Classification of marine objects by discrete part of power spectral density of noise detection signals

There is a problem of providing the required probability of correct classification of marine objects using classification signs, defined by power spectral density of noise detection signals. The problem can be solved by using power spectral density of noise detection signals as a classification sign. In present paper a solution to the problem of classification of marine objects by discrete part of power spectral density of noise detection signals using statistical methods and polygaussian probabilistic models is discussed.