The article continues the study devoted to the design of automatic plant phenotyping systems. This topic of scientific research is now widely developed. The intensive development of digital technologies in agribusiness can significantly increase labor productivity, reduce errors in the visual analysis of plant health, and as a result, increase productivity. It is commonly known that building an automatic plant phenotyping system requires mass analysis of a large number (about a thousand) of plants through digital image processing. As a key element of the automatic phenotyping system, the convolutional neural network apparatus is used. This apparatus analyzes the characteristics of plant leaves under the influence of the external environment for the presence of diseases and morphological features of the plant. The analysis of the quality of the automatic phenotyping system based on convolutional neural networks shows a high efficiency of plant disease assessment. As a component of the adaptation of the control system, we use the E-network graph, which allows forming a control vector for the technical vision system and the development of agronomic recommendations.

The interaction of the user with the information system in the process of solving various tasks within the service provided by the information service is investigated. The use of an ontological model, objects participating in it, and their interconnections are substantiated. For this, an overview of similar existing models to the subject area is used. An original author’s ontological model is proposed. It introduces the basic concepts such as a user, task, information service, request service, control service, game service, information system, database, interaction, scheme, model, script, interface, form, graphic element. The nesting of model elements into each other and interaction between them is indicated.
The model is depicted in graphical and tabular form. The ways of further research and application predictions of the results are determined.

The article discusses the use of virtual containers, which can improve data processing efficiency and enable customers to quickly deploy innovative solutions to modernize applications and use cloud-based applications based on microservices. It states that containerization helps accelerate the release of new versions of software, provides portability between hybrid and multi-cloud environments, and also reduces infrastructure and operational costs. The concept of a medical information system of a cardiovascular surgeon-phlebologist with the use of virtual containers is described, as well as a system for collecting phlebology data in two versions.

The purpose of this study is to develop a polling method in real-time systems based on the RS-485 standard, which would help to get rid of common problems. These problems include the data redundancy and polling of an insufficiently large number of devices in real time. The scientific novelty in the work is the approach to solving this problem at the hardware level using a microcontroller. As a result of the research, a method was developed that works according to the modernized DCON data exchange protocol.

An algorithm for finding a sufficient amount of a representative set of sample data for training artificial neural networks using the numerical parameters of the original sample set is proposed. The algorithm is carried out on the example of analyzing a vector signal generated by a gas analytical multisensor micro-arrays based on a thin SnO2 film when calibrated to the effect of CO, isopropanol, and ethanol in a mixture with air. As a result of the operation of the algorithm, the minimum required volume of the training sample of artificial neural networks was found, which allows achieving a high (more than 99 %) recognition quality. The results show the efficiency of the proposed algorithm.

The paper presents the results of the control of air leaks into a vacuum system and the dependence of its value on the parameters of the leak hole. To obtain these data, an experimental installation based on a capacitive pressure sensor was created. The process of air leak into the vacuum system through various calibrated holes is experimentally investigated. It is established that the change in the air pressure in the system can be described by an exponential function. Moreover, the
nature of the leakage for all holes is the same, only the value of the exponent changes, which depends on the parameters of the hole. Analysis of the obtained data showed that this parameter decreases with increasing hole length and increases with increasing its cross-sectional area.

The paper presents the results of numerical simulation of the flow of a thin liquid layer with a free surface. The simulation was performed at moderate Reynolds numbers within the framework of the partial differential equation for the state of the free surface of the film. Equation coefficients include various physicochemical factors, namely surface tension, and temperature gradients.
Computational experiments are carried out for a thin layer of a viscous liquid. The modes of free runoff, evaporation and counter flow are investigated. The values of the wave characteristics are found. The flows of a liquid film with the maximum value of the growth rate are identified. Such modes have been recorded in experimental studies by other scientists. The results of modeling the wave surface of a liquid film in Python are presented. The results can be used in the design or modernization of existing equipment, as well as in the development of technological processes in liquid films.

Numerical studies are performed with the two-dimensional axisymmetric model of gas hydrate decomposition in porous media under the action of microwave heating. The system of equations describing the above process includes the mass balance equations of gas, water and hydrate phases, the energy balance equation, generalized Darcy’s law for water and gas, and the Kim–Bishnoi kinetics equation for hydrate decomposition reaction. The system of equations resolves itself into four differential equations relative to temperature, pressure, volume hydrate, water, and gas saturation with appropriate boundary and initial conditions. Simulation of gas hydrate decomposition in porous media under the action of microwave heating is carried out by finite element method. Physical parameters characteristic of a typical hydrate reservoir are used in the modeling. The reservoir was heated for ten days. Spatial and temporal distribution of temperature, pressure, hydrate, water, and gas saturation were obtained. The mass of gas evolved during hydrate dissociation was determined. The calculation of the energy efficiency of electromagnetic heating was carried out. These results are quite usable from a practical standpoint, and the electromagnetic heating method is technically achievable and competitive.