Zichun Tong

Date of Award


Degree Name

Master of Science in Engineering


Electrical and Computer Engineering

First Advisor

Dr. Ikhlas Abdel-Qader

Second Advisor

Dr. Raghe Gejji

Third Advisor

Dr. Azim Houshyar


Cardiac sounds, phonocardiogram, wavelet, Hilbert-Huang transform, Support Vector Machine

Access Setting

Masters Thesis-Open Access


The Phonocardiogram (PCG) signal contains valuable information about the cardiac condition and is a useful tool in recognizing dysfunction and heart failure. By analyzing the PCG, early detection and diagnosis of heart diseases can be accomplished since many pathological conditions of the cardiovascular system cause murmurs or abnormal heart sounds. This thesis presents an algorithm to classify normal and abnormal heart sound signals using PCG. The proposed analysis is based on a framework composed of several statistical signal analysis techniques such as wavelet based de-noising, energy-based segmentation, Hilbert-Huang transform based feature extraction, and Support Vector Machine based classification. The MATLAB test results using PCG recordings validate the model used in the proposed system with very high classification accuracy averaged at 90.5%.