Construction of Fuzzy System for Classification of Heart Disease Based on Phonocardiogram Signal

Abstract

Heart disease (cardiovascular disease) is any condition that causes interference with the heart. This study aims to determine the classification of heart disease based on phonocardiogram signals using the fuzzy system. The data used are the heart sound recordings from patients with normal hearts and cardiovascular abnormalities, which were recorded using a phonocardiogram device. The signal extraction process was carried out using wavelet decomposition mother Haar to produce features as input variables. While the output produced is a classification for heart conditions (normal or abnormal). Furthermore, the singular value decomposition method was utilized to determine the consequence parameters of the first-order Takagi-Sugeno-Kang (TSK) fuzzy rule. Fuzzy C-Means Clustering (FCM) was also used to optimize the number of fuzzy rules. As for the defuzzification process, the weight average method was used. The results showed that the accuracy and specificity of the training and testing data are better compared to the Mamdani and the radial basis function neural network (RBFNN) methods.