A method based on wavelet packets-fractal and SVM for underwater acoustic signals recognition

Underwater targets recognition was one of the important and difficult topics of underwater acoustic signal processing. It was of important to extract and analysis the nonlinear and chaotic feature of ship radiated noise and recognize underwater target. To solve underwater targets recognition problem, a method based on wavelet packets-fractal and Support Vector Machine (SVM) for underwater target recognition was studied. Wavelet packets-fractal was used to extract feature of ship radiated noise. The fractal box-counting dimensions of ship radiated noise were taken as new parameters, they could reflect the frequency component of signals. And SVM was used for multi-class classification. The experiment result showed that this method based on wavelet fractal and SVM for underwater target recognition had good classification rate.