No abstract

No abstract

No abstract

Abstract. The article discusses the method for the classification of non-moving group objects for information received from unmanned aerial vehicles (UAVs) by synthetic aperture radar (SAR). A theoretical approach to analysis of group objects can be estimated by cross-entropy using a naive Bayesian classifier. The entropy of target spots on SAR images revaluates depending on the altitude and aspect angle of a UAV. The paper shows that classification of the target for three classes able to predict with fair accuracy P=0,964 based on an artificial neural network. The study of results reveals an advantage compared with other radar recognition methods for a criterion of the constant false-alarm rate (PCFAR<0.01). The reliability was confirmed by checking the initial data using principal component analysis.

The estimation of the feature space in analysis of radar signals (airplanes, ships, navigation stations, etc.), is an important element of machine learning. From the point of view of queuing theory, a mathematical model of a complex detected signal can be represented as the ordinary flow of events described by a Poisson distribution for randomly varying parameters of a signal. The paper demonstrates the orthogonality of the characteristic space of radar sources based on the entropy estimation. We show that the information measure of the discrepancy (Kullback-Leibler divergence) between intra-pulse modulation signals and frequency-modulated signals decreases with increasing pulse duration. Thus, in the recognition of radar sources using methods of machine learning, it is possible to limit ourselves to features without algorithms for processing intra-pulse modulation. Key words: radar source, queuing theory, Kullback-Leibler divergence, machine learning.