This repository provides a complete pipeline for preprocessing, training, and evaluating models on the CHB-MIT Scalp EEG Database.
Please download the CHB-MIT EEG dataset from:
-
To preprocess data for a single patient, run:
make preprocess
-
To preprocess data for all patients, run:
make preprocess_chb
-
To train a model on a single patient's data, run:
make train
-
To train on all patients' data, run:
make train_chb
-
To evaluate a model trained on a single patient, run:
make eval -
To evaluate models trained on all patients, run:
make eval_chb
This project utilizes techniques and concepts described in the following publication. Please cite this work if you use the associated codebase or methodologies:
Q. Dong, H. Zhang, J. Xiao, and J. Sun, "Multi-Scale Spatio-Temporal Attention Network for Epileptic Seizure Prediction," IEEE Journal of Biomedical and Health Informatics, 2025. doi: 10.1109/JBHI.2025.3545265
Keywords: Feature extraction; Electroencephalography; Epilepsy; Seizure prediction; Multi-scale spatio-temporal attention.
If you encounter any missing dependencies or configuration issues, please don’t hesitate to contact me.