Meta-Learning for EEG, Sleep Staging, Transfer Learning, Pre-trained EEG, PSG datasets (IEEE Journal of Biomedical and Health Informatics)
Five publicly datasets were used to evaluate our method including
[All of them should be prepared and put in /data - only MASS datasets were pre-processed using bandpass filters as described in our paper]
configure.py
python MAML.py
python NormalPretrain.py
python FinetuneCNNKFolds.py
FinetuneAndTestOnBestHyperparams-List.ipynb
To cite our paper,
@ARTICLE{9258375,
author={N. {Banluesombatkul} and P. {Ouppaphan} and P. {Leelaarporn} and P. {Lakhan} and B. {Chaitusaney} and N. {Jaimchariya} and E. {Chuangsuwanich} and W. {Chen} and H. {Phan} and N. {Dilokthanakul} and T. {Wilaiprasitporn}},
journal={IEEE Journal of Biomedical and Health Informatics},
title={MetaSleepLearner: A Pilot Study on Fast Adaptation of Bio-signals-Based Sleep Stage Classifier to New Individual Subject Using Meta-Learning},
year={2020},
volume={},
number={},
pages={1-1},
doi={10.1109/JBHI.2020.3037693}}