期刊
SENSORS
卷 21, 期 21, 页码 -出版社
MDPI
DOI: 10.3390/s21217163
关键词
autoencoding; electrocardiogram; Gaussian mixture clustering; heart rate estimation
资金
- Suzhou Science and Technology Project [SYG201906]
- Science and Technology Cooperation High-Tech Industrialization Special Project - Jilin Province
- Chinese Academy of Sciences [2020SYHZ0043]
- Natural Science Foundation of Shaanxi Province [2019ZDLGY03-02-02]
The study proposes a heart rate estimation method based on convolution autoencoding and Gaussian mixture clustering, which can extract high-level heartbeat features unsupervised and calculate beat-to-beat heart rate. Experimental results demonstrate that the method, which does not rely on accurately labeled heartbeat locations, maintains better accuracy and generalization ability compared to existing heart rate estimation methods.
Heart rate is one of the most important diagnostic bases for cardiovascular disease. This paper introduces a deep autoencoding strategy into feature extraction of electrocardiogram (ECG) signals, and proposes a beat-to-beat heart rate estimation method based on convolution autoencoding and Gaussian mixture clustering. The high-level heartbeat features were first extracted in an unsupervised manner by training the convolutional autoencoder network, and then the adaptive Gaussian mixture clustering was applied to detect the heartbeat locations from the extracted features, and calculated the beat-to-beat heart rate. Compared with the existing heartbeat classification/detection methods, the proposed unsupervised feature learning and heartbeat clustering method does not rely on accurate labeling of each heartbeat location, which could save a lot of time and effort in human annotations. Experimental results demonstrate that the proposed method maintains better accuracy and generalization ability compared with the existing ECG heart rate estimation methods and could be a robust long-time heart rate monitoring solution for wearable ECG devices.
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