HYDROACOUSTICS
ANNUAL JOURNAL |
START | NEW VOL 20 | SEARCH | STATISTICS | PAS - GDANSK DIVISION |
pp. 161-166, vol. 2, 1999 P. SoszyĆski Polish Naval Academy, Gdynia, Poland Maritime University of Szczecin, Gdynia, Poland A. Stateczny Polish Naval Academy, Gdynia, Poland Maritime University of Szczecin, Gdynia, Poland Key words: Abstract: An algorithm for detection/identification of underwater objects is proposed. The algorithm is based upon the classification ability of a simple multi-layer neural network, also called a Perceptron. A signal recorded by a hydrophone and preprocessed by a computer is supplied to the ANN, which classifies it according to the possessed information encoded within its structure and an array of weighs. Analysis of effectiveness is conducted depending on the variables pertaining to the neural network.
Download: Fulltext PDF, BibTeX © Polish Acoustical Society - Gdansk Department, Polish Academy of Sciences. This work is licensed under the Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported. (CC BY-NC-SA 3.0) |