chahmed12/eeg-absence-detection

How chahmed12/eeg-absence-detection works

EEG Absence Detection turns annotated multichannel EEG recordings into seizure-event intervals, evaluated by patient-held-out validation and presented through a Streamlit demo. The documented workflow is signal loading and causal filtering, annotation/window labeling, feature or raw-window modeling, temporal postprocessing, then event-level evaluation and visualization. Separate experimental branches cover LightGBM and deep-learning models, including EEGNet and threshold selection. Source excerpts establish several module calls; broader pipeline-stage links rely on the README, so unsampled implementation details are not expanded.

Main entry points: io.py Signal and annotation I/O · postprocess.py Event reconstruction · evaluation.py Event evaluation · verify_three_checks.py Validation checks

Components 19

Data and targets

EEG recordings
Seizure annotations
Signal and annotation I/O src/io.py
Sample labeling src/labeling.py

Signal preparation

Pipeline configuration src/config.py
Causal filtering src/preprocess.py
Window generation src/windowing.py
EEG features src/features.py

Detection models

Classical models src/models.py
Deep learning src/deep_learning.py
Nested LightGBM scripts/scripts_step6_exp00_lightgbm_nested.py
EEGNet experiment scripts/scripts_step6_exp03_eegnet.py
Threshold selection scripts/scripts_step6_exp04_threshold.py

Assessment and results

Validation checks scripts/verify_three_checks.py
Event reconstruction src/postprocess.py
Event evaluation src/evaluation.py
EEG visualization src/viz.py

Interactive demo

Streamlit demo app/streamlit_app.py

Other components

Analyst

Connections 34

Analyst → Streamlit demo: opens demo README.md
EEG recordings → Signal and annotation I/O: loads README.md
Seizure annotations → Signal and annotation I/O: loads and audits src/io.py
Signal and annotation I/O → Causal filtering: filters signal src/io.py
Pipeline configuration → Signal and annotation I/O: configures paths src/config.py
Signal and annotation I/O → Sample labeling: supplies annotations README.md
Sample labeling → Window generation: labels windows README.md
Causal filtering → EEG features: prepares signal README.md
Window generation → EEG features: segments signal src/features.py
EEG features → Classical models: provides features README.md
Window generation → Deep learning: provides raw windows src/deep_learning.py
Nested LightGBM → Classical models: uses models scripts/scripts_step6_exp00_lightgbm_nested.py
Nested LightGBM → Event evaluation: evaluates folds scripts/scripts_step6_exp00_lightgbm_nested.py
Nested LightGBM → Signal and annotation I/O: loads recordings scripts/scripts_step6_exp00_lightgbm_nested.py
Nested LightGBM → Event reconstruction: reconstructs events scripts/scripts_step6_exp00_lightgbm_nested.py
EEGNet experiment → Deep learning: uses network scripts/scripts_step6_exp03_eegnet.py
EEGNet experiment → Event evaluation: evaluates folds scripts/scripts_step6_exp03_eegnet.py
EEGNet experiment → Signal and annotation I/O: loads recordings scripts/scripts_step6_exp03_eegnet.py
EEGNet experiment → Event reconstruction: reconstructs events scripts/scripts_step6_exp03_eegnet.py
Threshold selection → Event reconstruction: selects thresholds scripts/scripts_step6_exp04_threshold.py
Threshold selection → Event evaluation: scores events scripts/scripts_step6_exp04_threshold.py
Classical models → Event reconstruction: scores windows
Deep learning → Event reconstruction: scores windows
Event reconstruction → Event evaluation: returns intervals src/evaluation.py
Event evaluation → EEG visualization: reports metrics
Streamlit demo → Signal and annotation I/O: loads data app/streamlit_app.py
Streamlit demo → Event reconstruction: uses event intervals app/streamlit_app.py
Streamlit demo → Event evaluation: uses event metrics app/streamlit_app.py
Streamlit demo → EEG visualization: renders views app/streamlit_app.py
Validation checks → Classical models: checks models scripts/verify_three_checks.py
Validation checks → Deep learning: checks networks scripts/verify_three_checks.py
Validation checks → Event evaluation: checks evaluation scripts/verify_three_checks.py
Validation checks → Signal and annotation I/O: loads recordings scripts/verify_three_checks.py
Validation checks → Event reconstruction: checks reconstruction scripts/verify_three_checks.py

Drawn by GitDiagram on November 14, 2026 from the repository's file tree, README and source files. Read as Markdown ·