OSCR

Frequency-aware transformer networks for robust and generalizable EEG-based seizure detection.

Overview

Authors: Mostafa Gamal1,2, Mustafa Abdel-Wanes3
  1. Department of Artificial Intelligence, Faculty of Computers and Artificial Intelligence, Benha University, Benha, 13518 Egypt
  2. Artificial Intelligence Department, Faculty of Artificial Intelligence, Egyptian Russian University Badr City, Cairo, 11829 Egypt
  3. Department of Neurosurgery, Faculty of Medicine, Benha University, Benha, 13518 Egypt
Institutions: Benha University (Egypt); Egyptian Russian University (Egypt)
Journal: Scientific reports, volume 16, issue 1, article 28076
Dates: received 5 May 2026; accepted 21 August 2026; published online 8 September 2026
Type: Research article · Language: English
License: CC BY
Identifiers: DOI 10.1038/s41598-026-68506-6 · PMID 42711447 · PMCID PMC13554211 · OpenAlex W7211974892
Open access: gold, a free copy (OpenAlex)
Categories: EEG (modality), human (organism), epilepsy (population), methods / tools (subfield)
Methods: Spectral & time-frequency, Smoothing, state filtering, decompositions, Preprocessing, Statistics, Machine learning, Physiology & signal measures
Keywords: Electroencephalography (EEG), Epileptic seizure detection, Deep learning, Spectro-temporal attention, Transformers, Computational biology and bioinformatics, Engineering, Mathematics and computing, Neuroscience
MeSH: Electroencephalography*, Seizures*, Algorithms, Convolutional Neural Networks, Deep Learning, Epilepsy, Humans, Signal Processing, Computer-Assisted (* major topic)
Topic: EEG and Brain-Computer Interfaces (Cognitive Neuroscience, Neuroscience), according to OpenAlex
Citations: not cited yet (Europe PMC); 55 references in the paper

Abstract

Automated epileptic seizure detection from electroencephalogram (EEG) signals remains a critical challenge for real-world clinical deployment due to the complex, nonstationary, and multi-scale nature of neural dynamics. Existing deep learning approaches, including convolutional and transformer-based models, often fail to jointly capture spectral–temporal dependencies while maintaining robustness across heterogeneous datasets and noisy clinical environments. In this work, we propose BrainXNet, a novel multi-scale spectro-temporal attention framework that unifies local feature extraction, frequency-aware representation learning, and global temporal modeling within a single architecture. The proposed model integrates (i) multi-scale convolutional pathways to capture transient and long-duration EEG patterns, (ii) a spectral attention module that dynamically emphasizes clinically relevant frequency bands, and (iii) a temporal transformer encoder for modeling long-range dependencies across EEG sequences. Extensive evaluations on two large-scale benchmark datasets, CHB-MIT and TUH Seizure Corpus, demonstrate that BrainXNet achieves state-of-the-art performance, reaching accuracies of 99.1% and 98.4%, respectively. Beyond in-dataset performance, the proposed framework exhibits strong cross-dataset generalization, maintaining over 94% accuracy in transfer settings, and demonstrates high robustness under noisy conditions. Ablation studies further confirm the complementary contributions of each architectural component. These results highlight the effectiveness of explicitly modeling multi-scale spectro-temporal dynamics for EEG analysis and position BrainXNet as a promising candidate for reliable, real-time clinical seizure detection systems. This work bridges the gap between high-performance experimental models and practical deployment in diverse healthcare environments.

Reproduced under the paper's license (CC BY), from the paper cited above.

Code

The paper links to its data and to no code of its authors: see the Data section.

Tracing map

A tracing map links a paper to the code its authors published: this paper has none, so it has no map.

Data

Datasets cited

Data availability

The datasets analyzed during the current study are publicly available benchmark EEG datasets.The CHB-MIT Scalp EEG Database is publicly available through PhysioNet at: https://physionet.org/content/chbmit/1.0.0/The Temple University Hospital EEG Seizure Corpus (TUSZ) is publicly available through the official TUH EEG Corpus repository at: https://isip.piconepress.com/projects/nedc/html/tuh_eeg/index.shtml#c_tuszAccess to the TUH EEG Corpus requires registration and completion of a data use agreement through the repository website.No new datasets were generated during the current study.

Reproduced under the paper's license (CC BY), from the paper cited above.

Versions

The history of this record: each version stored by the harvester or made by a correction of its authors or of the maintainers of its code, and what changed in its facts. The texts of the paper (its abstract, its availability statements) are not part of it; versions that changed only those are not listed.

Version 3, 28 September 2026

  • Funding: added Science and Technology Development Fund

Version 1, 27 September 2026: the first record

Recorded: type, language, journal, volume, issue, pages, dates, 2 authors, 9 keywords, 8 MeSH terms, 22 references.

