QRS Complex Detection in ECG Signals Using Empirical Wavelet Transform and Flower Pollination Algorithm

Abstract

The QRS complex is the most important component of electrocardiogram (ECG) signals; therefore, its detection is the first step of all kinds of automatic feature extraction and crucial part of an ECG analysis system. The R wave is one of the most important sections of the QRS complex, which has an essential role in diagnosis of irregular heartbeats. This paper employs Empirical Wavelet Transform (EWT) and Hilbert transforms as well as by employing Flower Pollination Algorithm (FPA) in order to approach an optimum combinational method for R peak detection. First, the Empirical Wavelet Transform (EWT) is used to eliminate the noise and improve the envelope extraction. The Hilbert envelope is then used to determine the positions of the R waves. Finally, FPA is used to adjust the envelope’s parameters. In the experimental section of this paper, the proposed approach is evaluated using the MIT/BIH database. We show that the proposed method can achieve results that are comparable to the state-of-the-art, with a global sensitivity of 99.95%, a positive predectivity of 99.92%, and a percentage error of 0.136%.