In this paper, the actuality of utilization of informational technology in forestry is underlined. There is noted, that the technical and technological modernization within the frameworks of “Industry 4.0” for this sector is required. There are described methods, which give the potential to reduce forest machines' negative influence on the environment. There is emphasized, that the maximal damage to soils is inflicted by wheel propellers. There is proposed to use decision support systems (DSS) for the control process improvement and simplification on the territory, intended for cutting. There is given the system structure, main elements, and theirs principles of functioning are described. There are proposed some performance characteristics for the measurement of changes in consequence of the implementation of the depicted DSS, among them: response time on an incident from the moment of detection, situation analysis time, clearing time, and track depth, created by forest machine. There is made the simulation of an array of situations, stressing an efficiency of DSS use, such as: a) Can one reduce a soil purification time from oil products? b) Can one prevent an exceeding of the required track depth level? There is considered an impact of this DSS on existing indices of “Industry 4.0”. There are substantiated conclusions about the reasonability and efficiency of this DSS usage in forestry. There is noticed, that the DSS application to some extent allows preventing the erosion of forest soils, also to warn a diminishing of fertility, created by the irrational use and chemical pollution.

Approaches to task generation for various disciplines are discussed, mentioned that a parameter method cannot be applied to programming. The authors developed an application of the idea of a constructive-selective method for creating programming tasks. A task created for constructive-selective methodical contains a set of components, from which a student makes up his answer (a program). Application of this method allows diversifying of tasks in programming and creates a new way of assessment based on the content of the answer. It’s also allows to grade both fully and partially correct answers. The main concepts of the model for representing programming tasks are illustrated by examples. The domain-specific markup language and its translator that allows generating tasks from a teacher’s program source text are proposed. An example of a translator usage is given.

The task of semantic segmentation of 2D-tomographic scans of hydrate-containing rocks is a multi-class classification of pixels of each input image in a set according to the classes “Granule”, “Fluid”, “Hydrate”. Now this is implemented in the form of segmentation by the “Granule” class using the convolutional architecture of the U-Net neural network and classification of pixels unclassified as “Granule” into the “Fluid” and “Hydrate” classes by the threshold value of pixel intensity.

Considering the limited processing time of a large volume of tomographic data, it is necessary to find a compromise between the complexity of the model and the quality of segmentation. On the other hand, it is also required to propose a second, simpler implementation of the network, to extend it to a 3D segmentation model.

The solution of these optimization problems is achieved by tuning the hyperparameters of the U-Net model. To determine which set of network hyperparameters is the best in a particular case, a partial search was performed over the hyperparameter grid, limited by the variables responsible for:

1) the number of trained filters in convolution operations;

2) learning the biases vector for output channels from convolutional operations;

3) choosing an algorithm to increase the resolution in the network decoder part.

This article describes the process of finding optimal models and provides an assumption about the possibilities for their improvement.

This paper presents the result of designing the architecture of a neural network on bio-inspired neurons, whose task is to work out the mechanism for recognizing an illusory contour using the example of “Kanizsa’s figures”. The neural network made it possible to achieve invariance to the number of corners of the figure and does not lose recognition quality when changing the size of the illusory contour. The main application of the approach can be found in the problem of separating “figure-background” in images.

The new method for the tsunami travel times calculation to the nodes of rectangular grid was developed and tested. The algorithm is based on constructing of the wave front segment inside the grid cell using tsunami arrival times to the cell corners. Testing the method proposed shows the better quality of the wave-front line approximation as compared to the existing method developed by the author earlier.

The current trends in the development of production dictate the need to increase competitiveness by bridging the gap between the organization of production and digital technologies. To improve production efficiency, lean manufacturing strategies are being implemented that focus on identifying and minimizing waste and eliminating them. At the same time, the capabilities of digital transformation allow monitoring of production processes in real time. Thus, it is possible to use lean manufacturing tools such as a value stream map to effectively capture processes and predict the production situation in a dynamic mode. In the developed automated system for dynamic mapping of the value stream, the principle of simulation is implemented. With the help of simulations, it is possible to study the alternatives for improving the process and the impact of the proposed changes before implementation. Dynamic modeling of the value stream map allows you to develop an automated control system with the definition of optimal parameters and modes of operation of the production process. The object of modeling is a value stream map that displays the stages of movement of flows of materials, parts, assembly units and information. To investigate the parameters of the production process and implement the principles of lean manufacturing, dynamic mapping of the current state value stream and modeling of the future state were implemented.

The article describes the process of automating Windows administration, in particular, automating the process of creating and distributing SSL certificates to servers. The built-in command shell PowerShell is used for development. Theoretical aspects of the subject are given: the concept of SSL certificates, the purpose of Vault storage and Consul service. The results of development in the form of code listings are presented.