Selection of a suitable mother wavelet for microemboli classification using SVM and RF signals

Fourier transform (FT) based techniques have been traditionally used for microemboli classification. We suggest in this study exploiting the Radio-Frequency (RF) signal backscattered by the emboli since they contain additional information on the embolus than the Doppler signal. A recent alternative approach of Wavelet Transform is applied for this purpose. The performances of such classification system are highly dependent upon the selection of an appropriate wavelet mother. Many mother wavelets have been used for this analysis such as Biorthogonal, Coiflet, Daubechies, and Symlet. This experimental study describes a strategy to choose a suitable mother wavelet for microemboli classification using SVM and RF signals.