MMFNet: A multi-branch multi-scale framework with adaptive sparse self-attention and cross-modal fusion for sleep stage assessment
Yuan Li, Ningning Wang · 2026
Read MMFNet: A multi-branch multi-scale framework with adaptive sparse self-attention and cross-modal fusion for sleep stage assessment by Yuan Li, Ningning Wang (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/plos-pone-0353930.txt.
Description
Yuan Li and Ningning Wang present a neural network that sorts sleep into stages. It works from brain and eye signals. Their paper appeared in PLOS ONE in 2026. Sleep staging normally takes an expert hours of reading traces by hand. Their framework listens at several time scales at once. It pays close attention to the most telling moments. It ignores redundant stretches. It also blends brain-wave and eye-movement channels. Each channel is weighted moment by moment.
On two public sleep datasets the system did well. It classified stages with accuracy in the low-to-mid eighties. The authors also show which signal drove each decision. Clinicians need that kind of openness. Only then can they trust automated scoring in real sleep clinics.
Catalog record
| CREATOR | Yuan Li, Ningning Wang |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 52226 |
| LICENSE | CC_BY |
| RIGHTS | CC BY |
| SOURCE | PLOS |