Saeed Saadatnejad, Mohammadhosein Oveisi, Matin Hashemi, "LSTM-Based ECG Classification for Continuous Monitoring on Personal Wearable Devices", IEEE Journal of Biomedical and Health Informatics (JBHI), Vol. 24, No. 2, February 2020.
Objective: A novel ECG classification algorithm is proposed for continuous cardiac monitoring on wearable devices with limited processing capacity. Methods: The proposed solution employs a novel architecture consisting of wavelet transform and multiple LSTM recurrent neural networks. Results: Experimental evaluations show superior ECG classification performance compared to previous works. Measurements on different hardware platforms show the proposed algorithm meets timing requirements for continuous and real-time execution on wearable devices. Conclusion: In contrast to many compute-intensive deep-learning based approaches, the proposed algorithm is lightweight, and therefore, brings continuous monitoring with accurate LSTM-based ECG classification to wearable devices. Significance: The proposed algorithm is both accurate and lightweight.
Source code of the ECG classification algorithm in TensorFlow (Python).
Hardware implementation codes to measure execution times on AndroidWear (Java) and also on Raspberry Pi and Nano Pi (C++).
Contact saeed.saadatnejad@epfl.ch or matin@sharif.edu in case you have any questions regarding the source codes.
Please use the following entry to cite our work in your publications:
@article{saadatnejad2020jbhi,
author = {Saeed Saadatnejad and Mohammadhosein Oveisi and Matin Hashemi},
title = {LSTM-Based ECG Classification for Continuous Monitoring on Personal Wearable Devices},
journal = {IEEE Journal of Biomedical and Health Informatics (JBHI)},
year = {2020},
month = {February},
volume = {24},
number = {2},
pages = {515-523},
doi = {10.1109/JBHI.2019.2911367}
}