FCEEG: federated learning-based seizure diagnosis through electroencephalogram (EEG) analysis
Bibliographic record
Abstract
Electroencephalography (EEG) signals are crucial for seizure diagnosis. The data provides detailed insights into brain activity which aids in epilepsy management. Artificial intelligence (AI) and deep learning are widely employed in the analysis of EEG signals to achieve promising classification performance. However, these AI models require centralized data processing, thereby raising privacy concerns. Thus, we propose FCEEG, a convolutional-based deep learning with federated learning (FL) to diagnose seizures with EEG signals while preserving data privacy. Specifically, EEG data are learned and analyzed using convolutional neural networks (CNNs) on local clients without the need to transmit the clients’ raw EEG data to the central server. The decentralized process ensures the confidentiality and integrity of these sensitive health records. This balances data privacy with a promising performance. Additionally, this research involves experimenting with the best aggregation methods for EEG signals in federated learning. The empirical results demonstrate that our proposed framework FCEEG with Federated Proximal (FedProx) aggregation method can effectively utilize diverse local EEG data from local clients to perform reliable seizure detection with a promising performance with an accuracy of 87.66%, precision of 99.95%, specificity of 99.96%, recall rate of 75.86% and F1-score of 86.25%.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.003 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".