Research on hemodynamic state prediction based on feature-enhanced multi-model ensemble
Shuai Yan, Minghua Liu, Xiaoyan Wang · 2026
Read Research on hemodynamic state prediction based on feature-enhanced multi-model ensemble by Shuai Yan, Minghua Liu, Xiaoyan 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/pmc-13251204.txt.
Description
Shuai Yan, Minghua Liu, and Xiaoyan Wang present a 2026 method for reading hidden brain signals out of standard fMRI scans. The scanner measures blood oxygen changes, which lag and blur the neural activity researchers really want. Their framework works backward from the blood signal to estimate both the neural drive and the vessel response behind it.
The method first extracts features from the blood signal at several time scales. It then feeds those features into a stack of different learning models whose outputs are merged by a final meta-model. On synthetic data from a standard vessel model, the system recovered the vessel signal with an R-squared of 0.92 and the neural signal at 0.78 on the same scale. Tests on real scans rebuilt blood signals that closely matched the recorded ones. The authors offer the approach for finer analysis of brain activity.
Catalog record
| CREATOR | Shuai Yan, Minghua Liu, Xiaoyan Wang |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 52 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |