QRS detection combining entropic criterion and wavelet transform

Abstract

In this paper, we introduce a new method for QRS wave's locations using the local entropic criterion applied to the signal split on different successive scales, based on the G. Gonon and M. Djafari approach, which offers a local estimator for segmenting of a signal based on entropic criteria, and on the work of Mallat and Hwang for singularity detection using local maxima of coefficients wavelet resulting from the decomposition of a signal. The R wave corresponds to two modulus maximum lines with opposite signs (min-max). We evaluated the algorithm on manually annotated databases QT.