Archives of Acoustics, 33, 4(S), pp. 85–90, 2008

Ship’s Hydroacoustics Signatures Classification

Andrzej ŻAK

The paper presents the technique of artificial neural networks used as classifier of hydroacoustics signatures generated by moving ship. The main task of proposed solution is to classify the objects which made the underwater noises. During the complex ships’ measurements on Polish Navy Test and Evaluation Acoustic Range hydroacoustics noises generated by moving ship were acquired. Basing on these results the classifier of coustic signatures using Kohonen neural network was worked out. To check the correctness of the classifier performance the research in which the number of right classification for presented and not presented before hydroacoustics signatures were made. Some results of research were presented in this paper.
Keywords: self-organizing map, Kohonen’s neural networks, hydroacousitcs signatures, classification
Full Text: PDF
Copyright © Polish Academy of Sciences & Institute of Fundamental Technological Research (IPPT PAN).