A novel feature representation approach for single-lead heartbeat classification based on adaptive Fourier decomposition

DOI10.1142/S0219691321500107MaRDI QIDQ5022934zbMATH OpenOpenAlexFDO

Authors Chunyu Tan, H.-T. Wu, Tao Qian, Liming Zhang

Publication date 20 January 2022

Published in International Journal of Wavelets, Multiresolution and Information Processing (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/1906.07361

zbMATH Keywords

adaptive Fourier decompositionheartbeat classificationinstantaneous frequencytime-frequency representation

Mathematics Subject Classification ID

Fourier and Fourier-Stieltjes transforms and other transforms of Fourier type (42A38) Biomedical imaging and signal processing (92C55)

Abstract: This paper proposes a novel approach for heartbeat classification from single-lead electrocardiogram (ECG) signals based on the novel adaptive Fourier decomposition (AFD). AFD is a recently developed signal processing tool that provides useful morphological features, referred to as AFD-derived instantaneous frequency (IF) features, that are different from those provided by traditional tools. A support vector machine (SVM) classifier is trained with the AFD-derived IF features, ECG landmark features, and RR interval features. To evaluate the performance of the trained classifier, the Association for the Advancement of Medical Instrumentation (AAMI) standard is applied to the publicly available benchmark databases, including MIT-BIH arrhythmia database and MIT-BIH supraventricular arrhythmia database, to classify heartbeats from single-lead ECG. The overall performance in terms of sensitivities and positive predictive values is comparable to the state-of-the-art automatic heartbeat classification algorithms based on two-leads ECG.

Recommendations

• A new ECG signal classification based on WPD and ApEn feature extraction
• A feasible arrhythmia classification algorithm based on transformer model
• A method for ECG classification using deep learning and fuzzy C-means
• Frequency-domain features for ECG beat discrimination using grey relational analysis-based classifier
• Comparison of support-vector machine and sparse representation using a modified rule-based method for automated myocardial ischemia detection

Cites work

• A survey of uncertainty principles and some signal processing applications
• Adaptive Fourier decomposition-based Dirac type time-frequency distribution
• Adaptive Fourier series---a variation of greedy algorithm
• Carrier frequencies, holomorphy, and unwinding
• FFT formulations of adaptive Fourier decomposition
• scientific article; zbMATH DE number 823069 (Why is no real title available?)
• Nonlinear phase unwinding of functions
• Transient time-frequency distribution based on mono-component decompositions

Cited in

(5)

• Frequency-domain features for ECG beat discrimination using grey relational analysis-based classifier
• A new ECG signal classification based on WPD and ApEn feature extraction
• A method for ECG classification using deep learning and fuzzy C-means
• A feasible arrhythmia classification algorithm based on transformer model
• Unsupervised semantic-aware adaptive feature fusion network for arrhythmia detection

Describes a project that uses

Uses Software

• PhysioToolkit
• LIBSVM

This page was built for publication: A novel feature representation approach for single-lead heartbeat classification based on adaptive Fourier decomposition

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5022934)