Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

Modeling of Noisy Acceleration Signals From Quasi-Periodic Movements for Drift-Free Position Estimation.

IEEE journal of biomedical and health informatics·2018

Same author

A low-rank matrix factorization approach for joint harmonic and baseline noise suppression in biopotential signals.

Computer methods and programs in biomedicine·2017

Same author

Wavelet-based unsupervised learning method for electrocardiogram suppression in surface electromyograms.

Medical engineering & physics·2016

Same author

Unsupervised learning technique for surface electromyogram denoising from power line interference and baseline wander.

Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference·2016

Same author

Simultaneous powerline interference and baseline wander removal from ECG and EMG signals by sinusoidal modeling.

Medical engineering & physics·2013

Same author

Nonstationary harmonic modeling for ECG removal in surface EMG signals.

IEEE transactions on bio-medical engineering·2012

Search research articles

Related Experiment Video

Updated: Apr 18, 2026

Simultaneous Scalp Electroencephalography EEG, Electromyography EMG, and Whole-body Segmental Inertial Recording for Multi-modal Neural Decoding

Simultaneous Scalp Electroencephalography EEG, Electromyography EMG, and Whole-body Segmental Inertial Recording for Multi-modal Neural Decoding

Published on: July 26, 2013

ECG-EMG separation by using enhanced non-negative matrix factorization.

Maciej Niegowski, Miroslav Zivanovic

Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference

|January 9, 2015

Summary

This study introduces an enhanced non-negative matrix factorization (NMF) method for separating electrocardiogram (ECG) and electromyogram (EMG) signals. The novel approach significantly improves signal separation accuracy in mixed recordings.

More Related Videos

Extraction of the EPP Component from the Surface EMG

Extraction of the EPP Component from the Surface EMG

Published on: December 16, 2009

Acquisition and Semi-Automated Analysis of Respiratory Muscle Surface Electromyography

Acquisition and Semi-Automated Analysis of Respiratory Muscle Surface Electromyography

Published on: January 24, 2025

Related Experiment Videos

Last Updated: Apr 18, 2026

Simultaneous Scalp Electroencephalography EEG, Electromyography EMG, and Whole-body Segmental Inertial Recording for Multi-modal Neural Decoding

Simultaneous Scalp Electroencephalography EEG, Electromyography EMG, and Whole-body Segmental Inertial Recording for Multi-modal Neural Decoding

Published on: July 26, 2013

Extraction of the EPP Component from the Surface EMG

Extraction of the EPP Component from the Surface EMG

Published on: December 16, 2009

Acquisition and Semi-Automated Analysis of Respiratory Muscle Surface Electromyography

Acquisition and Semi-Automated Analysis of Respiratory Muscle Surface Electromyography

Published on: January 24, 2025

Area of Science:

Biomedical Engineering
Signal Processing
Machine Learning

Background:

Electrocardiogram (ECG) and electromyogram (EMG) signals are crucial for diagnosing cardiac and neuromuscular conditions, respectively.
Separating single-channel ECG and EMG signals is challenging due to their overlapping spectral characteristics.
Existing methods often struggle with accurate separation, particularly in complex real-world scenarios.

Purpose of the Study:

To develop and validate a novel enhanced non-negative matrix factorization (NMF) approach for improved single-channel ECG-EMG signal separation.
To leverage distinct time-frequency (TF) patterns of ECG and EMG for enhanced decomposition.
To compare the proposed method against established techniques using both synthetic and real-world data.

Main Methods:

A linear decomposition of the input signal spectrogram into two non-negative components representing ECG and EMG spectrogram estimates.
Enhancement of the decomposition by reshaping the spectrogram to emphasize sparse ECG patterns over noisy EMG.
Initialization of the NMF algorithm with pre-defined ECG and EMG structures to improve separation performance.

Main Results:

The proposed enhanced NMF method demonstrated superior performance in separating ECG and EMG signals compared to two reference methods.
Effective separation was achieved in both synthetic signal mixtures and real-world recordings.
The time-frequency pattern emphasis and structural initialization significantly boosted separation accuracy.

Conclusions:

The developed enhanced NMF technique offers a robust and effective solution for single-channel ECG-EMG signal separation.
This method holds promise for improving the accuracy of diagnostic information extracted from physiological signals.
The approach provides a valuable tool for biomedical signal processing applications.