rfonod/deepsleep2
😴 DeepSleep2 is a compact U-Net-inspired convolutional neural network with 740,551 parameters, designed to predict non-apnea sleep arousals from full-length multi-channel polysomnographic recordings at 5-millisecond resolution. Achieves similar performance to DeepSleep with lower computational cost.
This tool helps sleep researchers and clinicians automatically identify non-apnea sleep arousals from full-length polysomnographic recordings. It takes multi-channel physiological signals as input and outputs precise predictions of sleep arousal events at a 5-millisecond resolution. This is designed for professionals studying sleep patterns and disorders.
No commits in the last 6 months.
Use this if you need to efficiently and accurately segment non-apnea sleep arousals from large volumes of polysomnography data, similar to the PhysioNet dataset.
Not ideal if your primary focus is on detecting sleep apnea or if you require real-time processing on embedded devices with very limited computational resources.
Stars
22
Forks
4
Language
Jupyter Notebook
License
MIT
Category
Last pushed
Aug 30, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/rfonod/deepsleep2"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Compare
Higher-rated alternatives
OxWearables/asleep
asleep: a sleep classifier for wearable sensor data using machine learning
akaraspt/deepsleepnet
DeepSleepNet: a Model for Automatic Sleep Stage Scoring based on Raw Single-Channel EEG
benmfox/PFTSleep
A foundational transformer leveraging full night, multichannel sleep study data accurately...
biomedical-signal-processing/sleepyland
A toolbox for sleep data analysis and sleep stage classification
raphaelvallat/yasa_classifier
Notebooks for training the classifier of YASA sleep staging