Wavelet and teager energy operator (TEO) for heart sound processing and identification

Abstract

The heart sound signal (heartbeat) recorded from normal subjects usually contains two separate tones, S1 and S2. In addition, an auscultation technique used to provide physicians with accurate and objective interpretation of heart sounds can be used to detect four sounds, namely, S1, S2, S3, and S4, during the heart cycle. In this project, we propose a technique to detect these four heartbeats effectively using the combination of multi-scale wavelet transform and Teager Energy Operator to increase the precision of the detection process. The purpose of combining TEO with Wavelets is to observe how different details obtained from the Wavelet Transform influence the Teager Operator success in detecting S1, S2, S3, and S4 heart sounds. The effectiveness of the proposed approach is evaluated in experiments related to different cardiac conditions, achieving 88 % accuracy for localization of S1 and S2, and 86 % accuracy for S3 and/or S4.