Detection of septal defects from cardiac sound signals using tunable-Q wavelet transform

Abstract

In this paper, we present a new method for detection of septal defects from cardiac sound signals using tunable-Q wavelet transform (TQWT). To begin with, the cardiac sound signals have been segmented into heart beat cycles using constrained TQWT based approach. In order to extract the timefrequency domain based features, TQWT based decomposition of heart beat cycles has been performed up to sixth stage. The murmurs have more fluctuations than heart sounds. Therefore, to characterize murmurs in cardiac sound signals, proposed feature set was formed with fluctuation indices that have been computed from reconstruction of decomposed sub-bands. Then, this feature set containing twenty one features has been used to classify cardiac sound signals for detection of septal defects. In order to validate the usefulness of the proposed method for diagnosis of septal defects, besides cardiac sound signals for septal defects and normal, this study also considers signals to be detected for valvular defects and other defects like ventricular hypertrophy, constrictive pericarditis etc. The classification has been performed using least squares support vector machine (LS-SVM) with radial basis (RBF) kernel function. In order to tune the quality-factor (Q) of the TQWT to provide highest classification accuracy, the experiment has been conducted with varying value of Q. The experimental results show that the proposed method has provided significant classification performance at Q = 2 for various clinical cases as comprised in the publicly available datasets. The test results demonstrate classification accuracy of 91.75% with sensitivity of 88.23% and specificity of 96.48% at Q = 2.

Exploiting Feature Selection and Neural Network Techniques for Identification of Focal and Nonfocal EEG Signals in TQWT Domain

“…e motivation stems from the successful deployment of TQWT in other biomedical signal processing applications such as detecting epileptic seizures [34,[43][44][45][46][47][48][49] and alcoholism [50] by EEG signals, detecting coronary artery disease [51] by heart rate variability (HRV) signals, heart valve [52,53] and septal defects disorders [54,55], aortic and mitral disorders [56,57] by cardiac sound signals [58], detecting hand movements [59] and amyotrophic lateral sclerosis (ALS) disorder [60] by electromyogram (EMG) signals, and sleep apnea [61] by electrocardiogram (ECG) signals that indicate the ability of TQWT in biosignal processing application.…”