Compact neural network algorithm for electrocardiogram classification
Christian M. Frausto-Avila, Juan P. Manriquez-Amavizca, Ana K. S. Rocha-Robledo, Mario A. Quiroz-Juarez, Alfred B. U’Ren · 2026
Read Compact neural network algorithm for electrocardiogram classification by Christian M. Frausto-Avila, Juan P. Manriquez-Amavizca, Ana K. S. Rocha-Robledo, Mario A. Quiroz-Juarez, Alfred B. U’Ren (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/PMC13638727.txt.
Description
Christian M. Frausto-Avila and four colleagues describe a 2026 method for sorting heart rhythm recordings with a small neural network instead of deep learning. Deep learning systems can read electrocardiograms well but need heavy computing power and large labeled datasets.
Their network uses seventeen features drawn from each heartbeat signal by math and signal-processing steps. It sorted five rhythm types, including normal rhythm and atrial fibrillation, with accuracy near ninety-six percent on two public databases. Because the model is compact and runs fast on a normal processor, the authors suggest it could suit low-cost devices.
Catalog record
| CREATOR | Christian M. Frausto-Avila, Juan P. Manriquez-Amavizca, Ana K. S. Rocha-Robledo, Mario A. Quiroz-Juarez, Alfred B. U’Ren |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 51397 |
| LICENSE | https://creativecommons.org/licenses/by/4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |