Loading...
LSTM-Based ecg classification for continuous monitoring on personal wearable devices
Saadatnejad, S ; Sharif University of Technology | 2020
828
Viewed
- Type of Document: Article
- DOI: 10.1109/JBHI.2019.2911367
- Publisher: Institute of Electrical and Electronics Engineers Inc , 2020
- Abstract:
- Objective: A novel electrocardiogram (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 long short-term memory (LSTM) recurrent neural networks (see Fig. 1). 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. The source code is available online at http://lis.ee.sharif.edu. © 2013 IEEE
- Keywords:
- Continuous cardiac monitoring ; Electrocardiogram (ECG) classification ; Embedded and wearable devices ; Long short-term memory (LSTM) ; Machine learning ; Brain ; Deep learning ; Electrocardiography ; Learning systems ; Monitoring ; Wavelet transforms ; Wearable technology ; Cardiac monitoring ; Classification algorithm ; Continuous monitoring ; Experimental evaluation ; Learning-based approach ; Processing capacities ; Timing requirements ; Wearable devices ; Long short-term memory ; Classification algorithm ; Convolutional neural network ; Electrocardiogram ; Heart arrhythmia ; Heart left bundle branch block ; Heart rate ; Heart right bundle branch block ; Heart ventricle extrasystole ; Image segmentation ; Long short term memory network ; RR interval ; Supraventricular premature beat ; Training ; Wavelet transform
- Source: IEEE Journal of Biomedical and Health Informatics ; Volume 24, Issue 2 , 2020 , Pages 515-523
- URL: https://ieeexplore.ieee.org/document/8691755