mims-harvard/Raindrop
Graph Neural Networks for Irregular Time Series
This tool helps healthcare professionals and researchers analyze health data, especially from ICU patients, or sensor data from human activity monitoring. It takes in irregularly recorded patient sensor data or activity monitor readings and outputs classifications, such as predicting sepsis, mortality, or specific physical activities. Medical and human activity researchers who work with time-series sensor data would find this useful.
219 stars. No commits in the last 6 months.
Use this if you need to classify patient conditions (like sepsis risk or mortality) or physical activities based on sensor data that is collected at inconsistent times or has missing sensor readings.
Not ideal if your data is perfectly regularly sampled or if you are not dealing with a classification task on multivariate time series.
Stars
219
Forks
47
Language
Python
License
MIT
Category
Last pushed
Oct 04, 2022
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/embeddings/mims-harvard/Raindrop"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
eliorc/node2vec
Implementation of the node2vec algorithm.
mims-harvard/decagon
Graph convolutional neural network for multirelational link prediction
mims-harvard/nimfa
Nimfa: Nonnegative matrix factorization in Python
ferencberes/online-node2vec
Node Embeddings in Dynamic Graphs
claws-lab/jodie
A PyTorch implementation of ACM SIGKDD 2019 paper "Predicting Dynamic Embedding Trajectory in...