Convolutional Autoencoding and Gaussian Mixture Clustering for Unsupervised Beat-to-Beat Heart Rate Estimation of Electrocardiograms from Wearable Sensors

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...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Jun Zhong, Dong Hai, Jiaxin Cheng, Changzhe Jiao, Shuiping Gou, Yongfeng Liu, Hong Zhou, Wenliang Zhu
Formato: article
Lenguaje:EN
Publicado: MDPI AG 2021
Materias:
Acceso en línea:https://doaj.org/article/4afda4a83b3a4b41b7586247173ede0e
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
id oai:doaj.org-article:4afda4a83b3a4b41b7586247173ede0e
record_format dspace
spelling oai:doaj.org-article:4afda4a83b3a4b41b7586247173ede0e2021-11-11T19:09:22ZConvolutional Autoencoding and Gaussian Mixture Clustering for Unsupervised Beat-to-Beat Heart Rate Estimation of Electrocardiograms from Wearable Sensors10.3390/s212171631424-8220https://doaj.org/article/4afda4a83b3a4b41b7586247173ede0e2021-10-01T00:00:00Zhttps://www.mdpi.com/1424-8220/21/21/7163https://doaj.org/toc/1424-8220Heart 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.Jun ZhongDong HaiJiaxin ChengChangzhe JiaoShuiping GouYongfeng LiuHong ZhouWenliang ZhuMDPI AGarticleautoencodingelectrocardiogramGaussian mixture clusteringheart rate estimationChemical technologyTP1-1185ENSensors, Vol 21, Iss 7163, p 7163 (2021)
institution DOAJ
collection DOAJ
language EN
topic autoencoding
electrocardiogram
Gaussian mixture clustering
heart rate estimation
Chemical technology
TP1-1185
spellingShingle autoencoding
electrocardiogram
Gaussian mixture clustering
heart rate estimation
Chemical technology
TP1-1185
Jun Zhong
Dong Hai
Jiaxin Cheng
Changzhe Jiao
Shuiping Gou
Yongfeng Liu
Hong Zhou
Wenliang Zhu
Convolutional Autoencoding and Gaussian Mixture Clustering for Unsupervised Beat-to-Beat Heart Rate Estimation of Electrocardiograms from Wearable Sensors
description 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.
format article
author Jun Zhong
Dong Hai
Jiaxin Cheng
Changzhe Jiao
Shuiping Gou
Yongfeng Liu
Hong Zhou
Wenliang Zhu
author_facet Jun Zhong
Dong Hai
Jiaxin Cheng
Changzhe Jiao
Shuiping Gou
Yongfeng Liu
Hong Zhou
Wenliang Zhu
author_sort Jun Zhong
title Convolutional Autoencoding and Gaussian Mixture Clustering for Unsupervised Beat-to-Beat Heart Rate Estimation of Electrocardiograms from Wearable Sensors
title_short Convolutional Autoencoding and Gaussian Mixture Clustering for Unsupervised Beat-to-Beat Heart Rate Estimation of Electrocardiograms from Wearable Sensors
title_full Convolutional Autoencoding and Gaussian Mixture Clustering for Unsupervised Beat-to-Beat Heart Rate Estimation of Electrocardiograms from Wearable Sensors
title_fullStr Convolutional Autoencoding and Gaussian Mixture Clustering for Unsupervised Beat-to-Beat Heart Rate Estimation of Electrocardiograms from Wearable Sensors
title_full_unstemmed Convolutional Autoencoding and Gaussian Mixture Clustering for Unsupervised Beat-to-Beat Heart Rate Estimation of Electrocardiograms from Wearable Sensors
title_sort convolutional autoencoding and gaussian mixture clustering for unsupervised beat-to-beat heart rate estimation of electrocardiograms from wearable sensors
publisher MDPI AG
publishDate 2021
url https://doaj.org/article/4afda4a83b3a4b41b7586247173ede0e
work_keys_str_mv AT junzhong convolutionalautoencodingandgaussianmixtureclusteringforunsupervisedbeattobeatheartrateestimationofelectrocardiogramsfromwearablesensors
AT donghai convolutionalautoencodingandgaussianmixtureclusteringforunsupervisedbeattobeatheartrateestimationofelectrocardiogramsfromwearablesensors
AT jiaxincheng convolutionalautoencodingandgaussianmixtureclusteringforunsupervisedbeattobeatheartrateestimationofelectrocardiogramsfromwearablesensors
AT changzhejiao convolutionalautoencodingandgaussianmixtureclusteringforunsupervisedbeattobeatheartrateestimationofelectrocardiogramsfromwearablesensors
AT shuipinggou convolutionalautoencodingandgaussianmixtureclusteringforunsupervisedbeattobeatheartrateestimationofelectrocardiogramsfromwearablesensors
AT yongfengliu convolutionalautoencodingandgaussianmixtureclusteringforunsupervisedbeattobeatheartrateestimationofelectrocardiogramsfromwearablesensors
AT hongzhou convolutionalautoencodingandgaussianmixtureclusteringforunsupervisedbeattobeatheartrateestimationofelectrocardiogramsfromwearablesensors
AT wenliangzhu convolutionalautoencodingandgaussianmixtureclusteringforunsupervisedbeattobeatheartrateestimationofelectrocardiogramsfromwearablesensors
_version_ 1718431581964599296