No abstract

The aim of the paper is to study the possibility of advancing noised non-Gaussian processes recognition using the features based on higher-order statistics. Several new recognition features based on the higher-order statistics, the basis of advancing recognition results in the presence of noise, decision rules and recognition system frameworks we proposed in the paper. The efficiency test of the proposed method is performed by statistical modeling. We proposed features of recognition based on the third-order statistics.

No abstract

New linear prediction polymodels is described in the article. The structure of the universal linear prediction model is shown. We propose new additive linear prediction model АR 1 (2)+АR 2 (2). We also obtain spectral characteristics of additive processes and a system of equations for calculation of the additive model's parameters. Сomparative analysis of resolution capability is made using four methods of statistical modeling.

The higher orders spectra analysis for non-Gaussian process spectrum estimation in the mix with Gaussian correlated interference are studied in the paper. The received expressions for parametric spectral estimation of higher orders are used for non-Gaussian processes spectra estimation that can be described by generic autoregressive models. The comparative analysis of the received parametric spectral third order estimations with similar estimations calculated using known methods based on Fourier transform was made.