الفهرس Only 14 pages are availabe for public view
 |  | from | 85 |  |  |
| | | from | 85 | | |
Abstract
Heart sounds contain useful information that can help in early diagnosis of heart disease. The analysis of such signals involves many directions for researchers in this field and still an active research point for many groups. In this work, we present a new processing and classification systems for heart sounds. An optimized processing systems that includes preprocessing using spectral subtraction denoising, feature extraction, feature reduction and classification is presented. We address the problem of feature extraction from heart sounds and introduce a new technique to convert the time series representation of heart sound signal into time-frequency heat map representation based on fractional Fourier transform based Mel-frequency spectral coefficients. Such representation is then classified using a stacked sparse autoencoder deep neural network, support vector machines (using linear, quadratic, cubic, and Gaussian kernels), k-nearest neighbor (using linear, cosine, cubic, and weighted distance metrics) and ensemble classification (bagged Trees, subspace KNN and RUSBoosted tree). The proposed system is experimentally verified on the heart sounds database. The cross-validation and local hold out train-test methods are used to perform the experiments and obtain the results and compare them using the sensitivity, the specificity and the accuracy measures. The proposed system showed potential for achieving excellent performance compared to previous methods