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.
☆18Updated 3 months ago
Alternatives and similar repositories for bg_control:
Users that are interested in bg_control are comparing it to the libraries listed below
- Predicting the probability of nocturnal hypoglycemic events with probabilistic forecasting.☆10Updated this week
- List of CGM datasets☆180Updated 3 months ago
- A Type-1 Diabetes simulator implemented in Python for Reinforcement Learning purpose☆263Updated 4 months ago
- Blood glucose prediction using long short-term memory recurrent neural networks.☆62Updated 3 months ago
- Patient-specific blood glucose prediction using deep learning, considering the challenges of "small dataset" and "data imbalance"☆47Updated 5 months ago
- Source code for predicting Blood Glucose Concentration☆44Updated last year
- Causal discovery for time series☆96Updated 3 years ago
- GluPredKit aims to make blood glucose model training and prediction more accessible.☆18Updated last week
- Temporal Causal Discovery Framework (PyTorch): discovering causal relationships between time series☆496Updated 3 years ago
- CausalFlow: a Collection of Methods for Causal Discovery from Time-series☆26Updated 3 weeks ago
- Granger causality discovery for neural networks.☆211Updated 4 years ago
- Augmenting Time Series Datasets with Weighted Elastic Barycenter Averaging