期刊
IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS
卷 24, 期 2, 页码 515-523出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/JBHI.2019.2911367
关键词
Continuous cardiac monitoring; electrocardiogram (ECG) classification; machine learning; long short-term memory (LSTM); embedded and wearable devices
类别
资金
- Iran National Science Foundation [95835171]
A novel electrocardiogram (ECG) classification algorithm is proposed for continuous cardiac monitoring on wearable devices with limited processing capacity. The proposed solution employs a novel architecture consisting of wavelet transform and multiple long short-term memory (LSTM) recurrent neural networks. 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. 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. The proposed algorithm is both accurate and lightweight. The source code is available online at http://lis.ee.sharif.edu.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据