How divya-eng21/eeg-drowsiness-detection works
This repository is a small EEG drowsiness-classification project. Its documented workflow uses a dataset of pre-extracted EEG frequency-band features to compare machine-learning and neural-network approaches, then reports model accuracy; Random Forest performs best in the README. The tree identifies separate MLP and 1D-CNN notebooks and a general ML-pipeline notebook, but no notebook contents were provided, so internal execution details and notebook-to-notebook calls cannot be verified.
Main entry points: acquiredDataset.csv EEG dataset · README.md Model results · eeg_drowsiness_detection_ML_pipeline.ipynb ML pipeline · eeg_drowsiness_DeepLearning_MLP.ipynb MLP experiment
Components 5
EEG data
- EEG dataset
acquiredDataset.csv
Model experiments
- ML pipeline
eeg_drowsiness_detection_ML_pipeline.ipynb - MLP experiment
eeg_drowsiness_DeepLearning_MLP.ipynb - 1D-CNN experiment
eeg_drowsiness_DeepLearning_1DCNN.ipynb - Model results
README.md
Connections 6
- EEG dataset → ML pipeline: classifies from
README.md - EEG dataset → MLP experiment: classifies from
- EEG dataset → 1D-CNN experiment: classifies from
- ML pipeline → Model results: reports comparison
README.md - MLP experiment → Model results: reports accuracy
README.md - 1D-CNN experiment → Model results: reports accuracy
README.md