MontageFL: code for "Montage-agnostic federated learning for privacy-preserving Alzheimer's disease classification from heterogeneous multi-site EEG"
Year: 2026
Type: software
Abstract: Analysis code accompanying the paper "Montage-agnostic federated learning for privacy-preserving Alzheimer's disease classification from heterogeneous multi-site EEG." The code reproduces the study's analyses on the public OpenNeuro dataset ds004504: a montage-agnostic harmonization pipeline that maps heterogeneous EEG montages to a fixed feature space, dual-stream (spectral and covariance) feature extraction, and federated, local, and centralized training evaluated under leakage-free subject-level cross-validation, together with a within-subject montage comparison and a data-scarcity experiment. See README.md for dependencies and run instructions.
Authors: Masry, Bahaa, Shahin, Anas, Karraz, George
Institutions: Damascus University, Syrian Virtual University
Language: English
Subfield: Cognitive Neuroscience
Field: Neuroscience
Domain: Life Sciences
Open Access status: green
OpenAlex ID: W7166646102