An Application of Fractional Brownian Motion to Vessel Identification Based on its Sound Spectrum
M. Wiciaka, I. Glozab, R. Jóźwiakb and P. Wiciakc
aCracow University of Technology, Institute of Mathematics, Warszawska 24, 31-155 Krakow, Poland
bPolish Naval Academy, Śmigowicza 69, 81-103 Gdynia, Poland
cAGH University of Science and Technology, Mickiewicza 30, 30-059 Krakow, Poland
Full Text PDF
The paper deals with the problem of vessel identification. The presented method is based on fractional Brownian analysis of vessel power spectrum. The measurements for three vessels were carried out with the use of a mobile measuring module in the Gulf of Gdansk; Next, the information obtained from sound spectra was identified. Two classifiers connected with fractional Brownian motion were used: the first-order increments and the standard deviation. Finally, classification decision was made using the Mahalanobis distance. Numerical experiments were performed using MATLAB.

DOI: 10.12693/APhysPolA.128.A-46
PACS numbers: 43.60.Lq