Analyzed three swarm intelligence algorithms, namely Ant Colony Optimization (ACO), Bee Colony Optimization (BCO), Particle Swarm Optimization (PSO) and the adaptability of these algorithms to a dynamic environment. Firstly, the ACO algorithm was analyzed, the behavior of ants in nature, the purpose of the algorithm, and its shortcomings in a dynamic environment. Then the existing modifications of this algorithm to changing environments were investigated, namely AСO with dynamic pheromone updating (AACO), ACO with adaptive memory (ACO-AP), ACO with multi-agent system (MAS-ACO), ACO with machine learning algorithms (MLACO). The advantages and disadvantages of these modifications are also discussed in detail. The software tools that implement the functionality of this algorithm, such as AntTweakBar, AntOpt, EasyAnt have been mentioned. These software tools provide an opportunity to develop new modifications of the ACO algorithms and to study existing ones. Furthermore, the capabilities of the BCO algorithm were clarified and the behavior and parameters of this algorithm were described, its pros and cons in a dynamic environment were investigated. The following BCO modifications were considered: Group Bee Algorithm (GBA), Artificial Bee Colony (ABC), and open source software: PySwarms, PyABC. The third part of the article investigates the work of the PSO algorithm, its advantages and disadvantages of adaptation to dynamic environments. Dynamic Particle Swarm Optimization with Permutation (DPSO-P), Dynamic Multi-swarm Particle Swarm Optimization Based on Elite Learning (DMS-P50-EL) are considered as modifications of PSO to adapt to dynamic environments. The libraries for work such as SciPy, DEAP, PyGAD, Particleswarm, JSwarm (has a wide API and well-written documentation), Dlib have been mentioned. Finally, a comparative table with the most important properties (resistance to environmental changes, complexity of implementation, the possibility of using for a UAV swarm, etc.) for all three algorithms was created, a brief description of similar articles comparing algorithms of swarm intelligence was also made, and the conclusions of the study were drawn.

 618.7-06:616.16-005.6

Тромботична мікроангіопатія (ТМА) - це гетерогенна група захворювань, які за наявності пошкодження ендотелію можуть призводити до тромбозу малих та мікросудин, вторинного споживання тромбоцитів, механічного гемолізу та ішемічного ураження кінцевих органів. Залежно від залучених органів можуть виникати ниркова недостатність, неврологічні симптоми, кардіальна патологія, дихальна недостатність,
порушення зору, панкреатит, ішемія кишківника і (рідше) зміни шкіри .
Така характерна тріада симптомів, як гостра ниркова недостатність (ГНН), мікроангіопатичний гемоліз і тромбоцитопенія, може також супроводжувати деякі специфічні для вагітності стани (зокрема, тяжку прееклампсію/HELLP-синдром (гемоліз, підвищення рівня печінкових ферментів та низька кількість тромбоцитів) , гостру жирову дистрофію печінки вагітних (ГЖДП), а також захворювання, не пов`язані з
вагітністю, але спровоковані нею (катастрофічний антифосфоліпідний синдром (кАФС)
[9], загострення системного червоного вовчаку (СЧВ)). Постає питання ранньої діагностики різних типів ТМА під час вагітності, їх диференційної діагностики з іншими ускладненнями перебігу гестаційного процесу та
проведення цілеспрямованої патогенетичної терапії.

The article presents the design and technological features of creating color labels-sensors of microelectromechanical systems intended for monitoring physicochemical parameters under the conditions of high- level electromagnetic interference. The software module of the hardware and software complex for the visualization of spectral intensity by converting it into an RGB colour model has been created. The algorithm for carrying out the procedure for calculating the color rendering index is shown and the main parameters of temperature colors in a wide range of visible radiation waves are determined 

The work proposes the use of a unique method of creating passive, multifunctional, non-contact pressure-temperature sensors. The basis of this method is a combination of inorganic semiconductors and high-molecular organic cholesteric crystals. According to their morphology, such crystals represent a spiral structure that is sensitive to changes in external physical factors, such as temperatures, due to changes in the periodicity of the structure, which leads to Bragg diffraction scattering of light on it. The consequence of such influence is the coloring of the cholesteric, which can be identified by external spectrosensitive devices on a non-contact basis. On the other hand, the use of inorganic semiconductors involves the production of a micro-profiled base with a thin silicon membrane that is sensitive to external pressure. The thickness of the membrane determines the operating conditions of the sensor depending on the range of applied pressure from 0.3 bar and above. A hardware and software complex was developed for continuous monitoring of changes in the color of passive pressure-temperature sensors, tracking the spectral distribution of the light intensity of the color of the liquid crystal depending on the operating conditions on a non-contact basis with an external spectrometer. The basis of such a system is a software module created on the basis of the MVVM (Model–View–View Model) architecture template. A feature of the software module is the use of the .NET and WPF frameworks, which natively support this architectural pattern for .NET Windows platforms and are supported by all popular versions of operating systems. The SQlite database, which is a relational database management system, is used to store data in the software application. The OmniDriver library was used in the system to operate and configure the spectrometer. The software module has two modes of operation with spectrometers. The first mode is characterized by the reading of a single spectrum, while the second mode is characterized by periodic reading and processing of the intensity spectral distribution in real time with a given period. When using the second mode, the software module allows you to dynamically change the periods and parameters of changing the color parameters of the light over time. The main algorithm of the software module is the transformation of the spectral intensity distribution normalized in the CIE XYZ color model, which is the basis for all further calculations, into the RGB model.

Since the outbreak of the pandemic in 2019, Covid-19 has become one of the most important topics in the field of medicine. This disease, caused by the SARSCoV-2 virus, can lead to serious respiratory diseases and other complications. They can even lead to death. In recent years, the number of Covid-19 cases around the world has increased significantly, resulting in the need for rapid and effective diagnosis of the disease. Currently, the use of deep learning in medical diagnostics is becoming more and more common. It provides the high diagnostic efficacy that scientists, doctors and patients care about. During the Covid-19 diagnostic procedure, most clinicians order images from Xray and CT to be taken from patients. It is the analysis of these images that gives a full diagnosis. In this article, we will discuss the use of deep neural networks in the diagnosis of Covid-19, especially using chest images taken from X-ray and CT.