Outlier Handling Strategy of Ensembled-Based Sequential Convolutional Neural Networks for Sleep Stage Classification
Wei Zhou, Hangyu Zhu, Wei Chen, Chen Chen, Jun Xu, Richard Bayford, Pietro Aricò · 2024
Read Outlier Handling Strategy of Ensembled-Based Sequential Convolutional Neural Networks for Sleep Stage Classification by Wei Zhou, Hangyu Zhu, Wei Chen, Chen Chen, Jun Xu, Richard Bayford, Pietro Aricò (2024) 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-11673830.txt.
Description
Wei Zhou and co-authors propose, in 2024, a sleep staging system designed to handle people whose data look like outliers. Automatic staging usually works well on average but fails for small groups or unusual individuals, and those cases can bias training. Their design pairs a clustering step with a sequence of convolutional networks.
People are grouped by how their features are distributed, and each group gets tailored weights. Those weights combine with the networks' feature extraction to produce the staging. On two public datasets the system scored about eighty-five percent accuracy overall. The authors say easing the outlier problem matters most for monitoring individual sleep quality.
Catalog record
| CREATOR | Wei Zhou, Hangyu Zhu, Wei Chen, Chen Chen, Jun Xu, Richard Bayford, Pietro Aricò |
|---|---|
| YEAR | 2024 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 41 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |