This repository includes the implentation of R peak detection method in Robust R-Peak Detection in Low-Quality Holter ECGs Using 1D Convolutional Neural Network.
- The China Physiological Signal Challenge 2020, (CPSC-2020) dataset is used for training & testing.
- R peak annotations are already available in the data folder.
- Download CPSC data from the link to the "data/" folder
- Data Preparation without augmentation
python prepare_data.py- Data Preparation with augmentation
python prepare_data_augmentation.py- Start patient wise training and evaluation.
python run_cnn.pyIf you use the provided method in this repository, please cite the following paper:
@article{zahid2021robust,
title={Robust R-Peak Detection in Low-Quality Holter ECGs Using 1D Convolutional Neural Network},
author={Zahid, Muhammad Uzair and Kiranyaz, Serkan and Ince, Turker and Devecioglu, Ozer Can and Chowdhury, Muhammad EH and Khandakar, Amith and Tahir, Anas and Gabbouj, Moncef},
journal={IEEE Transactions on Biomedical Engineering},
volume={69},
number={1},
pages={119--128},
year={2021},
publisher={IEEE}
}