search

RobotPsychologist / bg_control

Improving short-term prandial blood glucose outcomes for people with type 1 diabetes, a complex disease that affects nearly 10 million people worldwide. We aim to leverage semi-supervised learning to identify unlabelled meals in time-series blood glucose data, develop meal-scoring functions, and explore causal machine-learning techniques.
http://bloodglucosecontrol.com/
18 stars 41 forks source link

Data Generation of Simulated Simglucose Data #154

Open RobotPsychologist opened 5 hours ago

RobotPsychologist commented 5 hours ago

We will also be running experiments on the simglucose simulated data. We'll need to understand how closely we can structure this data to resemble real world data. It would be good to have more data to work with when we get this working.

https://github.com/jxx123/

The results of our implementation would be calling a function with our specifications that can essentially create all of the csvs in this directory:

https://github.com/jxx123/simglucose/tree/master/examples/results/2017-12-31_17-46-32

RobotPsychologist commented 4 hours ago

@Tony911029 let me know if you're interested in picking this up. I'll keep adding more details.

Tony911029 commented 3 hours ago

I will take a look!