HESREN: A Derivative-Informed Reservoir Framework for Detecting Transient Neural Events and Windowless Estimation of Dynamic Functional Connectivity
Ugur Kadak · 2026
Read HESREN: A Derivative-Informed Reservoir Framework for Detecting Transient Neural Events and Windowless Estimation of Dynamic Functional Connectivity by Ugur Kadak (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/PMC13253793.txt.
Description
Ugur Kadak introduces HESREN, a new brain scan analysis tool, in a 2026 paper. Standard ways to track changing brain connections use sliding time windows, which trade time detail against reliability. Rare brief brain events can also get lost. HESREN instead uses a reservoir network fed with signal values plus their rates of change.
Tested on the NEBULA101 resting-state scan data set, HESREN found brief events far better than raw-derivative baselines and other common tools. It caught events about nine seconds sooner than sliding-window methods on average. Its window-free connection tracks also gave finer time detail while matching teacher estimates.
Catalog record
| CREATOR | Ugur Kadak |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 150311 |
| LICENSE | https://creativecommons.org/licenses/by/4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |