HYDROACOUSTICS
ANNUAL JOURNAL
START NEW VOL 20 SEARCH STATISTICS PAS - GDANSK DIVISION

Methods of end-user classification of hydroacoustics signatures

pp. 207-213, vol. 15, 2012

Andrzej Zak
Polish Naval Academy, Gdynia, Poland

Key words: neural network; classification

Abstract: Paper presents problem of choosing methods which should be able to give end-user classification. Two methods are discussed in this paper. First of all the technique of neural networks is proposed to solve problem of und-user classification. The mathematical description of learning process as well as detail description of calculation process were presented. Secondly the fuzzy logic is proposed to solve end-user classification problem. The main processing blocks of fuzzy model as well as algorithms of calculation were in detail resented. At the end some results of using both methods as end-user classifiers based on results acquired in previous investigation were presented.

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)