Skip to content

Latest commit

 

History

History
15 lines (8 loc) · 834 Bytes

README.md

File metadata and controls

15 lines (8 loc) · 834 Bytes
Raw

Denoising Autoencoders for Learning from Noisy Patient-Reported Data

This directory includes all code and simulated data used in the paper: Denoising Autoencoders for Learning from Noisy Patient-Reported Data.

CTDAE.py includes all code used to train models. The commands used for running all experiments are included in the comments at the beginning of the file.

gather_results.py includes all code used to generate results reported.

sim_data.zip includes all simulated data used, with notes about the data structure and how it was generated. It also includes files necessary to modify the simulator found on GitHub to generate our datasets.

We do not have rights to distribute the Ohio dataset, but it can be made available through a data use agreement with the owners: http://smarthealth.cs.ohio.edu/OhioT1DM-dataset.html