This repository was made for the course EL7006 Neural Networks and Information Theory for Learning, Universidad de Chile, with educational purposes.
This is a toy example of sleep stage scoring with simple features and a Random Forest classifier, using sleep data from the MASS Database [1] (not included in this repository). Scripts for visualization and classification can be found inside the 'scripts' directory. It is meant to be a working example for the input pipeline of the classification task needed for course projects.
Access to the database should be properly requested following the instructions at http://ceams-carsm.ca/en/mass
Requirements:
- Numpy
- Matplotlib
- Scikit-learn
- Scipy
- Pyedflib
[1] O’Reilly, C., Gosselin, N., Carrier, J. & Nielsen, T. (2014) Montreal Archive of Sleep Studies: An open-access resource for instrument benchmarking & exploratory research. Journal of Seep Research, 628-635. doi: 10.1111/jsr.12169 .