How thomaswengerter/eeg_driverfatigue works
This repository publishes MATLAB feature extraction for EEG-based driver-fatigue research, not a complete live detection system. The documented workflow preprocesses labelled EEG recordings into channel-specific epochs, extracts features, then hands those features to an external supervised-learning system. The README describes these relationships; source excerpts were not provided, so implementation details beyond that documentation are omitted.
Main entry points: FeatureExtraction.m Feature extraction · CNTpreprocess.m Epoch and filter · Channelinfo.xls Channel reference · SampEn.m Sample entropy
Components 12
EEG preprocessing
- EEG recordings
- Channel reference
Channelinfo.xls - Epoch and filter
CNTpreprocess.m - Channel training data
Feature extraction
- Feature extraction
FeatureExtraction.m - Spectral and signal statistics
FeatureExtraction.m - Sample entropy
SampEn.m - Fuzzy feature module
Fuzzy_MI.m - Channel feature data
Supervised learning
- Supervised learning system
- Fatigue detector
Other components
- Researcher
Connections 12
- Researcher → Epoch and filter: runs script
README.md - EEG recordings → Epoch and filter: loads and labels
README.md - Channel reference → Epoch and filter: guides selection
README.md - Epoch and filter → Channel training data: saves epochs
README.md - Researcher → Feature extraction: runs script
README.md - Channel training data → Feature extraction: analyzes
README.md - Feature extraction → Spectral and signal statistics: extracts features
README.md - Feature extraction → Sample entropy: extracts feature
README.md - Feature extraction → Fuzzy feature module: extracts feature
- Feature extraction → Channel feature data: saves features
README.md - Channel feature data → Supervised learning system: feeds features
README.md - Supervised learning system → Fatigue detector: trains detector
README.md