Cite

This paper

Gamal, M., & Abdel-Wanes, M. (2026). Frequency-aware transformer networks for robust and generalizable EEG-based seizure detection. Scientific reports, 16(1), 28076. https://doi.org/10.1038/s41598-026-68506-6

BibTeX

@article{gamal2026frequency,
author = {Gamal, Mostafa and Abdel-Wanes, Mustafa},
title = {{Frequency-aware transformer networks for robust and generalizable EEG-based seizure detection}},
journal = {Scientific reports},
year = {2026},
month = sep,
volume = {16},
number = {1},
pages = {28076},
publisher = {Nature Publishing Group},
issn = {2045-2322},
doi = {10.1038/s41598-026-68506-6},
url = {https://doi.org/10.1038/s41598-026-68506-6},
pmid = {42711447},
pmcid = {PMC13554211}
}

RIS

TY - JOUR
AU - Gamal, Mostafa
AU - Abdel-Wanes, Mustafa
TI - Frequency-aware transformer networks for robust and generalizable EEG-based seizure detection
T2 - Scientific reports
J2 - Sci Rep
PY - 2026
DA - 2026/09/08
VL - 16
IS - 1
SP - 28076
SN - 2045-2322
PB - Nature Publishing Group
DO - 10.1038/s41598-026-68506-6
UR - https://doi.org/10.1038/s41598-026-68506-6
LA - en
ER -

CSL-JSON

{
"id": "10.1038/s41598-026-68506-6",
"type": "article-journal",
"title": "Frequency-aware transformer networks for robust and generalizable EEG-based seizure detection",
"container-title": "Scientific reports",
"author": [
{
"family": "Gamal",
"given": "Mostafa"
},
{
"family": "Abdel-Wanes",
"given": "Mustafa"
}
],
"container-title-short": "Sci Rep",
"volume": "16",
"issue": "1",
"page": "28076",
"DOI": "10.1038/s41598-026-68506-6",
"PMID": "42711447",
"PMCID": "PMC13554211",
"ISSN": "2045-2322",
"publisher": "Nature Publishing Group",
"URL": "https://doi.org/10.1038/s41598-026-68506-6",
"language": "en",
"issued": {
"date-parts": [
[
2026,
9,
8
]
]
}
}

Similar papers

The papers with a page that share the most with this one: the tools found in their code, their categories, datasets, cited references and authors, the rarest counting most.

[1] doi:10.1186/s12967-025-06862-z
Multi-stream feature fusion of vision transformer and CNN for precise epileptic seizure detection from EEG signals.
Journal: Journal of translational medicine
In common: physionet.org/content/chbmit, epilepsy, methods / tools, EEG, 1 reference
[2] doi:10.1371/journal.pone.0305166
Epilepsy detection based on multi-head self-attention mechanism.
Journal: PloS one
In common: physionet.org/content/chbmit, epilepsy, methods / tools, EEG, 1 reference
[3] doi:10.3390/s24010077
Automatic Seizure Detection Based on Stockwell Transform and Transformer.
Journal: Sensors (Basel, Switzerland)
In common: physionet.org/content/chbmit, epilepsy, methods / tools, EEG, 1 reference
[4] doi:10.3389/fnins.2025.1698960
A deep hybrid CSAE-GRU framework with two-stage balancing for automatic epileptic seizure detection using EEG-derived features.
Journal: Frontiers in neuroscience
In common: physionet.org/content/chbmit, epilepsy, methods / tools, EEG, 1 reference
[5] doi:10.3390/bioengineering12020109
Predicting Epileptic Seizures Using EfficientNet-B0 and SVMs: A Deep Learning Methodology for EEG Analysis.
Journal: Bioengineering (Basel, Switzerland)
In common: physionet.org/content/chbmit, epilepsy, methods / tools, EEG, 1 reference
[6] doi:10.1098/rsos.230601 [code]
Epileptic seizure detection using CHB-MIT dataset: The overlooked perspectives.
Journal: Royal Society open science
In common: physionet.org/content/chbmit, epilepsy, methods / tools, EEG, 1 reference
[7] doi:10.3390/s26030863
Explainable AI-Enhanced Ensemble Protocol Using Gradient-Boosted Models for Zero-False-Alarm Seizure Detection from EEG.
Journal: Sensors (Basel, Switzerland)
In common: physionet.org/content/chbmit, epilepsy, EEG, 1 reference
[8] doi:10.1186/s12911-024-02845-0
A hybrid CNN-Bi-LSTM model with feature fusion for accurate epilepsy seizure detection.
Journal: BMC medical informatics and decision making
In common: physionet.org/content/chbmit, epilepsy, EEG, 1 reference
[9] doi:10.1038/s41598-026-44536-y
PSD-LW-DCN: a generalizable power spectral density based lightweight deep convolutional neural network for seizure detection.
Journal: Scientific reports
In common: physionet.org/content/chbmit, epilepsy, EEG, 1 reference
[10] doi:10.3389/fnins.2023.1174005 [code]
Epileptic prediction using spatiotemporal information combined with optimal features strategy on EEG.
Journal: Frontiers in neuroscience
In common: physionet.org/content/chbmit, epilepsy, EEG, 1 reference

Contribute

The authors of this paper can claim it, correct its record and validate its tracing map, and the maintainers of its code (its owner, or a public member of its organization) correct what it says of their repository; anyone signed in can ask for its removal. Every request goes to OSCR's own machine, which answers it; your account page follows them.

Sign in with ORCID to claim this paper as one of its authors, correct its record or validate its tracing map: when the paper's metadata lists your ORCID iD, you are recognized at once. Maintainers of its code: sign in with GitHub, then claim the repository on your account page.

Request its removal

To ask OSCR to remove this record, the copies of its authors' scripts or its tracing map, use the removal request page: signed in, you say who you are, what to remove and why, then review and confirm the request. Published rules decide every request (how).

Discussion, reproductions, activity

Discussion: code errors and mismatches between the code and the paper about this paper and its code, from readers and its authors, beside the paper and its tracing map.

Reproductions: reports from readers who ran the authors' code and did not get the paper's result, what they ran, with which environment, commit and data.

Activity: what happens around this paper: new versions of its record, its map's validation, discussions and reproductions. It opens with sign-in.