár, P., Dobeš, M. Dysgraphia detection through machine learning. Sci Rep 10, 21541 (2020). https://doi.org/10.1038/s41598-020-78611-9