Intelligent Classification of Heartbeats for Automated Real-Time ECG Monitoring

Park, Ju‐Young; Kang, Kyungtae

doi:10.1089/tmj.2014.0033

Cited by 11 publications

(6 citation statements)

References 29 publications

(42 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…They also analyzed the human walking dynamics to estimate the dominating forces and used this knowledge to find the heading direction of the pedestrian. For the application of biological monitoring, Park et al [29] demonstrated a very promising application to classify and monitor heartbeats, while Nandakumar et al [30] monitored sleep apnea using the sensors in smartphones to develop more convenient conditions for gesture recognition [31]. Besides, there are also some other applications.…”

Section: Related Workmentioning

confidence: 99%

Deep Fisher discriminant learning for mobile hand gesture recognition

Xie

Zhang

et al. 2018

Pattern Recognition

View full text Add to dashboard Cite

show abstract

Section: Related Workmentioning

confidence: 99%

Deep Fisher discriminant learning for mobile hand gesture recognition

Xie

Zhang

et al. 2018

Pattern Recognition

View full text Add to dashboard Cite

show abstract

“…The second study case, [19], present a preemptive approach to hearth disease management. This is based on the thought that any heart condition has multiple symptoms that can go from arrhythmia, pain, fainting or straight a heart attack.…”

Section: Researchmentioning

confidence: 99%

Survey on IoT solutions applied to Healthcare

Castro

Coral

Cabra

et al. 2017

DYNA

View full text Add to dashboard Cite

The Internet of Things (IoT) is a new technological paradigm that allows any object or thing to be connected to other things, services or people through the Internet. IoT brings tools for empowering working areas such as health, logistics, industry, security, agriculture and environment. In this paper, we introduce a comprehensive survey of IoT technologies, methods, statistics and success cases applied to healthcare. In the last section its talked about the work done in this subject on the Colombian context, including successful applications and current projects.Keywords: Internet of things; e-Health; healthcare.Revisión del estado del arte de soluciones IoT en salud Resumen El internet de las cosas, también conocido como IoT por sus siglas en inglés (Internet of Things), es un nuevo paradigma tecnológico que permite la interconexión de objetos (las cosas), servicios y/o personas por medio de internet. IoT introduce nuevas herramientas que enriquecen el trabajo en diferentes sectores industriales. Este artículo presenta un estudio del trabajo desarrollado en todo el mundo en tecnologías con base en el concepto de IoT en el marco de la industria del cuidado de la salud, incluyendo métodos, estadísticas y casos de éxito. En la última sección, se discute sobre el trabajo realizado en este ámbito en el contexto colombiano, incluyendo aplicaciones exitosas y proyectos que se encuentran en desarrollo.Palabras clave: Internet de las cosas; e Health; cuidado en la salud.

show abstract

“…The feature extraction techniques can be grouped according to the mathematical models used to assess the P-QRS-T waveform complexity. The widely used approach applies P-QRS-T onset/offset delineation or extraction of QRS patterns within a fixed-length window around the fiducial point to measure morphological features in the time domain, including amplitudes, areas, specific interval durations or magnitudes and angles of the QRS vectors in the vectorcardiographic (VCG) planes [ 2 – 5 , 8 – 19 ]. Other ECG descriptors rely on QRS frequency components calculated either by discrete Fourier transform (DFT) [ 11 , 18 , 20 ] or by computationally efficient algorithms with filter banks [ 4 , 21 ].…”

Section: Introductionmentioning

confidence: 99%

“…Different mathematical approaches for decision support systems have been proposed for the automatic classification of heartbeats. Widely applied classification methods are based on linear programming using the Kth nearest-neighbours (KNN) using clustering technique [ 5 , 9 – 11 , 26 ], linear discriminant analysis (LDA) [ 3 , 13 – 15 ], fuzzy analysis [ 4 , 12 , 21 ] and decision tree classifiers [ 7 , 8 , 16 , 17 , 21 , 25 , 32 ]. Another frequently used classifier is the support vector machine (SVM)–least square SVM applying linear kernel function [ 22 – 24 ] or SVM relying on quadratic optimization by mapping of the feature space into a high dimensional space using various kernel transformations like hyperbolic tangent sigmoid transfer function [ 18 ] or Gaussian radial basis function [ 19 , 20 , 23 , 24 ].…”

Section: Introductionmentioning

confidence: 99%

“…Decision trees are also well employed in the final classification step of a complex features extraction scheme by DWT, PCA and independent component analysis [ 25 ]. Such complicated computation schemes, however, are losing the benefit from simplicity that gains the decision tree model, which is the core for building remote automated real-time ECG analysis modules, such as PDAs (Personal Digital Assistants) [ 32 ] or wireless Holter monitors [ 7 , 8 ].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Superiority of Classification Tree versus Cluster, Fuzzy and Discriminant Models in a Heartbeat Classification System

Krasteva

Jekova

Leber³

et al. 2015

PLoS ONE

View full text Add to dashboard Cite

This study presents a 2-stage heartbeat classifier of supraventricular (SVB) and ventricular (VB) beats. Stage 1 makes computationally-efficient classification of SVB-beats, using simple correlation threshold criterion for finding close match with a predominant normal (reference) beat template. The non-matched beats are next subjected to measurement of 20 basic features, tracking the beat and reference template morphology and RR-variability for subsequent refined classification in SVB or VB-class by Stage 2. Four linear classifiers are compared: cluster, fuzzy, linear discriminant analysis (LDA) and classification tree (CT), all subjected to iterative training for selection of the optimal feature space among extended 210-sized set, embodying interactive second-order effects between 20 independent features. The optimization process minimizes at equal weight the false positives in SVB-class and false negatives in VB-class. The training with European ST-T, AHA, MIT-BIH Supraventricular Arrhythmia databases found the best performance settings of all classification models: Cluster (30 features), Fuzzy (72 features), LDA (142 coefficients), CT (221 decision nodes) with top-3 best scored features: normalized current RR-interval, higher/lower frequency content ratio, beat-to-template correlation. Unbiased test-validation with MIT-BIH Arrhythmia database rates the classifiers in descending order of their specificity for SVB-class: CT (99.9%), LDA (99.6%), Cluster (99.5%), Fuzzy (99.4%); sensitivity for ventricular ectopic beats as part from VB-class (commonly reported in published beat-classification studies): CT (96.7%), Fuzzy (94.4%), LDA (94.2%), Cluster (92.4%); positive predictivity: CT (99.2%), Cluster (93.6%), LDA (93.0%), Fuzzy (92.4%). CT has superior accuracy by 0.3–6.8% points, with the advantage for easy model complexity configuration by pruning the tree consisted of easy interpretable ‘if-then’ rules.

show abstract

Intelligent Classification of Heartbeats for Automated Real-Time ECG Monitoring

Abstract: This work provides a guide to the systematic design of an intelligent classification system for decision support in Holter ECG monitoring.

Cited by 11 publications

References 29 publications

Deep Fisher discriminant learning for mobile hand gesture recognition

Deep Fisher discriminant learning for mobile hand gesture recognition

Survey on IoT solutions applied to Healthcare

Superiority of Classification Tree versus Cluster, Fuzzy and Discriminant Models in a Heartbeat Classification System

Contact Info

Product

Resources

About