Frequency-aware transformer networks for robust and generalizable EEG-based seizure detection
Mostafa Gamal, Mustafa Abdel-Wanes · 2026
Read Frequency-aware transformer networks for robust and generalizable EEG-based seizure detection by Mostafa Gamal, Mustafa Abdel-Wanes (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-13554211.txt.
Description
Mostafa Gamal and Mustafa Abdel-Wanes build a neural network that spots epileptic seizures in brain wave recordings, in work from 2026. Automatic detection is hard because EEG signals are noisy, shifting, and vary widely between hospitals.
Their model, BrainXNet, mixes three parts. Multi-scale filters catch both brief spikes and long patterns. A frequency attention module stresses the wave bands that matter clinically. A transformer then reads long stretches of the signal in context. On two large benchmark datasets the system reached about 99 and 98 percent accuracy. It kept over 94 percent accuracy when moved between datasets, and stayed strong under noise.
Catalog record
| CREATOR | Mostafa Gamal, Mustafa Abdel-Wanes |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 61 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |