A processing of border pixel from pixel map originate problem while work with outline objects segmentation algorithm on bitmap images, which are based on 2D convolution operation. The problem correspond with addition set of pixels which are outside pixel matrix border of processing image. This problem is actual also in other algorithms, which have a common feature – 2D convolution operation. The level of importance are defined by multi used nonlinear filters to border pixels and then union a few images without distortions at the boundaries. The existing methods of pixel set redefining on pre processing step are primitive and affects on subsequent stages of processing. This affects exist between methods of redefining border pixels and algorithms of outline objects segmentation: Sharra, Pruitta, Sobel. The object of investigation is pixel map of halftone image. The subject of investigation is relation assessment between algorithms of outline objects segmentation with methods redefining border pixels. The main target is describing of features special methods to redefining border pixels which positively affecting the subsequent evaluation of the responses for this pixels by algorithms of outline objects segmentation. Analysis, the influence of the algorithm for the outline objects segmentation on the boundary pixels from the preliminary selection of methods of redefinition is carried out by example of combining several satellite images along the outline of urban infrastructure. For simplicity and by necessary of large data volume visualization (pixel half tone matrix size) presented graphs: halftone codes for redefining and border pixels, pixels requests for the algorithm of outline objects segmentation. By analysis criteria and characteristics of an effective method of redefining boundary pixels are described with correspond affects on algorithms of outline objects segmentation on bitmap images.

Diabetic retinopathy is one of the main side effects of diabetes, which causes severe effects, including blindness. The main challenge is the early diagnosis of this disease for timely and effective treatment. Diabetic retinopathy can be detected much faster and more accurately by using machine learning methods for image analyzing of the human retina. The development of methods and algorithms for the detection and classification of this disease, the automation of this process are the actual and costeffective goals.

The article focuses on the classification of the stages of diabetic retinopathy using neural networks based on human retinal images. Classification problem of diabetic retinopathy stages is described.

The architecture of deep neural networks based on VGG16 and VGG19 with the addition of custom layers is proposed. Recommendations for the selection of the size of the initial retinal images and the preprocessing stage (cropping) are given As a result of the performed experimental research. Analysis of the dataset was performed. Neural network models were trained and results were evaluated with class imbalance taken into account.

This article describes the software implementation of the system for extracting and evaluating information features from 2D images of bone fractures and bone objects for classifying fractures and identifying the alleged instrument that caused the injury. As parameters, the textural characteristics of Haralick, local binary patterns of pixels for 2D images, Gabor filters, Laws energy texture characteristics for 2D images are considered. The analysis carried out on basis of information content estimation to select the features that are most suitable for solving the problem of bone fractures classification. The results will be used for development of methods for complex forensic examination of complex polygonal surfaces of solid objects for automated system for analyzing digital images.

In this study, using the model of passenger flow formation on a conditional transport network based on the iterative process of changes in the passenger flows and velocities, the need for high-speed public transport, in particular, the subway, is estimated. The model allows the formation of the route of potential high-speed transport based on the calculated passenger flows. The results of the experiment are presented for the example of the Krasnodar transport system for three periods – 2007, 2017, 2022.

Given article is devoted features of the decision of a problem of planning of a route of a pilotless flying machine (UAV). The decision of a considered problem is offered to be carried out in two consecutive stages. At the first stage calculation of optimum closed route UAV is carried out. Thus as an efficiency indicator the fuel resource, and as criterion of an optimality of a route a minimum of the general expense of fuel is accepted. Efficiency of the received decision is estimated in relation to the known algorithm LinKernighan realised in application Concorde 1.1.  At the second stage by means of the developed algorithm updating of found route UAV taking into account an available stock of fuel is carried out, i.e. The question on returning UAV or after replenishment of a stock of fuel in intermediate point of continuation of flight of the remained sites is solved.

The work is devoted to solving the problem of topological optimization in the design of lightweight structures. The advantages and disadvantages of popular topological optimization methods are analyzed. One of the characteristic problems of all methods is the dependence of their results on grid partitioning. Besides, there is a necessity to recast the geometry model of the structure. To solve this problem, it is proposed to perform the formation of cavities based on the ESO method directly at the constructive solid geometry from the shape elements. The main stages of the proposed approach are described, the use of clustering to simplify the shape of the surfaces of the formed cavities is justified.

A formal description of the mathematical model of a steganographic system based on key information in the form of stegosets is given. The mathematical model of the steganographic system is intended both for placing hidden marks to control the integrity of documents acting as a container, and for covert data transmission. Exist-ing mathematical models do not fully meet the requirements for steganographic systems. The proposed model is based on the concepts of a three-level key, a stegoset, a container component, and a message block. The three-level key is a set of actual steganographic transformations depending on the type of container. A stegoset is an element of a key set. A component of a container is such a subset of it that there is a stegoset for it. A message block is such a sequential part of the message that there is a container component for it, in which it can be hidden using the appropriate stegoset. The model implements the application of different stegosets to different container compo-nents, and the message can be divided into blocks. The model allows controlling the integrity of the message and adapts to different types of containers. Possible options for the practical application of the mathematical model are proposed, such as monitoring the integrity of the message when calculating the control number, splitting the message into blocks and sequentially monitoring their integrity by analogy with the blockchain system.

FEM simulation of Eddystone lighthouse is provided. Incorporated bionic tower is modelled as well. Load cases including gravity force, wind thrust, water stream and 50-year wave impulse are accomplished. Stress concentrator system is described. Effect of tension stress concentrator compensation caused by gravity is showed. Low gradient stress dispensation is demonstrated for bionic tower outer surfaces. Recommendation touching places to monitor are given.

Methodic experience related to interactive one-command student – professor FEM simulation of responsible load-bearing systems is collected.