Implementation of adaptive processing schemes in active and passive sonar systems

1996 ◽  
Vol 100 (4) ◽  
pp. 2853-2853
Author(s):  
Stergios Stergiopoulos
1975 ◽  
Author(s):  
R. J. Hornick ◽  
G. Yamashita ◽  
J. E. Robinson ◽  
H. J. Winkler

1991 ◽  
Vol 16 (3) ◽  
pp. 267-278 ◽  
Author(s):  
C. Ferla ◽  
M.B. Porter

Author(s):  
O.A. Andreev ◽  
A.T. Trofimov

The paper addresses the issue of insuring the required probability of correct classification of marine objects in low-frequency passive sonar systems. The solution to the issue is sought through the application of methods for the synthesis of neural network classification algorithms using poly-Gaussian probabilistic models (Gaussian mixture models, GMM). It is shown that the use of GMM makes it possible to solve a number of problems specific to the issue; classification algorithms synthesized using mentioned methods can be implemented in the form of neural networks, which in turn can be described in C++/VHDL to create endpoint computing devices or software systems. The results of modeling of synthesized classification algorithms on experimental data are presented; it is demonstrated that such algorithms make it possible to increase the probability of correct classification of marine objects and to satisfy typical requirements for classification systems in low-frequency passive sonar systems.


Sign in / Sign up

Export Citation Format

Share Document