Novel logarithmic ECG feature extraction algorithm based on pan and tompkins

Muna Darweesh, Temesghen Habte, Hani Saleh, Baker Mohammad, Mohammed Ismail

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

4 Scopus citations

Abstract

ECG signal is an important tool to analyze the heart operation and detect many cardiac diseases. In this paper an improved Pan and Tompkins algorithm in the log2 domain is proposed. The proposed algorithm successfully detects the QRS complex and significantly reduces noise in the ECG signal. An average sensitivity of 99.68% and predictivity of 100% was obtained using the proposed algorithm. Many normal sinus rhythm ECG signals from the Physionet MIT-BIH database were used to validate the accuracy of the proposed algorithm. The algorithm was also used to measure the average heart rate using the R-R interval, an average error of 1.05% was obtained when compared the measured heart rate with the annotated data. Due to the inherent benefits of simplifying multiplication and division calculations in the log domain, the proposed algorithm provides many benefits over traditional Pan and Tompkins when it comes to hardware realization and a low-power ASIC implementation.

Original languageBritish English
Title of host publication2016 IEEE 59th International Midwest Symposium on Circuits and Systems, MWSCAS 2016
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781509009169
DOIs
StatePublished - 2 Jul 2016
Event59th IEEE International Midwest Symposium on Circuits and Systems, MWSCAS 2016 - Abu Dhabi, United Arab Emirates
Duration: 16 Oct 201619 Oct 2016

Publication series

NameMidwest Symposium on Circuits and Systems
Volume0
ISSN (Print)1548-3746

Conference

Conference59th IEEE International Midwest Symposium on Circuits and Systems, MWSCAS 2016
Country/TerritoryUnited Arab Emirates
CityAbu Dhabi
Period16/10/1619/10/16

Keywords

  • Accuracy
  • Application specific integrated circuit (ASIC)
  • ECG signal
  • Log domain
  • Pan and tompkins
  • QRS complex

Fingerprint

Dive into the research topics of 'Novel logarithmic ECG feature extraction algorithm based on pan and tompkins'. Together they form a unique fingerprint.

Cite this