BULETINUL INSTITUTULUI POLITEHNIC DIN IAŞI Publicat de Universitatea Tehnică „Gheorghe Asachi” din Iaşi Volumul 65 (69), Numărul 1, 2019 Secţia ELECTROTEHNICĂ. ENERGETICĂ. ELECTRONICĂ WAVELET FAMILIES COMPARISON FOR R-PEAKS DETECTION IN ELECTROCARDIOGRAM SIGNAL BY SAMIA BELKACEM 1,* , NOUREDDINE MESSAOUDI 1 and ZOHIR DIBI 2 1 University of Boumerdes. Boumerdes, Algeria, Faculty of Engineering Sciences, Department of Electrical Systems Engineering, 2 University of Batna 2. Batna, Algeria, Faculty of Technology, Department of Electronics Received: December 27, 2018 Accepted for publication: February 15, 2019 Abstract. A detection of R-peaks in electrocardiogram signal (ECG) based on modified threshold in wavelet transform domain is presented. In this paper, the threshold determination is based on segmentation approach and with help of different wavelet families. However, the decision about the possible R-peaks is done by using the physiological heart parameters. Our method has been applied to MIT-BIH arrhythmia database to show its practical efficiency in terms of sensitivity, median, mean and standard deviation values. A comparative study is done between the results of our proposed algorithm based on modified threshold with different wavelets combinations, and the work based only on Daubechies wavelet with simple threshold. The survey showed that the combination of Daubechies wavelet mother gives with Symlet, Coiflet and Biorthogonal wavelets mother the best results. Keywords: threshold; BW artifact; sensitivity; median; standard deviation. 1. Introduction The body can be considered as a chemical and electrical system supported by a mechanical structure. Measuring and quantifying such electrical * Corresponding author: e-mail: s.belkacem@univ-boumerdes.dz