Robust R-Peak Detection in Low-Quality Holter ECGs Using 1D Convolutional Neural Network

  title={Robust R-Peak Detection in Low-Quality Holter ECGs Using 1D Convolutional Neural Network},
  author={Muhammad Uzair Zahid and Serkan Kiranyaz and Turker Ince and Ozer Can Devecioglu and Muhammad Enamul Hoque Chowdhury and Amith Khandakar and Anas M. Tahir and M. Gabbouj},
  journal={IEEE Transactions on Biomedical Engineering},
Objective: Noise and low quality of ECG signals acquired from Holter or wearable devices deteriorate the accuracy and robustness of R-peak detection algorithms. This paper presents a generic and robust system for R-peak detection in Holter ECG signals. While many proposed algorithms have successfully addressed the problem of ECG R-peak detection, there is still a notable gap in the performance of these detectors on such low-quality ECG records. Methods: In this study, a novel implementation of… 

Figures and Tables from this paper

COV-ECGNET: COVID-19 detection using ECG trace images with deep convolutional neural network

This is the first study that will explore the possibility of using deep convolutional neural network (CNN) models to detect COVID-19 from electrocardiogram (ECG) trace images and the proposed method uses ECG trace images which can be captured by smartphones and are readily available facilities in low-resources countries.

EDITH : ECG Biometrics Aided by Deep Learning for Reliable Individual Authentication

EDITH, a deep learning-based framework for ECG biometrics authentication system, is presented and the proposed Siamese architecture manages to reduce the identity verification Equal Error Rate (EER) to 1.29 %.

DSD-R: Deep Learning Based Segmentation for the Detection of R peaks in ECG Signals

This study aims to segmentation-based detection of R-peak locations in ECG signals by transforming the ECG signal into a Continuous Wavelet Transform based scalogram image, and U-Net-based deep learning architectures are utilized for the segmentation.

A Novel Exploitative and Explorative GWO-SVM Algorithm for Smart Emotion Recognition

This work demonstrates that the X-GWO-SVM algorithm can be used for emotion recognition and the algorithm exhibits superior performance in reliability compared to the use of other supervised machine learning methods in earlier works.

Global ECG Classification by Self-Operational Neural Networks With Feature Injection

This study has demonstrated that using a compact and superior network model, a global ECG classification can still be achieved with an elegant performance level even when no patient-specific information is used.


The obtained performance of the proposed R peak position determination system is very high and can be applied to determine the R peak of the ECG signal measuring devices in practice.

Robust R-peak detection in an electrocardiogram with stationary wavelet transformation and separable convolution

A novel deep learning model for R-peak detection using stationary wavelet transform (SWT) and separable convolution with atrous spatial pyramidal pooling and a high performance even for cross-database validations is developed.

Adaptive R-Peak Detector in Extreme Noise Using EMD Selective Analyzer

An adaptive approach is introduced, based on Empirical Mode Decomposition (EMD), to accurately detect the R-peaks in an extremely noisy ECG signal obtained using a single-arm measurement, showing a promising technique for detecting R- peaks in extreme noise.

A Stochastic Resonance Electrocardiogram Enhancement Algorithm for Robust QRS Detection

A new QRS detection algorithm making use of the background noise that is inevitably present in electrocardiogram (ECG) recordings, and demonstrates QRS-enhancement by facilitating stochastic resonance while suppressing in-band noise of ECG signals.



RPnet: A Deep Learning approach for robust R Peak detection in noisy ECG

A novel application of the Unet combined with Inception and Residual blocks is proposed to perform the extraction of R-peaks from an ECG, which is a substantial improvement over the other beat detectors.

Robust QRS Detection Using High-Resolution Wavelet Packet Decomposition and Time-Attention Convolutional Neural Network

A QRS detection method based on high-resolution wavelet packet decomposition (HR-WPD) and convolutional neural network (CNN) and a variable threshold is imposed to locate the QRS.

QRS Detection in ECG Signal Based on Residual Network

  • Xingjun WangQingyan Zou
  • Computer Science
    2019 IEEE 11th International Conference on Communication Software and Networks (ICCSN)
  • 2019
A powerful and accurate convolutional neural network model of QRS detection in electrocardiogram (ECG) based on one dimensional residual network that is more robust to noise and it's easier to implement.

Real-Time Patient-Specific ECG Classification by 1-D Convolutional Neural Networks

A fast and accurate patient-specific electrocardiogram (ECG) classification and monitoring system that achieves a superior classification performance than most of the state-of-the-art methods for the detection of ventricular ectopic beats and supraventricular ectopy beats.

Automatic QRS complex detection using two-level convolutional neural network

An automatic QRS detection method using two-level 1-D CNN and simple signal preprocessing technique is proposed for QRS complex detection, which acquires comparable accuracy with state-of-the-art approaches.

Robust ECG R-peak detection using LSTM

A new R-peak detection method that is based on the Long Short-Term Memory (LSTM) network, which outperforms traditional algorithms while the greatest competitive edge is achieved with the noisy ECG signals.

R Peak Detection in Electrocardiogram Signal Based on an Optimal Combination of Wavelet Transform, Hilbert Transform, and Adaptive Thresholding

By using wavelet and Hilbert transforms as well as by employing adaptive thresholding technique, an optimal combinational method for R peak detection namely WHAT is obtained that outperforms other techniques quantitatively and qualitatively.

Robust and fast heart rate variability analysis of long and noisy electrocardiograms using neural networks and images

The approach of encoding ECGs, tachograms and other cardiac time series in the form of raster images, which greatly speeds and eases their visual inspection and analysis.

ECG Signal Quality During Arrhythmia and Its Application to False Alarm Reduction

An automated algorithm to assess electrocardiogram (ECG) quality for both normal and abnormal rhythms is presented for false arrhythmia alarm suppression of intensive care unit (ICU) monitors and results suggest that the SQIs should be rhythm specific and that the classifier should be trained for each rhythm call independently.

R-peak detector stress test with a new noisy ECG database reveals significant performance differences amongst popular detectors

The results show that using an error margin with sample precision, common ECG R peak detection algorithms perform much worse than previously reported.