https://github.com/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.
https://github.com/rfonod/deepsleep2
cnn computational-efficiency convolutional-networks deep-learning encoder-decoder machine-learning medical-ai multichannel neural-networks physionet polysomnography pytorch segmentation sleep-analysis sleep-apnea sleep-arousals time-series u-net
Last synced: 6 months ago
JSON representation
😴 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.
- Host: GitHub
- URL: https://github.com/rfonod/deepsleep2
- Owner: rfonod
- License: mit
- Created: 2022-01-21T17:51:09.000Z (about 4 years ago)
- Default Branch: main
- Last Pushed: 2025-08-30T20:34:48.000Z (6 months ago)
- Last Synced: 2025-08-30T22:18:29.423Z (6 months ago)
- Topics: cnn, computational-efficiency, convolutional-networks, deep-learning, encoder-decoder, machine-learning, medical-ai, multichannel, neural-networks, physionet, polysomnography, pytorch, segmentation, sleep-analysis, sleep-apnea, sleep-arousals, time-series, u-net
- Language: Jupyter Notebook
- Homepage: https://doi.org/10.3390/ai3010010
- Size: 791 MB
- Stars: 17
- Watchers: 1
- Forks: 4
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
- Citation: CITATION.cff