QRS detection using S-Transform and Shannon energy
| Autor: | Zahia Zidelmal, Alain Dieterlen, Ali Moukadem, Ahmed Amirou, D. Ould-Abdeslam |
|---|---|
| Přispěvatelé: | Université Mouloud Mammeri [Tizi Ouzou] (UMMTO), Modélisation, Intelligence, Processus et Système (MIPS), Ecole Nationale Supérieure d'Ingénieur Sud Alsace-Université de Haute-Alsace (UHA) Mulhouse - Colmar (Université de Haute-Alsace (UHA))-IUT de Colmar-IUT de Mulhouse |
| Rok vydání: | 2014 |
| Předmět: |
Shannon energy
Speech recognition Word error rate Health Informatics Sensitivity and Specificity Pattern Recognition Automated Electrocardiography QRS complex Time–frequency representation Heart Rate QRS detection Humans Diagnosis Computer-Assisted Sensitivity (control systems) Time domain S-Transform S transform Mathematics business.industry Resolution (electron density) Reproducibility of Results Arrhythmias Cardiac Signal Processing Computer-Assisted Pattern recognition Computer Science Applications Artificial intelligence business [SPI.SIGNAL]Engineering Sciences [physics]/Signal and Image processing Algorithms Software Energy (signal processing) |
| Zdroj: | Computer Methods and Programs in Biomedicine Computer Methods and Programs in Biomedicine, Elsevier, 2014, pp.1-9. ⟨10.1016/j.cmpb.2014.04.008⟩ |
| ISSN: | 0169-2607 |
| DOI: | 10.1016/j.cmpb.2014.04.008 |
| Popis: | International audience; This paper presents a novel method for QRS detection in electrocardiograms (ECG). It is basedon the S-Transform, a new time frequency representation (TFR). The S-Transform providesfrequency-dependent resolution while maintaining a direct relationship with the Fourierspectrum. We exploit the advantages of the S-Transform to isolate the QRS complexes in thetime–frequency domain. Shannon energy of each obtained local spectrum is then computedin order to localize the R waves in the time domain.Significant performance enhancement is confirmed when the proposed approach is testedwith the MIT-BIH arrhythmia database (MITDB). The obtained results show a sensitivityof 99.84%, a positive predictivity of 99.91% and an error rate of 0.25%. Furthermore, to bemore convincing, the authors illustrated the detection parameters in the case of certainECG segments with complicated patterns. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
Full Text from ScienceDirect