This article is devoted to the problem of information security in complexes with unmanned aerial vehicles (UAV). Science knows a new promising method of information protection: moving target defense (MTD). The essence of this method is that due to periodic changes in the parameters of the infocommunication network the information about the information infrastructure collected by the attacker at the reconnaissance stage becomes irrelevant, and the attack becomes ineffective. This article also discusses the features and types of confidential information processed in complexes with UAV and provides a review of the experience of creating systems for protecting information from unauthorized access of complexes with UAV. The proposed hypothesis is tested using a model created using a tool: the GNS3 program. The model in the form of a test network in the GNS3 emulator recreates the proposed method. It was concluded that the effectiveness of the harmful impact on the complex with UAV was reduced by three times. The disadvantages of the proposed method include the problem of ensuring the availability of protected information resources for other legitimate, authorized participants in network interaction, as well as the need to solve the problem of choosing the optimal frequency of changing parameters.

This article presents the constraining factors that limit the increase in the efficiency of logging production by modern multi-operation machines operating on the Scandinavian cut-to-length technology in the felling phase, namely the selection and registration of wood species. The factors for creating a complete architecture of a fully connected neural network (NN) are given. The dependence of the prediction accuracy of a fully connected NN on a test sample on the size of the training dataset, and an image of the dependence of the prediction accuracy on the number of trees in the random forest method for image classification is shown. For a fully connected NN, a sufficient number of images and a test sample size were established for training, using tree-trunk breed-class labels as target values. A selected list of trees was given, with the size of the training sample of images presenting a problem for the classification of tree trunks using the random forest method. The aim was the discovery of the optimal number of trees necessary to achieve prediction accuracy.