An ECG Segmentation Method Based on GMM and Clusterwise Regression

Min LI; Raymond CHAN; Yumei HUANG; Tieyong ZENG

doi:10.1007/s42967-024-00467-x

An ECG Segmentation Method Based on GMM and Clusterwise Regression

Min LI, Raymond CHAN, Yumei HUANG^*, Tieyong ZENG

^*Corresponding author for this work

School of Data Science

Research output: Journal Publications › Journal Article (refereed) › peer-review

Abstract

The electrocardiogram (ECG) segmentation needs to separate different waves from an ECG and cluster the waves simultaneously. Clusterwise regression is a useful approach that can segment and cluster the data simultaneously. In this paper, we apply the clusterwise regression method to segment the ECG. By modeling the ECG signal wave by the Gaussian mixture model (GMM) and introducing a weight function, we propose a minimization model that consists of the weighted sum of the negative log-likelihood and the total variation (TV) of the weight function. The TV of the weight function enforces the temporal consistency. A supervised algorithm is designed to solve the proposed model. Experimental results show the efficiency of the proposed method for the ECG segmentation.

Original language	English
Journal	Communications on Applied Mathematics and Computation
Early online date	22 Feb 2025
DOIs	https://doi.org/10.1007/s42967-024-00467-x
Publication status	E-pub ahead of print - 22 Feb 2025

Bibliographical note

Publisher Copyright:
© Shanghai University 2025.

Funding

This work was supported by the National Natural Science Foundation of China (No. 11971215), the Science and Technology Project of Gansu Province of China (No. 22JR5RA391), Center for Data Science of Lanzhou University, China, and the Key Laboratory of Applied Mathematics and Complex Systems of Lanzhou University, China.

Keywords

Clusterwise regression
Electrocardiogram (ECG)
Fiducial point extraction
Gaussian mixture model (GMM)
Segmentation

Access to Document

10.1007/s42967-024-00467-x

https://link.springer.com/10.1007/s42967-024-00467-x

Cite this

@article{d770b5c77c494fd18d3910af27b40d87,

title = "An ECG Segmentation Method Based on GMM and Clusterwise Regression",

abstract = "The electrocardiogram (ECG) segmentation needs to separate different waves from an ECG and cluster the waves simultaneously. Clusterwise regression is a useful approach that can segment and cluster the data simultaneously. In this paper, we apply the clusterwise regression method to segment the ECG. By modeling the ECG signal wave by the Gaussian mixture model (GMM) and introducing a weight function, we propose a minimization model that consists of the weighted sum of the negative log-likelihood and the total variation (TV) of the weight function. The TV of the weight function enforces the temporal consistency. A supervised algorithm is designed to solve the proposed model. Experimental results show the efficiency of the proposed method for the ECG segmentation.",

keywords = "Clusterwise regression, Electrocardiogram (ECG), Fiducial point extraction, Gaussian mixture model (GMM), Segmentation",

author = "Min LI and Raymond CHAN and Yumei HUANG and Tieyong ZENG",

note = "Publisher Copyright: {\textcopyright} Shanghai University 2025.",

year = "2025",

month = feb,

day = "22",

doi = "10.1007/s42967-024-00467-x",

language = "English",

journal = "Communications on Applied Mathematics and Computation",

issn = "2096-6385",

publisher = "Springer",

}

TY - JOUR

T1 - An ECG Segmentation Method Based on GMM and Clusterwise Regression

AU - LI, Min

AU - CHAN, Raymond

AU - HUANG, Yumei

AU - ZENG, Tieyong

PY - 2025/2/22

Y1 - 2025/2/22

N2 - The electrocardiogram (ECG) segmentation needs to separate different waves from an ECG and cluster the waves simultaneously. Clusterwise regression is a useful approach that can segment and cluster the data simultaneously. In this paper, we apply the clusterwise regression method to segment the ECG. By modeling the ECG signal wave by the Gaussian mixture model (GMM) and introducing a weight function, we propose a minimization model that consists of the weighted sum of the negative log-likelihood and the total variation (TV) of the weight function. The TV of the weight function enforces the temporal consistency. A supervised algorithm is designed to solve the proposed model. Experimental results show the efficiency of the proposed method for the ECG segmentation.

AB - The electrocardiogram (ECG) segmentation needs to separate different waves from an ECG and cluster the waves simultaneously. Clusterwise regression is a useful approach that can segment and cluster the data simultaneously. In this paper, we apply the clusterwise regression method to segment the ECG. By modeling the ECG signal wave by the Gaussian mixture model (GMM) and introducing a weight function, we propose a minimization model that consists of the weighted sum of the negative log-likelihood and the total variation (TV) of the weight function. The TV of the weight function enforces the temporal consistency. A supervised algorithm is designed to solve the proposed model. Experimental results show the efficiency of the proposed method for the ECG segmentation.

KW - Clusterwise regression

KW - Electrocardiogram (ECG)

KW - Fiducial point extraction

KW - Gaussian mixture model (GMM)

KW - Segmentation

UR - http://www.scopus.com/inward/record.url?scp=85218241390&partnerID=8YFLogxK

U2 - 10.1007/s42967-024-00467-x

DO - 10.1007/s42967-024-00467-x

M3 - Journal Article (refereed)

SN - 2096-6385

JO - Communications on Applied Mathematics and Computation

JF - Communications on Applied Mathematics and Computation

ER -

An ECG Segmentation Method Based on GMM and Clusterwise Regression

Abstract

Bibliographical note

Funding

Keywords

Access to Document

Other files and links

Fingerprint

Cite this