A machine learning approach to objective cardiac event detection

N. Twomey*, P. A. Flach

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference Contribution (Conference Proceeding)

1 Citation (Scopus)
246 Downloads (Pure)

Abstract

This paper presents an automated framework for the detection of the QRS complex from Electrocardiogram (ECG) signals. We introduce an artefact-tolerant pre-processing algorithm which emphasises a number of characteristics of the ECG that are representative of the QRS complex. With this processed ECG signal we train Logistic Regression and Support Vector Machine classification models. With our approach we obtain over 99.7% detection sensitivity and precision on the MIT-BIH database without using supplementary de-noising or pre-emphasis filters.

Original languageEnglish
Title of host publication2014 8th International Conference on Complex, Intelligent and Software Intensive Systems, CISIS 2014
PublisherInstitute of Electrical and Electronics Engineers (IEEE)
Pages519-524
Number of pages6
ISBN (Print)9781479943258
DOIs
Publication statusPublished - 1 Jan 2014
Event2014 8th International Conference on Complex, Intelligent and Software Intensive Systems, CISIS 2014 - Birmingham, United Kingdom
Duration: 2 Jul 20144 Jul 2014

Conference

Conference2014 8th International Conference on Complex, Intelligent and Software Intensive Systems, CISIS 2014
CountryUnited Kingdom
CityBirmingham
Period2/07/144/07/14

Structured keywords

  • Jean Golding

Keywords

  • Pattern recognition
  • QRS detection

Fingerprint Dive into the research topics of 'A machine learning approach to objective cardiac event detection'. Together they form a unique fingerprint.

Cite this