Wearable Sleep-Stage Classification: A Systematic Analysis of Signal Modalities, Representations, and Multimodal Fusion
Unaza Tallal, Rupesh Agrawal, Shruti Kshirsagar · 2026
Read Wearable Sleep-Stage Classification: A Systematic Analysis of Signal Modalities, Representations, and Multimodal Fusion by Unaza Tallal, Rupesh Agrawal, Shruti Kshirsagar (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-13611820.txt.
Description
Unaza Tallal, Rupesh Agrawal, and Shruti Kshirsagar sort out which signals and encodings make wearable sleep staging work best. Their 2026 study compares ways to turn wrist sensor data into sleep stages, a job normally done by a full lab setup that cannot scale to long home monitoring. Tests used two cohorts, one small and rich, one large.
Hand-made features lost to frequency-based encodings of the same signals. The pulse wave signal was the strongest single channel, above all for dream sleep. Mixing both encodings beat either alone, while fancier fusion added nothing. Fine stage splits stayed hard, with light and deep sleep the slipperiest. Bigger cohorts helped pulse-only staging. The authors say smart encoding beats stacking more sensors.
Catalog record
| CREATOR | Unaza Tallal, Rupesh Agrawal, Shruti Kshirsagar |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 60 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |