Connectivity algorithms that leverage the MNE-Python API.
-
Updated
Oct 5, 2026 - Python
Connectivity algorithms that leverage the MNE-Python API.
24/7 multimodal bio-sensing wearable platform: tiered acquisition (PPG/IMU continuous → EEG/fNIRS rest), edge AI triage, LSL/XDF sync, validated on WESAD/MIT-BIH/Sleep-EDF
EEG source localization pipeline for mouse models using the Antwerp Mouse Brain Atlas. Supports multiple BEM head models, inverse methods (sLORETA, dSPM, MNE, beamformers), and multi-subject batch processing.
Statistical analysis toolkit for source-localized EEG data. 13 modules across ROI, vertex, and electrode levels: PSD, aperiodic, connectivity (6 metrics), transfer entropy, PAC, wholebrain, FCD, specparam, MVPA, graph theory/NBS, spatial LMM. Python + R.
Contextual MEG/EEG source estimation: an LSTM learns the temporal context of brain activity to sharpen dSPM/MNE estimates. PyTorch + ONNX, MNE-Python compatible.
Single-subject pilot study code for evaluating ICA, ASR, and IMU-referenced regression for motion artifact suppression in wearable EEG across 14-, 8-, and 4-channel configurations.
Curated, verified list of open-source EEG software: EEGLAB, MNE-Python, Brainstorm, FieldTrip, BCI/deep learning, sleep & clinical tools, datasets.
Open-source, local-first EEG/MEG language-decoding research toolkit with bounded data access, honest baselines, reproducible caches, and explicit proof boundaries.
Evaluating computational brain models as dimensionality reduction methods for EEG (MSc thesis, Imperial College London)
End-to-end resting-state EEG pipeline classifying younger (20-34) vs. older (52-70) adults from 405 people in OpenNeuro ds005385: MNE-Python preprocessing, Welch spectral features and nested cross-validated gradient boosting (ROC AUC 0.90, permutation p < 0.01).
Catalogue of 24 open optically pumped magnetoencephalography deposits with 4 no-person noise recordings
A modular pipeline for EEG signal conditioning, ICA ocular artifact removal, and EEGNet decoding.
Closed-loop BCI pipeline for automated lucid dream induction via real-time EEG sleep stage classification | Part of LUCID: Reality?
Automatically process entire electrophysiological datasets using MNE-Python.
EEG motor-imagery classification with a hybrid CNN-Transformer: 72.3% accuracy across 103 subjects, 4.2 ms real-time inference (PhysioNet EEGMMIDB).
Representational Similarity Analysis on MEG and EEG data
Open-data EEG pipeline for ageing, sleep and dementia (Python · MNE) — learning project, in progress
EEG-based analysis and Machine Learning for Alzheimer's disease using MNE-Python and spontaneous EEG data
To associate your repository with the mne-python topic, visit your repo's landing page and select "manage topics."