StableSleep: Source-Free Test-Time Adaptation for Sleep Staging with Lightweight Safety Rails
Fuente:
arXiv
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908517218123776 |
|---|---|
| author | Arasu, Hritik Jahangiri, Faisal R |
| author_facet | Arasu, Hritik Jahangiri, Faisal R |
| contents | Sleep staging models often degrade when deployed on patients with unseen physiology or recording conditions. We propose a streaming, source-free test-time adaptation (TTA) recipe that combines entropy minimization (Tent) with Batch-Norm statistic refresh and two safety rails: an entropy gate to pause adaptation on uncertain windows and an EMA-based reset to reel back drift. On Sleep-EDF Expanded, using single-lead EEG (Fpz-Cz, 100 Hz, 30s epochs; R&K to AASM mapping), we show consistent gains over a frozen baseline at seconds-level latency and minimal memory, reporting per-stage metrics and Cohen's k. The method is model-agnostic, requires no source data or patient calibration, and is practical for on-device or bedside use. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_02982 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | StableSleep: Source-Free Test-Time Adaptation for Sleep Staging with Lightweight Safety Rails Arasu, Hritik Jahangiri, Faisal R Machine Learning Artificial Intelligence Neural and Evolutionary Computing Neurons and Cognition Sleep staging models often degrade when deployed on patients with unseen physiology or recording conditions. We propose a streaming, source-free test-time adaptation (TTA) recipe that combines entropy minimization (Tent) with Batch-Norm statistic refresh and two safety rails: an entropy gate to pause adaptation on uncertain windows and an EMA-based reset to reel back drift. On Sleep-EDF Expanded, using single-lead EEG (Fpz-Cz, 100 Hz, 30s epochs; R&K to AASM mapping), we show consistent gains over a frozen baseline at seconds-level latency and minimal memory, reporting per-stage metrics and Cohen's k. The method is model-agnostic, requires no source data or patient calibration, and is practical for on-device or bedside use. |
| title | StableSleep: Source-Free Test-Time Adaptation for Sleep Staging with Lightweight Safety Rails |
| topic | Machine Learning Artificial Intelligence Neural and Evolutionary Computing Neurons and Cognition |
| url | https://arxiv.org/abs/2509.02982 |