LM-Coherence Biology VI: Multi-Subject Validation and Robust Classification of Conscious States Using Neural Phase Dynamics
Summary
No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.
Summarise with VIRAT Free to try with your Science Catalogs account.Abstract
This dataset and code repository provides the full computational framework used in LM-Coherence Biology VI, where we performed a multi-subject validation of the LM-Coherence theory using real EEG data from the PhysioNet Sleep-EDF database. The repository includes: EEG data preprocessing pipeline (based on MNE) Phase extraction via the Hilbert transform Calculation of LM coherence observables: Global phase coherence (C) Phase entropy (S_phi) Dynamic susceptibility (Chi) Sliding window analysis for temporal feature extraction Construction of multi-subject datasets (wake vs. deep sleep N3) Classification using machine learning (logistic regression) Leave-One-Subject-Out (LOSO) cross-validation Performance metrics (ROC curves, AUC, accuracy) Visualization of state space and classification results This work demonstrates that LM coherence observables generalize across individuals and serve as robust and largely interpretable biomarkers of conscious states. LM.
Fields of Study & Subjects
EEG and Brain-Computer Interfaces
Neural dynamics and brain function
Sleep and Wakefulness Research
Publication details
- Journal / source
- Zenodo (CERN European Organization for Nuclear Research)
- Publication date
- 30 March 2026
- Language
- EN
- Document type
- Book