Adaptive R-peak Detection Using Empirical Mode Decomposition

Christina Kozia, Randa Herzallah, David Lowe

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Accurate QRS detection plays a pivotal role in the diagnosis of heart diseases and the estimation of heart rate variability and respiration rate. The investigation of R-peak detection is a continuing concern in computer-based ECG analysis because current methods are still inaccurate and miss heart beats. This paper presents a different algorithm to the state-of-the-art Empirical Mode Decomposition based algorithms for R-peak detection. Although our algorithm is based on Empirical Mode Decomposition, it uses an adaptive threshold over a sliding window combined with a gradient-based and refractory period
checks to differentiate large Q peaks and reject false R peaks. The performance
of the algorithm was tested on multiple databases including the MIT-BIH Arrhythmia database, Preterm Infant Cardio-Respiratory
Signals database and the Capnobase dataset, achieving a detection rate over 99%. Our modified approach outperforms other published results using Hilbert or derivative-based methods on common databases.
Original languageEnglish
Title of host publicationTime Series Analysis and Forecasting
Subtitle of host publication International Conference on Time Series and Forecasting, ITISE 2018
PublisherSpringer
Number of pages12
Publication statusAccepted/In press - 31 Jul 2018
EventInternational Conference on Time Series and Forecasting, ITISE 2018 - Granada, Spain
Duration: 19 Sep 201821 Sep 2018

Conference

ConferenceInternational Conference on Time Series and Forecasting, ITISE 2018
CountrySpain
CityGranada
Period19/09/1821/09/18

Fingerprint

Decomposition
Electrocardiography
Refractory materials
Derivatives

Cite this

Kozia, C., Herzallah, R., & Lowe, D. (Accepted/In press). Adaptive R-peak Detection Using Empirical Mode Decomposition. In Time Series Analysis and Forecasting : International Conference on Time Series and Forecasting, ITISE 2018 Springer.
Kozia, Christina ; Herzallah, Randa ; Lowe, David. / Adaptive R-peak Detection Using Empirical Mode Decomposition. Time Series Analysis and Forecasting : International Conference on Time Series and Forecasting, ITISE 2018. Springer, 2018.
@inproceedings{7911f5d115ff4f2b9f08cc5d3a9e78bc,
title = "Adaptive R-peak Detection Using Empirical Mode Decomposition",
abstract = "Accurate QRS detection plays a pivotal role in the diagnosis of heart diseases and the estimation of heart rate variability and respiration rate. The investigation of R-peak detection is a continuing concern in computer-based ECG analysis because current methods are still inaccurate and miss heart beats. This paper presents a different algorithm to the state-of-the-art Empirical Mode Decomposition based algorithms for R-peak detection. Although our algorithm is based on Empirical Mode Decomposition, it uses an adaptive threshold over a sliding window combined with a gradient-based and refractory periodchecks to differentiate large Q peaks and reject false R peaks. The performanceof the algorithm was tested on multiple databases including the MIT-BIH Arrhythmia database, Preterm Infant Cardio-RespiratorySignals database and the Capnobase dataset, achieving a detection rate over 99{\%}. Our modified approach outperforms other published results using Hilbert or derivative-based methods on common databases.",
author = "Christina Kozia and Randa Herzallah and David Lowe",
year = "2018",
month = "7",
day = "31",
language = "English",
booktitle = "Time Series Analysis and Forecasting",
publisher = "Springer",
address = "Germany",

}

Kozia, C, Herzallah, R & Lowe, D 2018, Adaptive R-peak Detection Using Empirical Mode Decomposition. in Time Series Analysis and Forecasting : International Conference on Time Series and Forecasting, ITISE 2018. Springer, International Conference on Time Series and Forecasting, ITISE 2018, Granada, Spain, 19/09/18.

Adaptive R-peak Detection Using Empirical Mode Decomposition. / Kozia, Christina; Herzallah, Randa; Lowe, David.

Time Series Analysis and Forecasting : International Conference on Time Series and Forecasting, ITISE 2018. Springer, 2018.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Adaptive R-peak Detection Using Empirical Mode Decomposition

AU - Kozia, Christina

AU - Herzallah, Randa

AU - Lowe, David

PY - 2018/7/31

Y1 - 2018/7/31

N2 - Accurate QRS detection plays a pivotal role in the diagnosis of heart diseases and the estimation of heart rate variability and respiration rate. The investigation of R-peak detection is a continuing concern in computer-based ECG analysis because current methods are still inaccurate and miss heart beats. This paper presents a different algorithm to the state-of-the-art Empirical Mode Decomposition based algorithms for R-peak detection. Although our algorithm is based on Empirical Mode Decomposition, it uses an adaptive threshold over a sliding window combined with a gradient-based and refractory periodchecks to differentiate large Q peaks and reject false R peaks. The performanceof the algorithm was tested on multiple databases including the MIT-BIH Arrhythmia database, Preterm Infant Cardio-RespiratorySignals database and the Capnobase dataset, achieving a detection rate over 99%. Our modified approach outperforms other published results using Hilbert or derivative-based methods on common databases.

AB - Accurate QRS detection plays a pivotal role in the diagnosis of heart diseases and the estimation of heart rate variability and respiration rate. The investigation of R-peak detection is a continuing concern in computer-based ECG analysis because current methods are still inaccurate and miss heart beats. This paper presents a different algorithm to the state-of-the-art Empirical Mode Decomposition based algorithms for R-peak detection. Although our algorithm is based on Empirical Mode Decomposition, it uses an adaptive threshold over a sliding window combined with a gradient-based and refractory periodchecks to differentiate large Q peaks and reject false R peaks. The performanceof the algorithm was tested on multiple databases including the MIT-BIH Arrhythmia database, Preterm Infant Cardio-RespiratorySignals database and the Capnobase dataset, achieving a detection rate over 99%. Our modified approach outperforms other published results using Hilbert or derivative-based methods on common databases.

M3 - Conference contribution

BT - Time Series Analysis and Forecasting

PB - Springer

ER -

Kozia C, Herzallah R, Lowe D. Adaptive R-peak Detection Using Empirical Mode Decomposition. In Time Series Analysis and Forecasting : International Conference on Time Series and Forecasting, ITISE 2018. Springer. 2018