Open AccessDelineation of electrocardiogram morphologies by using discrete wavelet transforms
Author(s) -
Annisa Darmawahyuni,
Siti Nurmaini,
Hanif Habibie Supriansyah,
Muhammad Irham Rizki Fauzi,
Muhammad Naufal Rachmatullah,
Firdaus Firdaus,
Bambang Tutuko
Publication year - 2021
Publication title -
indonesian journal of electrical engineering and computer science
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.241
H-Index - 17
eISSN - 2502-4760
pISSN - 2502-4752
DOI - 10.11591/ijeecs.v22.i1.pp159-167
Subject(s) - qrs complex , discrete wavelet transform , pattern recognition (psychology) , offset (computer science) , wavelet , t wave , mathematics , standard deviation , amplitude , wavelet transform , artificial intelligence , computer science , algorithm , statistics , electrocardiography , physics , cardiology , medicine , optics , programming language
The accuracy of electrocardiogram (ECG) delineation can affect the precise diagnose for cardiac disorders interpretation. Some nonideal ECG presentation can make a false decision in precision medicine. Besides, the physiological variation of heart rate and different characteristics of the different ECG waves in terms of shape, frequency, amplitude, and duration is also affected. This paper proposes a discrete wavelet transform (DWT), non-stationary signal analysis for noise removal, and onset-offset of PQRST feature extraction. A well-known database from Physionet: QT database (QTDB) is used to validate the DWT function for detecting the onset and offset of P-wave, QRS-complex, and T-wave localization. From the results, P-peak detection gets the highest result that achieves 2.19 and 13.62 milliseconds of mean error and standard deviation, respectively. In contrast, Toff has obtained the highest error value due to differences in the T-wave morphology. It can be affected by inverted o r biphasic T-waves and others.