Electrical tomography is a non-invasive method of monitoring the interior of objects, which is used in various industries. In particular, it is possible to monitor industrial processes inside reactors and tanks using tomography. Tomography enables real-time observation of crystals or gas bubbles growing in a liquid. However, obtaining high-resolution tomographic images is problematic because it involves solving the so-called ill-posed inverse problem. Noisy input data cause problems, too. Therefore, the use of appropriate hardware solutions to eliminate this phenomenon is necessary. An important cause of obtaining accurate tomographic images may also be the incorrect selection of algorithmic methods used to convert the measurements into the output images. In a dynamically changing environment of a tank reactor, selecting the optimal algorithmic method used to create a tomographic image becomes an optimization problem. This article presents the machine learning method’s original concept of intelligent selection depending on the reconstructed case. The long short-term memory network was used to classify the methods to choose one of the five homogenous methods—elastic net, linear regression with the least-squares learner, linear regression with support vector machine learner, support vector machine model, or artificial neural networks. In the presented research, tomographic images of selected measurement cases, reconstructed using five methods, were compared. Then, the selection methods’ accuracy was verified thanks to the long short-term memory network used as a classifier. The results proved that the new concept of long short-term memory classification ensures better tomographic reconstructions efficiency than imaging all measurement cases with single homogeneous methods.

This article presents research results on a smart building prediction, navigation and asset management system. The main goal of this work was to combine all comfort subsystems, such as lighting, heating or air conditioning control, into one coherent management system supported by navigation using radio tomographic imaging techniques and computational intelligence in order to improve the building’s ability to track users and then maximize the energy efficiency of the building by analyzing their behavior. In addition, the data obtained in this way were used to increase the quality of navigation services, improve the safety and ergonomics of using the room access control system and create a centralized control panel enriched with records of the working time of individual people. The quality of the building’s user habit learning is ensured by a network of sensors collecting environmental data and thus the setting values of the comfort modules. The advantage of such a complex solution is an increase in the accuracy of navigation services provided, an improvement in the energy balance, an improvement in the level of safety and faster facility diagnostics. The solution uses proprietary small device assemblies with implementation of popular wireless transmission standards such as Bluetooth, Wi-Fi, ZigBee or Z-Wave. These PANs (personal area networks) are used to update and transmit environmental and navigation data (Bluetooth), to maintain the connection of other PANs to the master server (Wi-Fi) and to communicate with specific end devices (ZigBee and Z-Wave).

Purpose:The aim of the article is an industrial system platform for diagnostics and control of the crystallization process with the use of tomographic technologies. Design/Methodology/Approach: Various methods are used to study crystallization processes. Here, the tomographic method has been applied. Findings: Tomography of industrial processes is a harmless, non-invasive imaging technique used in various industrial in-process technologies. It plays an important role in continuous data measurement for better understanding and monitoring of industrial processes, providing a fast and dynamic response that facilitates real-time process control, fault detection and system malfunctions. Practical Implications: Sensor networks with their feedback loops are fundamental elements of production control. A critical difference in the mass production of chemicals, metals, building materials, food and other commodities is that common process sensors provide only local measurements, e.g. temperature, pressure, fill level, flow rate or species concentration. However, in most production systems such local measurements are not representative of the entire process, so spatial solutions are required. Here the future belongs to distributed and image sensors. Originality/Value: The concept of a system based on industrial tomography represents a solution currently unavailable on the world market, in its assumptions and effects it has a legitimate character of innovation on a global scale. At the same time, it means the creation of a new, fundamentally different from those available on the market, universal product in the technological sphere. It is an innovative, efficient tool for diagnostics and process control.

The start of the full-scale Russian-Ukrainian war caused the largest wave of migration in the 21st century. More than five million Ukrainian citizens left for EU countries within a few months of the start of the conflict. The purpose of this paper is to forecast the level of health care expenditure in Ukraine for 2023–2024, considering the scale of migration and the fall in the level of GDP. The authors propose three scenarios for the development of Ukraine’s economy in 2023–2024, taking into account changes in the age structure of the population, migration, and the amount of health care expenditure: (1) Pessimistic, in which economic growth will resume only in 2024, with a GDP rise of 5.6%, provided that the war concludes at the end of 2022. Under this scenario, inflation will be about 21% in 2023–2024, a slight decrease compared with the previous year. Some 12% of the population of Ukraine will have emigrated, resulting in a corresponding 12% drop in health care expenditure in 2023–2024. (2) Basic (realistic), in which economic growth will be about 5% in 2023–2024, inflation will be under 10%, and migration will have accounted for 5% of the country’s population. Under this scenario, there will be an increase in health care expenditure of more than 40% in 2023–2024. (3) Optimistic, according to which rapid economic growth is expected in 2023–2024, inflation will not exceed 7%, the majority of those who left Ukraine in the early months of the war will return, and health care expenditure will increase by more than 70% in 2023–2024. The methodology of forecasting public expenditure on health care has been based on a six-step cohort method. The results have indicated that the cost of updating the age structure of Ukraine’s population every year will decrease due to the aging of the population, and the overall impact of demographic processes will be negative. The impact of mass migration due to the war creates a significant change in health care costs, requiring administrative bodies to monitor the situation promptly and make appropriate changes to the structure of budget expenditure.

The article presents the results of expert assessment of the quality of three different branch of trucks in terms of their suitability for long-term rental. The expert assessment is faster and cheaper compared to the analogous evaluation obtained on the basis of operational tests, hence the purpose of this article is to assess the accuracy of the results obtained in expert studies. The reliability characteristics of vehicles, such as: readiness, probability of first failure and distribution of mileage between successive repairs, were used as parameters for empirical quality assessment. Operational tests covered three groups of 30 vehicles. As part of the research, changes in vehicle technical readiness occurring during operation were also assessed. The failures of individual functional systems of the vehicle were also analyzed, which were compared with the results of expert studies. The expert assessment was based on a questionnaire regarding the overall assessment of the reliability and performance of cars. 32 experts - appraisers, with good knowledge of the construction of cars of the tested brands participated in these studies. On the basis of comparisons of the results of the expert assessment with the results of empirical studies, conclusions were drawn regarding the correctness of the assessment made by experts.