Privacy–preserving dementia classification from EEG via hybrid–fusion EEGNetv4 and federated learning
As global life expectancy rises, a growing proportion of the population is affected by dementia, particularly Alzheimer's disease (AD) and Frontotemporal dementia (FTD). Electroencephalography (EEG) based diagnosis presents a non-invasive, cost effective alternative for early detection, yet exi...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2025-08-01
|
| Series: | Frontiers in Computational Neuroscience |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fncom.2025.1617883/full |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849235281875566592 |
|---|---|
| author | Muhammad Umair Muhammad Shahbaz Khan Muhammad Hanif Wad Ghaban Ibtehal Nafea Sultan Noman Qasem Sultan Noman Qasem Faisal Saeed |
| author_facet | Muhammad Umair Muhammad Shahbaz Khan Muhammad Hanif Wad Ghaban Ibtehal Nafea Sultan Noman Qasem Sultan Noman Qasem Faisal Saeed |
| author_sort | Muhammad Umair |
| collection | DOAJ |
| description | As global life expectancy rises, a growing proportion of the population is affected by dementia, particularly Alzheimer's disease (AD) and Frontotemporal dementia (FTD). Electroencephalography (EEG) based diagnosis presents a non-invasive, cost effective alternative for early detection, yet existing methods are challenged by data scarcity, inter-subject variability, and privacy concerns. This study proposes lightweight and privacy-preserving EEG classification framework combining deep learning and Federated Learning (FL). Five convolutional neural networks (EEGNetv1, EEGNetv4, EEGITNet, EEGInception, EEGInceptionERP) have been evaluated on resting-state EEG dataset comprising 88 subjects. EEG signals are preprocessed using band-pass (1–45 Hz) and notch filtering, followed by exponential standardization and 4-second windowing. EEGNetv4 outperformed among other EEG tailored models, and upon utilizing the hybrid fusion techniques it achieves 97.1% accuracy using only 1,609 parameters and less than 1 MB of memory, demonstrating high efficiency. Moreover, FL using FedAvg is implemented across five stratified clients, achieving 96.9% accuracy on the hybrid fused EEGNetV4 model while preserving data privacy. This work establishes a scalable, resource-efficient, and privacy-compliant framework for EEG-based dementia diagnosis, suitable for deployment in real-world clinical and edge-device settings. |
| format | Article |
| id | doaj-art-34e6fcab89af48a5ab8d9b56604bfd4a |
| institution | Kabale University |
| issn | 1662-5188 |
| language | English |
| publishDate | 2025-08-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Computational Neuroscience |
| spelling | doaj-art-34e6fcab89af48a5ab8d9b56604bfd4a2025-08-20T04:02:50ZengFrontiers Media S.A.Frontiers in Computational Neuroscience1662-51882025-08-011910.3389/fncom.2025.16178831617883Privacy–preserving dementia classification from EEG via hybrid–fusion EEGNetv4 and federated learningMuhammad Umair0Muhammad Shahbaz Khan1Muhammad Hanif2Wad Ghaban3Ibtehal Nafea4Sultan Noman Qasem5Sultan Noman Qasem6Faisal Saeed7School of Engineering, University of Southern Queensland, Toowoomba, QLD, AustraliaSchool of Computing, Engineering and the Built Environment, Edinburgh Napier University, Edinburgh, United KingdomDepartment of Informatics, School of Business, Örebro Universitet, Örebro, SwedenApplied College, University of Tabuk, Tabuk, Saudi ArabiaCollege of Computer Science and Engineering, Taibah University, Medina, Saudi ArabiaComputer Science Department, College of Computer and Information Sciences, Imam Mohammad Ibn Saud Islamic University (IMSIU), Riyadh, Saudi ArabiaKing Salman Center for Disability Research, Riyadh, Saudi ArabiaCollege of Computing, Birmingham City University, Birmingham, United KingdomAs global life expectancy rises, a growing proportion of the population is affected by dementia, particularly Alzheimer's disease (AD) and Frontotemporal dementia (FTD). Electroencephalography (EEG) based diagnosis presents a non-invasive, cost effective alternative for early detection, yet existing methods are challenged by data scarcity, inter-subject variability, and privacy concerns. This study proposes lightweight and privacy-preserving EEG classification framework combining deep learning and Federated Learning (FL). Five convolutional neural networks (EEGNetv1, EEGNetv4, EEGITNet, EEGInception, EEGInceptionERP) have been evaluated on resting-state EEG dataset comprising 88 subjects. EEG signals are preprocessed using band-pass (1–45 Hz) and notch filtering, followed by exponential standardization and 4-second windowing. EEGNetv4 outperformed among other EEG tailored models, and upon utilizing the hybrid fusion techniques it achieves 97.1% accuracy using only 1,609 parameters and less than 1 MB of memory, demonstrating high efficiency. Moreover, FL using FedAvg is implemented across five stratified clients, achieving 96.9% accuracy on the hybrid fused EEGNetV4 model while preserving data privacy. This work establishes a scalable, resource-efficient, and privacy-compliant framework for EEG-based dementia diagnosis, suitable for deployment in real-world clinical and edge-device settings.https://www.frontiersin.org/articles/10.3389/fncom.2025.1617883/fullneurobehavior analysisEEGNETdementiafederated learningdeep learningsmart healthcare |
| spellingShingle | Muhammad Umair Muhammad Shahbaz Khan Muhammad Hanif Wad Ghaban Ibtehal Nafea Sultan Noman Qasem Sultan Noman Qasem Faisal Saeed Privacy–preserving dementia classification from EEG via hybrid–fusion EEGNetv4 and federated learning Frontiers in Computational Neuroscience neurobehavior analysis EEGNET dementia federated learning deep learning smart healthcare |
| title | Privacy–preserving dementia classification from EEG via hybrid–fusion EEGNetv4 and federated learning |
| title_full | Privacy–preserving dementia classification from EEG via hybrid–fusion EEGNetv4 and federated learning |
| title_fullStr | Privacy–preserving dementia classification from EEG via hybrid–fusion EEGNetv4 and federated learning |
| title_full_unstemmed | Privacy–preserving dementia classification from EEG via hybrid–fusion EEGNetv4 and federated learning |
| title_short | Privacy–preserving dementia classification from EEG via hybrid–fusion EEGNetv4 and federated learning |
| title_sort | privacy preserving dementia classification from eeg via hybrid fusion eegnetv4 and federated learning |
| topic | neurobehavior analysis EEGNET dementia federated learning deep learning smart healthcare |
| url | https://www.frontiersin.org/articles/10.3389/fncom.2025.1617883/full |
| work_keys_str_mv | AT muhammadumair privacypreservingdementiaclassificationfromeegviahybridfusioneegnetv4andfederatedlearning AT muhammadshahbazkhan privacypreservingdementiaclassificationfromeegviahybridfusioneegnetv4andfederatedlearning AT muhammadhanif privacypreservingdementiaclassificationfromeegviahybridfusioneegnetv4andfederatedlearning AT wadghaban privacypreservingdementiaclassificationfromeegviahybridfusioneegnetv4andfederatedlearning AT ibtehalnafea privacypreservingdementiaclassificationfromeegviahybridfusioneegnetv4andfederatedlearning AT sultannomanqasem privacypreservingdementiaclassificationfromeegviahybridfusioneegnetv4andfederatedlearning AT sultannomanqasem privacypreservingdementiaclassificationfromeegviahybridfusioneegnetv4andfederatedlearning AT faisalsaeed privacypreservingdementiaclassificationfromeegviahybridfusioneegnetv4andfederatedlearning |