Wavelet transform-based QRS complex detector

In this paper, the authors describe a QRS complex detector based on the dyadic wavelet transform (D _yWT) which is robust to time-varying QRS complex morphology and to noise. They design a spline wavelet that is suitable for QRS detection. The scales of this wavelet are chosen based on the spectral characteristics of the electrocardiogram (ECG) signal. They illustrate the performance of the D _yWT-based QRS detector by considering problematic ECG signals from the American Heart Association (AHA) database. Seventy hours of data was considered. The authors also compare the performance of D _yWT-based QRS detector with detectors based on Okada, Hamilton-Tompkins, and multiplication of the backward difference algorithms. From the comparison, results the authors observed that although no one algorithm exhibited superior performance in all situations, the D _yWT-based detector compared well with the standard techniques. For multiform premature ventricular contractions, bigeminy, and couplets tapes, the D _yWT-based detector exhibited excellent performance.