ycq091044/BIOT

BIOT - A framework for pretraining biosignals at scale. Large EEG pre-trained models.

47
/ 100
Emerging

This project helps medical researchers and neurologists analyze large collections of raw EEG data, even if it has different channel configurations, varying lengths, or missing values. It takes in raw EEG signals and outputs pre-trained models that can be fine-tuned for specific diagnostic tasks, or directly used for supervised or unsupervised learning. The end user is typically a medical researcher, neurologist, or data scientist working with biosignals.

182 stars. No commits in the last 6 months.

Use this if you need to process and build predictive models from extensive and diverse EEG datasets, especially those with inconsistencies or gaps, to identify patterns related to conditions like seizures or sleep disorders.

Not ideal if you are working with biosignal data other than EEG or if you need to build models from scratch without leveraging large pre-trained representations.

neurology EEG-analysis sleep-disorders seizure-detection biosignal-processing
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 21 / 25

How are scores calculated?

Stars

182

Forks

36

Language

Python

License

MIT

Last pushed

Dec 11, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/ycq091044/BIOT"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.