The project is about applying CNNs to EEG data from CHB-MIT to predict seizure
-
Updated
May 19, 2023 - Python
The project is about applying CNNs to EEG data from CHB-MIT to predict seizure
Benchmark of 15+ neural architectures on 916 hours of pediatric EEG (CHB-MIT) for seizure detection.
Applying REVE, an EEG foundation model, to seizure detection using the CHB-MIT scalp EEG dataset.
“High-performance seizure detection system using Spiking Neural Networks (SNN) with STDP learning and SVM classification. Built on BindsNET & PyTorch for neuromorphic EEG signal processing.”
Automated epileptic seizure detection framework combining Topological Data Analysis (Persistent Homology), ICA artifact removal and Random Forest classification on CHB-MIT Scalp EEG data, featuring an interactive Streamlit dashboard.
Python pipeline for the CHB-MIT Scalp EEG database featuring ictal/pre-ictal segment extraction and covariance-based feature engineering
Seizure prediction models on the chb-mit dataset
EEG seizure detection on CHB-MIT (chb01) with Welch bandpower features and time-ordered evaluation (walk-forward CV).
Desktop EEG viewer: waveform, animated topomap, and seizure annotations for EDF/BDF datasets
EEG preprocessing, frequency-band analysis and seizure-segment exploration using MATLAB.
Extract EEG signal arrays and seizure metadata from CHB-MIT and EU Epilepsy datasets.
To associate your repository with the chb-mit topic, visit your repo's landing page and select "manage topics."