A Theory for Multiresolution Signal Decomposition: The Wavelet Representation
IEEE Transactions on Pattern Analysis and Machine Intelligence
Wavelet applications in medicine
IEEE Spectrum
International Journal of Data Analysis Techniques and Strategies
Multi-level basis selection of wavelet packet decomposition tree for heart sound classification
Computers in Biology and Medicine
Hi-index | 12.05 |
The phonocardiogram signal (PCG) can be utilized more efficiently by medical doctors when they are displayed visually, rather through a conventional stethoscope. This signal provides clinician with valuable diagnostic and prognostic information. Although the PCG signal analysis by auscultation is convenient as clinical tool, heart sound signals are so complex and non-stationary that they have a great difficulty to analyze in time or frequency domain. We have studied the extraction of features out of heart sounds in time-frequency (TF) domain for recognition of heart sounds through TF analysis. This article highlights the importance of the choice of wavelet analyzing wavelet and its order in the phonocardiogram signal analysis using the two versions of the wavelet transform: the discrete wavelet transform (DWT) and the packet wavelet transform (PWT). This analysis is based on the application of a large number of orthogonal and bi-orthogonal wavelets and whenever you measure the value of the average difference (in absolute value) between the original signal and the synthesis signal obtained by multiresolution analysis (AM). The performance of the discrete wavelet transform (DWT) and the packet wavelet transform (PWT) in the PCG signal analysis are evaluated and discussed in this paper. The results we obtain show the clinical usefulness of our extraction methods for recognition of heart sounds (or PCG signal).