CLASSIFICATION OF SIGNALS WITH DIGITAL PARAMETER MODULATION USING SG-STATISTICS

The paper deals with the classification of signals with amplitude and phase manipulation of their parameters when observed against the background of additive Gaussian noise. It is shown that the use of non-parametric SG-statistics as an index of predictability allows for the classification of signals and their distinction within each class. A scale of signals according to their predictability index is proposed, which ranks signals according to their complexity. Keywords: predictability index, signal classification, amplitude and phase modulation.