Ship recognition via its radiated sound: The fractal based approaches

Due to the complexity of its radiated sound, ship recognition is difficult. Fractal approaches are proposed in this study, including fractal Brownian motion based analysis, fractal dimension analysis, and wavelet analysis, to augment existing feature extraction methods that are based on spectrum analysis. Experimental results show that fractal approaches are effective. When used to augment two traditional features, line and average spectra, fractal approaches led to better classification results. This implies that fractal approaches can capture some information not detected by traditional approaches alone. (C) 2002 Acoustical Society of America.